| 1. |
- Scandurra, Isabella, 1973-, et al.
(författare)
-
Advancing the State-of-the-Art for Virtual Autopsies : Initial Forensic Workflow Study
- 2010
-
Ingår i: Studies in Health Technology and Informatics. - : IOS Press. - 0926-9630 .- 1879-8365. ; 160, s. 639-643
-
Tidskriftsartikel (refereegranskat)abstract
- There are numerous advantages described of how imaging technology can support forensic examinations. However, postmortem examinations of bodies are mainly performed to address demands which differ from those of traditional clinical image processing. This needs to be kept in mind when gathering information from image data sets for forensic purposes. To support radiologists and forensicclinicians using Virtual Autopsy technologies, an initial workflow study regarding post-mortem imaging has been performed, aiming to receive an improved understanding of how Virtual Autopsyworkstations, image data sets and processes can be adjusted to support and improve conventional autopsies. This paper presents potential impacts and a current forensic Virtual Autopsy workflowaiming to form a foundation for collaborative procedures that increase the value of Virtual Autopsy. The workflow study will provide an increased and mutual understanding of involved professionals. In addition, insight into future forensic workflows based on demands from both forensic and radiologist perspectives bring visualization and medical informatics researchers together to develop and improvethe technology and software needed.
|
|
| 2. |
- Asa, Sylvia, et al.
(författare)
-
2020 vision of digital pathology in action
- 2019
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 10:27
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 3. |
- Cervin, Ida, et al.
(författare)
-
Improving the creation and reporting of structured findings during digital pathology review
- 2016
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 7:1, s. 32-32
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Today, pathology reporting consists of many separate tasks, carried out by multiple people. Common tasks include dictation during case review, transcription, verification of the transcription, report distribution, and report the key findings to follow-up registries. Introduction of digital workstations makes it possible to remove some of these tasks and simplify others. This study describes the work presented at the Nordic Symposium on Digital Pathology 2015, in Linköping, Sweden. Methods: We explored the possibility to have a digital tool that simplifies image review by assisting note-taking, and with minimal extra effort, populates a structured report. Thus, our prototype sees reporting as an activity interleaved with image review rather than a separate final step. We created an interface to collect, sort, and display findings for the most common reporting needs, such as tumor size, grading, and scoring. Results: The interface was designed to reduce the need to retain partial findings in the head or on paper, while at the same time be structured enough to support automatic extraction of key findings for follow-up registry reporting. The final prototype was evaluated with two pathologists, diagnosing complicated partial mastectomy cases. The pathologists experienced that the prototype aided them during the review and that it created a better overall workflow. Conclusions: These results show that it is feasible to simplify the reporting tasks in a way that is not distracting, while at the same time being able to automatically extract the key findings. This simplification is possible due to the realization that the structured format needed for automatic extraction of data can be used to offload the pathologists' working memory during the diagnostic review.
|
|
| 4. |
- Chow, Joyce A, et al.
(författare)
-
A design study investigating augmented reality and photograph annotation in a digitalized grossing workstation
- 2017
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 8
-
Tidskriftsartikel (refereegranskat)abstract
- Context: Within digital pathology, digitalization of the grossing procedure has been relatively underexplored in comparison to digitalization of pathology slides. Aims: Our investigation focuses on the interaction design of an augmented reality gross pathology workstation and refining the interface so that information and visualizations are easily recorded and displayed in a thoughtful view. Settings and Design: The work in this project occurred in two phases: the first phase focused on implementation of an augmented reality grossing workstation prototype while the second phase focused on the implementation of an incremental prototype in parallel with a deeper design study. Subjects and Methods: Our research institute focused on an experimental and “designerly” approach to create a digital gross pathology prototype as opposed to focusing on developing a system for immediate clinical deployment. Statistical Analysis Used: Evaluation has not been limited to user tests and interviews, but rather key insights were uncovered through design methods such as “rapid ethnography” and “conversation with materials”. Results: We developed an augmented reality enhanced digital grossing station prototype to assist pathology technicians in capturing data during examination. The prototype uses a magnetically tracked scalpel to annotate planned cuts and dimensions onto photographs taken of the work surface. This article focuses on the use of qualitative design methods to evaluate and refine the prototype. Our aims were to build on the strengths of the prototype's technology, improve the ergonomics of the digital/physical workstation by considering numerous alternative design directions, and to consider the effects of digitalization on personnel and the pathology diagnostics information flow from a wider perspective. A proposed interface design allows the pathology technician to place images in relation to its orientation, annotate directly on the image, and create linked information. Conclusions: The augmented reality magnetically tracked scalpel reduces tool switching though limitations in today's augmented reality technology fall short of creating an ideal immersive workflow by requiring the use of a monitor. While this technology catches up, we recommend focusing efforts on enabling the easy creation of layered, complex reports, linking, and viewing information across systems. Reflecting upon our results, we argue for digitalization to focus not only on how to record increasing amounts of data but also how these data can be accessed in a more thoughtful way that draws upon the expertise and creativity of pathology professionals using the systems.
|
|
| 5. |
- Cossío, Fernando, et al.
(författare)
-
VAI-B: a multicenter platform for the external validation of artificial intelligence algorithms in breast imaging
- 2023
-
Ingår i: Journal of Medical Imaging. - : SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS. - 2329-4302 .- 2329-4310. ; 10:06
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Multiple vendors are currently offering artificial intelligence (AI) computer-aided systems for triage detection, diagnosis, and risk prediction of breast cancer based on screening mammography. There is an imminent need to establish validation platforms that enable fair and transparent testing of these systems against external data.Approach: We developed validation of artificial intelligence for breast imaging (VAI-B), a platform for independent validation of AI algorithms in breast imaging. The platform is a hybrid solution, with one part implemented in the cloud and another in an on-premises environment at Karolinska Institute. Cloud services provide the flexibility of scaling the computing power during inference time, while secure on-premises clinical data storage preserves their privacy. A MongoDB database and a python package were developed to store and manage the data on-premises. VAI-B requires four data components: radiological images, AI inferences, radiologist assessments, and cancer outcomes.Results: To pilot test VAI-B, we defined a case-control population based on 8080 patients diagnosed with breast cancer and 36,339 healthy women based on the Swedish national quality registry for breast cancer. Images and radiological assessments from more than 100,000 mammography examinations were extracted from hospitals in three regions of Sweden. The images were processed by AI systems from three vendors in a virtual private cloud to produce abnormality scores related to signs of cancer in the images. A total of 105,706 examinations have been processed and stored in the database.Conclusions: We have created a platform that will allow downstream evaluation of AI systems for breast cancer detection, which enables faster development cycles for participating vendors and safer AI adoption for participating hospitals. The platform was designed to be scalable and ready to be expanded should a new vendor want to evaluate their system or should a new hospital wish to obtain an evaluation of different AI systems on their images.
|
|
| 6. |
- Eilertsen, Gabriel, 1984-, et al.
(författare)
-
Ensembles of GANs for synthetic training data generation
- 2021
-
Konferensbidrag (refereegranskat)abstract
- Insufficient training data is a major bottleneck for most deep learning practices, not least in medical imaging where data is difficult to collect and publicly available datasets are scarce due to ethics and privacy. This work investigates the use of synthetic images, created by generative adversarial networks (GANs), as the only source of training data. We demonstrate that for this application, it is of great importance to make use of multiple GANs to improve the diversity of the generated data, i.e. to sufficiently cover the data distribution. While a single GAN can generate seemingly diverse image content, training on this data in most cases lead to severe over-fitting. We test the impact of ensembled GANs on synthetic 2D data as well as common image datasets (SVHN and CIFAR-10), and using both DCGANs and progressively growing GANs. As a specific use case, we focus on synthesizing digital pathology patches to provide anonymized training data.
|
|
| 7. |
- Falk, Martin, Dr.rer.nat. 1981-, et al.
(författare)
-
Feature Exploration in Medical Volume Data using Local Frequency Distributions
- 2020
-
Konferensbidrag (refereegranskat)abstract
- Frequency distributions (FD) are an important instrument when analyzing and investigating scientific data. In volumetric visualization, for example, frequency distributions visualized as histograms, often assist the user in the process of designing transfer function (TF) primitives. Yet a single point in the distribution can correspond to multiple features in the data, particularly in low-dimensional TFs that dominate time-critical domains such as health care. In this paper, we propose contributions to the area of medical volume data exploration, in particular Computed Tomography (CT) data, based on the decomposition of local frequency distributions (LFD). By considering the local neighborhood utilizing LFDs we can incorporate a measure for neighborhood similarity to differentiate features thereby enhancing the classification abilities of existing methods. This also allows us to link the attribute space of the histogram with the spatial properties of the data to improve the user experience and simplify the exploration step. We propose three approaches for data exploration which we illustrate with several visualization cases highlighting distinct features that are not identifiable when considering only the global frequency distribution. We demonstrate the power of the method on selected datasets.
|
|
| 8. |
- Falk, Martin, Dr.rer.nat. 1981-, et al.
(författare)
-
Interactive Visualization of 3D Histopathology in Native Resolution
- 2019
-
Ingår i: IEEE Transactions on Visualization and Computer Graphics. - : Institute of Electrical and Electronics Engineers (IEEE). - 1077-2626 .- 1941-0506 .- 2160-9306. ; 25:1, s. 1008-1017
-
Tidskriftsartikel (refereegranskat)abstract
- We present a visualization application that enables effective interactive visual analysis of large-scale 3D histopathology, that is, high-resolution 3D microscopy data of human tissue. Clinical work flows and research based on pathology have, until now, largely been dominated by 2D imaging. As we will show in the paper, studying volumetric histology data will open up novel and useful opportunities for both research and clinical practice. Our starting point is the current lack of appropriate visualization tools in histopathology, which has been a limiting factor in the uptake of digital pathology. Visualization of 3D histology data does pose difficult challenges in several aspects. The full-color datasets are dense and large in scale, on the order of 100,000 x 100,000 x 100 voxels. This entails serious demands on both rendering performance and user experience design. Despite this, our developed application supports interactive study of 3D histology datasets at native resolution. Our application is based on tailoring and tuning of existing methods, system integration work, as well as a careful study of domain specific demands emanating from a close participatory design process with domain experts as team members. Results from a user evaluation employing the tool demonstrate a strong agreement among the 14 participating pathologists that 3D histopathology will be a valuable and enabling tool for their work.
|
|
| 9. |
- Ghita, Cristina, 1986-
(författare)
-
Technology in Absentia : A New Materialist Study of Digital Disengagement
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The rhetoric associated with society-wide digitalisation promises benefits such as increased quality of life, democracy, or sustainability, which point towards normative trajectories of increased automation and digitalisation of nearly all aspects of society. Meanwhile, there is evidence of a disenchantment with digital use, forming a movement that challenges the pervasiveness of digital artefacts such as the smartphone. This kind of scepticism towards digital technologies is currently informing and changing how we assume, understand, and conceptualise technology in our professional and private lives, leading to an emerging trend of volitionally reducing or postponing the use of digital devices – a practice often labelled as digital disengagement. In this dissertation the research lens is directed towards how the disengagement from ubiquitous digital devices unfolds and to what results. Thus, it investigates the productive potential of technology intentionally made absent, repositioning the traditional approach of articulating such absence as a deficit.Drawing on a new materialist perspective of technology use which combines assemblage theory with agential realism, this dissertation explores the search for meaningful technological encounters through a multi-sited ethnographic approach. More specifically, it combines autoethnography, a diary study, interviews, participatory observations, and netnography in which moments of disconnection are observed in order to understand experiences of digital disengagement at individual and collective levels. Through this lens, the performativity, temporality, and productivity of digital disengagement are made visible and analysed. Results show that digital disengagement is not an insular practice, including in its composition a myriad of external components. Digitalisation is shown to be in direct dialogue with practices of digital disengagement through their mutual dichotomic logics. Further analysis of such dichotomies suggests new manners of engaging with technology in which digital use and non-use are entangled, resulting in a novel type of technology engagement called diffractive digital use
|
|
| 10. |
- Hedlund, Joel, 1978-, et al.
(författare)
-
Key insights in the AIDA community policy on sharing of clinical imaging data for research in Sweden
- 2020
-
Ingår i: Scientific Data. - : Springer Nature. - 2052-4463. ; 7
-
Tidskriftsartikel (refereegranskat)abstract
- Development of world-class artificial intelligence (AI) for medical imaging requires access to massive amounts of training data from clinical sources, but effective data sharing is often hindered by uncertainty regarding data protection. We describe an initiative to reduce this uncertainty through a policy describing a national community consensus on sound data sharing practices.
|
|
| 11. |
|
|
| 12. |
- Kost, Henning, et al.
(författare)
-
Training nuclei detection algorithms with simple annotations
- 2017
-
Ingår i: Journal of Pathology Informatics. - : Elsevier BV. - 2229-5089 .- 2153-3539. ; 8:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.
|
|
| 13. |
- Lindholm, Stefan, et al.
(författare)
-
Spatial Conditioning of Transfer Functions Using Local Material Distributions
- 2010
-
Ingår i: IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS. - : IEEE. - 1077-2626. ; 16:6, s. 1301-1310
-
Tidskriftsartikel (refereegranskat)abstract
- In many applications of Direct Volume Rendering (DVR) the importance of a certain material or feature is highly dependent on its relative spatial location. For instance, in the medical diagnostic procedure, the patients symptoms often lead to specification of features, tissues and organs of particular interest. One such example is pockets of gas which, if found inside the body at abnormal locations, are a crucial part of a diagnostic visualization. This paper presents an approach that enhances DVR transfer function design with spatial localization based on user specified material dependencies. Semantic expressions are used to define conditions based on relations between different materials, such as only render iodine uptake when close to liver. The underlying methods rely on estimations of material distributions which are acquired by weighing local neighborhoods of the data against approximations of material likelihood functions. This information is encoded and used to influence rendering according to the users specifications. The result is improved focus on important features by allowing the user to suppress spatially less-important data. In line with requirements from actual clinical DVR practice, the methods do not require explicit material segmentation that would be impossible or prohibitively time-consuming to achieve in most real cases. The scheme scales well to higher dimensions which accounts for multi-dimensional transfer functions and multivariate data. Dual-Energy Computed Tomography, an important new modality in radiology, is used to demonstrate this scalability. In several examples we show significantly improved focus on clinically important aspects in the rendered images.
|
|
| 14. |
- Lindvall, Martin
(författare)
-
Designing with Machine Learning in Digital Pathology : Augmenting Medical Specialists through Interaction Design
- 2021
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Recent advancements in machine learning (ML) have led to a dramatic increase in AI capabilities for medical diagnostic tasks. Despite technical advances, developers of predictive AI models struggle to integrate their work into routine clinical workflows. Inefficient human-AI interactions, poor sociotechnical fit and a lack of interactive strategies for dealing with the imperfect nature of predictions are known factors contributing to this lack of adoption.User-centred design methods are typically aimed at discovering and realising desirable qualities in use, pragmatically oriented around finding solutions despite the limitations of material- and human resources. However, existing methods often rely on designers possessing knowledge of suitable interactive metaphors and idioms, as well as skills in evaluating ideas through low-fidelity prototyping and rapid iteration methods—all of which are challenged by the data-driven nature of machine learning and the unpredictable outputs from AI models.Using a constructive design research approach, my work explores how we might design systems with AI components that aid clinical decision-making in a human-centred and iterative fashion. Findings are derived from experiments and experiences from four exploratory projects conducted in collaboration with professional physicians, all aiming to probe this design space by producing novel interactive systems for or with ML components.Contributions include identifying practical and theoretical design challenges, suggesting novel interaction strategies for human-AI collaboration, framing ML competence for designers and presenting empirical descriptions of conducted design processes. Specifically, this compilation thesis contains three works that address effective human-machine teaching and two works that address the challenge of designing interactions that afford successful decision-making despite the uncertainty and imperfections inherent in machine predictions.Finally, two works directly address design-researchers working with ML, arguing for a systematic approach to increase the repertoire available for theoretical annotation and understanding of the properties of ML as a designerly material.
|
|
| 15. |
- Lindvall, Martin, et al.
(författare)
-
Rapid Assisted Visual Search : Supporting Digital Pathologists with Imperfect AI
- 2021
-
Ingår i: IUI '21: 26th International Conference on Intelligent User Interfaces. - New York, NY, USA : ACM Digital Library. - 9781450380171 ; , s. 504-513
-
Konferensbidrag (refereegranskat)abstract
- Designing useful human-AI interaction for clinical workflows remains challenging despite the impressive performance of recent AI models. One specific difficulty is a lack of successful examples demonstrating how to achieve safe and efficient workflows while mitigating AI imperfections. In this paper, we present an interactive AI-powered visual search tool that supports pathologists in cancer assessments. Our evaluation with six pathologists demonstrates that it can 1) reduce time needed with maintained quality, 2) build user trust progressively, and 3) learn and improve from use. We describe our iterative design process, model development, and key features. Through interviews, design choices are related to the overall user experience. Implications for future human-AI interaction design are discussed with respect to trust, explanations, learning from use, and collaboration strategies.
|
|
| 16. |
- Lindvall, Martin, et al.
(författare)
-
TissueWand, a rapid histopathology annotation tool
- 2020
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 11:27
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Recent advancements in machine learning (ML) bring great possibilities for the development of tools to assist with diagnostic tasks within histopathology. However, these approaches typically require a large amount of ground truth training data in the form of image annotations made by human experts. As such annotation work is a very time-consuming task, there is a great need for tools that can assist in this process, saving time while not sacrificing annotation quality. Methods: In an iterative design process, we developed TissueWand – an interactive tool designed for efficient annotation of gigapixel-sized histopathological images, not being constrained to a predefined annotation task. Results: Several findings regarding appropriate interaction concepts were made, where a key design component was semi-automation based on rapid interaction feedback in a local region. In a user study, the resulting tool was shown to cause substantial speed-up compared to manual work while maintaining quality. Conclusions: The TissueWand tool shows promise to replace manual methods for early stages of dataset curation where no task-specific ML model yet exists to aid the effort.
|
|
| 17. |
- Ljung, Patric, 1968-, et al.
(författare)
-
Forensic Virtual Autopsies by Direct Volume Rendering
- 2007
-
Ingår i: IEEE signal processing magazine (Print). - Piscataway, NJ, USA : IEEE. - 1053-5888 .- 1558-0792. ; 24:6, s. 112-116
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents state-of-the-art methods, which address the technical challenges in visualizing large three-dimensional (3D) data and enable rendering at interactive frame rates.
|
|
| 18. |
- Ljung, Patric, 1968-, et al.
(författare)
-
Full Body Virtual Autopsies Using A State-of-the-art Volume Rendering Pipeline
- 2006
-
Ingår i: IEEE Transactions on Visualization and Computer Graphics. - 1077-2626 .- 1941-0506. ; 12:5, s. 869-876
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a procedure for virtual autopsies based on interactive 3D visualizations of large scale, high resolutiondata from CT-scans of human cadavers. The procedure is described using examples from forensic medicine and the added valueand future potential of virtual autopsies is shown from a medical and forensic perspective. Based on the technical demands ofthe procedure state-of-the-art volume rendering techniques are applied and refined to enable real-time, full body virtual autopsiesinvolving gigabyte sized data on standard GPUs. The techniques applied include transfer function based data reduction using levelof-detail selection and multi-resolution rendering techniques. The paper also describes a data management component for large,out-of-core data sets and an extension to the GPU-based raycaster for efficient dual TF rendering. Detailed benchmarks of thepipeline are presented using data sets from forensic cases.
|
|
| 19. |
- Ljung, Patric, 1968-, et al.
(författare)
-
Multiresolution Interblock Interpolation in Direct Volume Rendering
- 2006
-
Ingår i: Proceedings of Eurographics/IEEE Symposium on Visualization 2006, Lisbon, Portugal. ; , s. 259-266
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- We present a direct interblock interpolation technique that enables direct volume rendering of blocked, multiresolution volumes. The proposed method smoothly interpolates between blocks of arbitrary block-wise level-of-detail (LOD) without sample replication or padding. This permits extreme changes in resolution across block boundaries and removes the interblock dependency for the LOD creation process. In addition the full data reduction from the LOD selection can be maintained throughout the rendering pipeline. Our rendering pipeline employs a flat block subdivision followed by a transfer function based adaptive LOD scheme. We demonstrate the effectiveness of our method by rendering volumes of the order of gigabytes using consumer graphics cards on desktop PC systems.
|
|
| 20. |
- Ljung, Patric, 1968-, et al.
(författare)
-
Transfer Function Based Adaptive Decompresion for Volume Rendering of Large Medical Data Sets
- 2004
-
Ingår i: Proceedings of IEEE/ACM Symposium on Volume Visualization 2004, Austin, USA. - : IEEE. ; , s. 25-32
-
Konferensbidrag (refereegranskat)abstract
- The size of standard volumetric data sets in medical imaging is rapidly increasing causing severe performance limitations in direct volume rendering pipelines. The methods presented in this paper exploit the medical knowledge embedded in the transfer function to reduce the required bandwidth in the pipeline. Typically, medical transfer functions cause large subsets of the volume to give little or no contribution to the rendered image. Thus, parts of the volume can be represented at low resolution while retaining overall visual quality. This paper introduces the use of transfer functions at decompression time to guide a level-of-detail selection scheme. The method may be used in combination with traditional lossy or lossless compression schemes. We base our current implementation on a multi-resolution data representation using compressed wavelet transformed blocks. The presented results using the adaptive decompression demonstrate a significant reduction in the required amount of data while maintaining rendering quality. Even though the focus of this paper is medical imaging, the results are applicable to volume rendering in many other domains.
|
|
| 21. |
- Lundin (Palmerius), Karljohan, et al.
(författare)
-
Enabling Haptic Interaction with Volumetric MRI Data Through Knowledge-based Tissue Separation
- 2006
-
Ingår i: Proceedings of Volume Graphics. ; , s. 75-78
-
Konferensbidrag (refereegranskat)abstract
- Direct volume haptics can provide both guidance and extra information during exploration of volumetric data. In this paper we present a novel approach to volume haptics enabling haptic exploration of tissue shape, borders and material properties in data despite low contrast and low signal to noise ratio, as is common in medical MRI data or low dose CT data. The method uses filtering based on implicit knowledge and addresses the problem of overlapping scalar ranges through the introduction of fuzzy classification and corresponding transfer functions for material properties as well as classification-based distance masking for haptic force direction.
|
|
| 22. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Characterizing visual analytics in diagnostic imaging
- 2011
-
Ingår i: EuroVA 2011. ; , s. 1-4
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Many necessary and desired improvements in healthcare are dependent on progress in medical imaging. As shown in this paper, the challenges targeted by visual analytics (VA) coincide with main challenges for radiologists' diagnostic work. Key prerequisites for VA in this application domain have been identified through analysis of a survey among 22 radiologists at a university hospital. Two major findings are that efficiency is perceived as the most challenging aspect of their diagnostic work and that an exploratory approach is necessary in everyday image review. The presented characterization constitutes a validated input for design of future VA research initiatives within medical imaging.
|
|
| 23. |
- Lundström, Claes, 1973-
(författare)
-
Efficient Medical Volume Visualization : An Approach Based on Domain Knowledge
- 2007
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Direct Volume Rendering (DVR) is a visualization technique that has proved to be a very powerful tool in many scientific visualization applications. Diagnostic medical imaging is one domain where DVR could provide clear benefits in terms of unprecedented possibilities for analysis of complex cases and highly efficient work flow for certain routine examinations. The full potential of DVR in the clinical environment has not been reached, however, primarily due to limitations in conventional DVR methods and tools.This thesis presents methods addressing four major challenges for DVR in clinical use. The foundation of all methods is to incorporate the domain knowledge of the medical professional in the technical solutions. The first challenge is the very large data sets routinely produced in medical imaging today. To this end a multiresolution DVR pipeline is proposed, which dynamically prioritizes data according to the actual impact in the rendered image to be reviewed. Using this prioritization the system can reduce the data requirements throughout the pipeline and provide high performance and visual quality in any environment.Another problem addressed is how to achieve simple yet powerful interactive tissue classification in DVR. The methods presented define additional attributes that effectively captures readily available medical knowledge. The task of tissue detection is also important to solve in order to improve efficiency and consistency of diagnostic image review. Histogram-based techniques that exploit spatial relations in the data to achieve accurate and robust tissue detection are presented in this thesis.The final challenge is uncertainty visualization, which is very pertinent in clinical work for patient safety reasons. An animation method has been developed that automatically conveys feasible alternative renderings. The basis of this method is a probabilistic interpretation of the visualization parameters.Several clinically relevant evaluations of the developed techniques have been performed demonstrating their usefulness. Although there is a clear focus on DVR and medical imaging, most of the methods provide similar benefits also for other visualization techniques and application domains.
|
|
| 24. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Extending and Simplifying Transfer Function Design in Medical Volume Rendering Using Local Histograms
- 2005
-
Ingår i: Proceedings EuroGraphics/IEEE Symposium on Visualization 2005, Leeds, UK. ; , s. 263-270
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Direct Volume Rendering (DVR) is known to be of diagnostic value in the analysis of medical data sets. However, its deployment in everyday clinical use has so far been limited. Two major challenges are that the current methods for Transfer Function (TF) construction are too complex and that the tissue separation abilities of the TF need to be extended. In this paper we propose the use of histogram analysis in local neighborhoods to address both these conflicting problems. To reduce TF construction difficulty, we introduce Partial Range Histograms in an automatic tissue detection scheme, which in connection with Adaptive Trapezoids enable efficient TF design. To separate tissues with overlapping intensity ranges, we propose a fuzzy classification based on local histograms as a second TF dimension. This increases the power of the TF, while retaining intuitive presentation and interaction.
|
|
| 25. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Local histograms for design of Transfer Functions in Direct Volume Rendering
- 2006
-
Ingår i: IEEE Transactions on Visualization and Computer Graphics. - 1077-2626 .- 1941-0506. ; 12:6, s. 1570-1579
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Direct Volume Rendering (DVR) is of increasing diagnostic value in the analysis of data sets captured using the latest medical imaging modalities. The deployment of DVR in everyday clinical work, however, has so far been limited. One contributing factor is that current Transfer Function (TF) models can encode only a small fraction of the user's domain knowledge. In this paper, we use histograms of local neighborhoods to capture tissue characteristics. This allows domain knowledge on spatial relations in the data set to be integrated into the TF. As a first example, we introduce Partial Range Histograms in an automatic tissue detection scheme and present its effectiveness in a clinical evaluation. We then use local histogram analysis to perform a classification where the tissue-type certainty is treated as a second TF dimension. The result is an enhanced rendering where tissues with overlapping intensity ranges can be discerned without requiring the user to explicitly define a complex, multidimensional TF.
|
|
| 26. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Multi-Dimensional Transfer Function Design Using Sorted Histograms
- 2006
-
Ingår i: Proceedings Eurographics/IEEE International Workshop on Volume Graphics 2006, Boston, USA. ; , s. 1-8
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Multi-dimensional Transfer Functions (MDTFs) are increasingly used in volume rendering to produce high quality visualizations of complex data sets. A major factor limiting the use of MDTFs is that the available design tools have not been simple enough to reach wide usage outside of the research context, for instance in clinical medical imaging. In this paper we address this problem by defining an MDTF design concept based on improved histogram display and interaction in an exploratory process. To this end we propose sorted histograms, 2D histograms that retain the intuitive appearance of a traditional 1D histogram while conveying a second attribute. We deploy the histograms in medical visualizations using data attributes capturing domain knowledge e.g. in terms of homogeneity and typical surrounding of tissues. The resulting renderings demonstrate that the proposed concept supports a vast number of visualization possibilities based on multi-dimensional attribute data.
|
|
| 27. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Summary of 2nd Nordic symposium on digital pathology
- 2015
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 6
-
Tidskriftsartikel (refereegranskat)abstract
- Techniques for digital pathology are envisioned to provide great benefits in clinical practice, but experiences also show that solutions must be carefully crafted. The Nordic countries are far along the path toward the use of whole-slide imaging in clinical routine. The Nordic Symposium on Digital Pathology (NDP) was created to promote knowledge exchange in this area, between stakeholders in health care, industry, and academia. This article is a summary of the NDP 2014 symposium, including conclusions from a workshop on clinical adoption of digital pathology among the 144 attendees.
|
|
| 28. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Summary of the 4th Nordic Symposium on Digital Pathology
- 2017
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 8
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- The Nordic symposium on digital pathology (NDP) was created to promote knowledge exchange across stakeholders in health care, industry, and academia. In 2016, the 4th NDP installment took place in Linköping, Sweden, promoting development and collaboration in digital pathology for the benefit of routine care advances. This article summarizes the symposium, gathering 170 attendees from 13 countries. This summary also contains results from a survey on integrated diagnostics aspects, in particular radiology-pathology collaboration.
|
|
| 29. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Summary of third Nordic symposium on digital pathology
- 2016
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 7:12
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Cross-disciplinary and cross-sectorial collaboration is a key success factor for turning the promise of digital pathology into actual clinical benefits. The Nordic symposium on digital pathology (NDP) was created to promote knowledge exchange in this area, among stakeholders in health care, industry, and academia. This article is a summary of the third NDP symposium in Linkφping, Sweden. The Nordic experiences, including several hospitals using whole-slide imaging for substantial parts of their primary reviews, formed a fertile base for discussions among the 190 NDP attendees originating from 15 different countries. This summary also contains results from a survey on adoption and validation aspects of clinical digital pathology use.
|
|
| 30. |
- Lundström, Claes, 1973-
(författare)
-
Technical report: Measuring digital image quality
- 2006
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Imaging is an invaluable tool in many research areas and other advanced domains such as health care. When developing any system dealing with images, image quality issues are insurmountable. This report describes digital image quality from many viewpoints, from retinal receptor characteristics to perceptual compression algorithms. Special focus is given to perceptual image quality measures.
|
|
| 31. |
- Lundström, Claes, 1973-, et al.
(författare)
-
The alpha-histogram: Using Spatial Coherence to Enhance Histograms and Transfer Function Design
- 2006
-
Ingår i: Proceedings Eurographics/IEEE Symposium on Visualization 2006, Lisbon, Portugal. ; , s. 227-234
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- The high complexity of Transfer Function (TF) design is a major obstacle to widespread routine use of Direct Volume Rendering, particularly in the case of medical imaging. Both manual and automatic TF design schemes would benefit greatly from a fast and simple method for detection of tissue value ranges. To this end, we introduce the a-histogram, an enhancement that amplifies ranges corresponding to spatially coherent materials. The properties of the a-histogram have been explored for synthetic data sets and then successfully used to detect vessels in 20 Magnetic Resonance angiographies, proving the potential of this approach as a fast and simple technique for histogram enhancement in general and for TF construction in particular.
|
|
| 32. |
- Lundström, Claes, 1973-, et al.
(författare)
-
Uncertainty Visualization in Medical Volume Rendering Using Probabilistic Animation
- 2007
-
Ingår i: IEEE Transactions on Visualization and Computer Graphics. - 1077-2626 .- 1941-0506. ; 13:6, s. 1648-1655
-
Tidskriftsartikel (refereegranskat)abstract
- Direct volume rendering has proved to be an effective visualization method for medical data sets and has reached wide-spread clinical use. The diagnostic exploration, in essence, corresponds to a tissue classification task, which is often complex and time-consuming. Moreover, a major problem is the lack of information on the uncertainty of the classification, which can have dramatic consequences for the diagnosis. In this paper this problem is addressed by proposing animation methods to convey uncertainty in the rendering. The foundation is a probabilistic Transfer Function model which allows for direct user interaction with the classification. The rendering is animated by sampling the probability domain over time, which results in varying appearance for uncertain regions. A particularly promising application of this technique is a "sensitivity lens" applied to focus regions in the data set. The methods have been evaluated by radiologists in a study simulating the clinical task of stenosis assessment, in which the animation technique is shown to outperform traditional rendering in terms of assessment accuracy.
|
|
| 33. |
- Lundström, Claes, 1973-
(författare)
-
vPSNR : a visualization-aware image fidelity metric tailored for diagnostic imaging
- 2013
-
Ingår i: International Journal of Computer Assisted Radiology and Surgery. - : Springer. - 1861-6410 .- 1861-6429. ; 8:3, s. 437-450
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose Often, the large amounts of data generated in diagnosticimaging cause overload problems for IT systems andradiologists. This entails a need of effective use of data reductionbeyond lossless levels, which, in turn, underlines theneed to measure and control the image fidelity. Existingimage fidelity metrics, however, fail to fully support importantrequirements from a modern clinical context: supportfor high-dimensional data, visualization awareness, and independencefrom the original data.Methods We propose an image fidelity metric, called thevisual peak signal-to-noise ratio (vPSNR), fulfilling the threemain requirements. A series of image fidelity tests on CTdata sets is employed. The impact of visualization transform(grayscalewindow) on diagnostic quality of irreversiblycompressed data sets is evaluated through an observer-basedstudy. In addition, several tests were performed demonstratingthe benefits, limitations, and characteristics of vPSNR indifferent data reduction scenarios.Results The visualization transform has a significant impacton diagnostic quality, and the vPSNR is capable of representingthis effect. Moreover, the tests establish that the vPSNRis broadly applicable.Conclusions vPSNR fills a gap not served by existingimage fidelity metrics, relevant for the clinical context. WhilevPSNR alone cannot fulfill all image fidelity needs, it can bea useful complement in a wide range of scenarios.
|
|
| 34. |
- Maras, Gordan, et al.
(författare)
-
Regional lymph node metastasis in colon adenocarcinoma
- 2019
-
Annan publikationabstract
- Whole slide pathology images from regional lymph node metastasis in colon adenocarcinoma produced at Region Gävleborg Clinical Pathology and Cytology department and Region Östergötland Clinical Pathology department. Annotations for AI training produced as part of AIDA clinical fellowship project investigating AI decision support in metastasis detection.
|
|
| 35. |
|
|
| 36. |
- Molin, Jesper, 1987, et al.
(författare)
-
A comparative study of input devices for digital slide navigation
- 2015
-
Ingår i: Journal of Pathology Informatics. - : Elsevier BV. - 2229-5089 .- 2153-3539. ; 6:7
-
Tidskriftsartikel (refereegranskat)abstract
- Quick and seamless integration between input devices and the navigation of digital slides remains a key barrier for many pathologists to "go digital." To better understand this integration, three different input device implementations were compared in terms of time to diagnose, perceived workload and users' preferences. Six pathologists reviewed in total nine cases with a computer mouse, a 6 degrees-of-freedom (6DOF) navigator and a touchpad. The participants perceived significantly less workload (P
|
|
| 37. |
- Molin, Jesper, 1987, et al.
(författare)
-
Feature-enhancing zoom to facilitate Ki-67 hot spot detection
- 2014
-
Ingår i: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. - : SPIE. - 1605-7422. - 9780819498342 ; 9041
-
Konferensbidrag (refereegranskat)abstract
- Image processing algorithms in pathology commonly include automated decision points such as classifications. While this enables efficient automation, there is also a risk that errors are induced. A different paradigm is to use image processing for enhancements without introducing explicit classifications. Such enhancements can help pathologists to increase efficiency without sacrificing accuracy. In our work, this paradigm has been applied to Ki-67 hot spot detection. Ki-67 scoring is a routine analysis to quantify the proliferation rate of tumor cells. Cell counting in the hot spot, the region of highest concentration of positive tumor cells, is a method increasingly used in clinical routine. An obstacle for this method is that while hot spot selection is a task suitable for low magnification, high magnification is needed to discern positive nuclei, thus the pathologist must perform many zooming operations. We propose to address this issue by an image processing method that increases the visibility of the positive nuclei at low magnification levels. This tool displays the modified version at low magnification, while gradually blending into the original image at high magnification. The tool was evaluated in a feasibility study with four pathologists targeting routine clinical use. In a task to compare hot spot concentrations, the average accuracy was 75±4.1% using the tool and 69±4.6% without it (n=4). Feedback on the system, gathered from an observer study, indicate that the pathologists found the tool useful and fitting in their existing diagnostic process. The pathologists judged the tool to be feasible for implementation in clinical routine.
|
|
| 38. |
- Molin, Jesper, 1987, et al.
(författare)
-
Scale Stain: Multi-Resolution Feature Enhancement in Pathology Visualization
- 2016
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Digital whole-slide images of pathological tissue samples have recently become feasible for use within routine diagnostic practice. These gigapixel sized images enable pathologists to perform reviews using computer workstations instead of microscopes. Existing workstations visualize scanned images by providing a zoomable image space that reproduces the capabilities of the microscope. This paper presents a novel visualization approach that enables filtering of the scale-space according to color preference. The visualization method reveals diagnostically important patterns that are otherwise not visible. The paper demonstrates how thisapproach has been implemented into a fully functional prototype that lets the user navigate the visualization parameter space in real time. The prototype was evaluated for two common clinical tasks with eight pathologists in a within-subjects study. The data reveal thattask efficiency increased by 15% using the prototype, with maintained accuracy. By analyzing behavioral strategies, it was possible to conclude that efficiency gain was caused by a reduction of the panning needed to perform systematic search of the images. The prototype system was well received by the pathologists who did not detect any risks that would hinder use in clinical routine.
|
|
| 39. |
- Molin, Jesper, 1987, et al.
(författare)
-
Slide navigation patterns among pathologists with long experience of digital review
- 2015
-
Ingår i: Histopathology. - : Wiley. - 0309-0167 .- 1365-2559. ; 67:2, s. 185-192
-
Tidskriftsartikel (refereegranskat)abstract
- Aims: In order to develop efficient digital pathologyworkstations, we studied the navigation patterns ofpathologists diagnosing whole-slide images. To gain abetter understanding of these patterns, we built aconceptual model based on observations. We alsodetermined whether or not new navigation patternshave emerged among pathologists with extensive digitalexperience.Methods and results: Five pathologists were asked todiagnose a set of four cases while thinking out loud.The navigation within the digital slides was recordedand divided into re-occurring navigation actions. Thepathologists reused the same type of actions, but theiroccurrence differed. The most common action was aslow panning that followed an edge structure orcovered an area systematically, which accounted for30.2% of all actions and had a median duration of7.2 s. Of all the actions, 49% were carried out withinthe navigation overview and 38% of the actionscould not have been performed with a conventionalmicroscope.Conclusions: The new navigation possibilities in thedigital workstation were used to a large extent. Thedivision of actions into different concepts can be usedto find and prioritize between existing user interfacedesigns as well as to understand the different navigationstyles used by different pathologists.
|
|
| 40. |
- Persson, Anders, et al.
(författare)
-
Standardized volume rendering for magnetic resonance angiography measurements in the abdominal aorta
- 2006
-
Ingår i: Acta Radiologica. - : SAGE Publications. - 0284-1851 .- 1600-0455. ; 47:2, s. 172-178
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: To compare three methods for standardizing volume rendering technique (VRT) protocols by studying aortic diameter measurements in magnetic resonance angiography (MRA) datasets.Material and Methods: Datasets from 20 patients previously examined with gadolinium-enhanced MRA and with digital subtraction angiography (DSA) for abdominal aortic aneurysm were retrospectively evaluated by three independent readers. The MRA datasets were viewed using VRT with three different standardized transfer functions: the percentile method (Pc-VRT), the maximum-likelihood method (ML-VRT), and the partial range histogram method (PRH-VRT). The aortic diameters obtained with these three methods were compared with freely chosen VRT parameters (F-VRT) and with maximum intensity projection (MIP) concerning inter-reader variability and agreement with the reference method DSA.Results: F-VRT parameters and PRH-VRT gave significantly higher diameter values than DSA, whereas Pc-VRT gave significantly lower values than DSA. The highest interobserver variability was found for F-VRT parameters and MIP, and the lowest for Pc-VRT and PRH-VRT. All standardized VRT methods were significantly superior to both MIP and F-VRT in this respect. The agreement with DSA was best for PRH-VRT, which was the only method with a mean error below 1 mm and which also had the narrowest limits of agreement (95% of cases between 2.1 mm below and 3.1 mm above DSA).Conclusion: All the standardized VRT methods compare favorably with MIP and VRT with freely selected parameters as regards interobserver variability. The partial range histogram method, although systematically overestimating vessel diameters, gives results closest to those of DSA.
|
|
| 41. |
- Pocevičiūtė, Milda, 1992-, et al.
(författare)
-
Detecting Domain Shift in Multiple Instance Learning for Digital Pathology Using Fréchet Domain Distance
- 2023
-
Ingår i: Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. - : Springer. - 9783031439032 - 9783031439049 ; , s. 157-167
-
Konferensbidrag (refereegranskat)abstract
- Multiple-instance learning (MIL) is an attractive approach for digital pathology applications as it reduces the costs related to data collection and labelling. However, it is not clear how sensitive MIL is to clinically realistic domain shifts, i.e., differences in data distribution that could negatively affect performance, and if already existing metrics for detecting domain shifts work well with these algorithms. We trained an attention-based MIL algorithm to classify whether a whole-slide image of a lymph node contains breast tumour metastases. The algorithm was evaluated on data from a hospital in a different country and various subsets of this data that correspond to different levels of domain shift. Our contributions include showing that MIL for digital pathology is affected by clinically realistic differences in data, evaluating which features from a MIL model are most suitable for detecting changes in performance, and proposing an unsupervised metric named Fréchet Domain Distance (FDD) for quantification of domain shifts. Shift measure performance was evaluated through the mean Pearson correlation to change in classification performance, where FDD achieved 0.70 on 10-fold cross-validation models. The baselines included Deep ensemble, Difference of Confidence, and Representation shift which resulted in 0.45, -0.29, and 0.56 mean Pearson correlation, respectively. FDD could be a valuable tool for care providers and vendors who need to verify if a MIL system is likely to perform reliably when implemented at a new site, without requiring any additional annotations from pathologists.
|
|
| 42. |
- Pocevičiūtė, Milda, 1992-
(författare)
-
Generalisation and reliability of deep learning for digital pathology in a clinical setting
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Deep learning (DL) is a subfield of artificial intelligence (AI) focused on developing algorithms that learn from data to perform some tasks that can aid humans in their daily life or work assignments. Research demonstrates the potential of DL in supporting pathologists with routine tasks like detecting breast cancer metastases and grading prostate cancer. However, a widespread adoption of DL technology in pathology labs has been slow for several reasons. DL models often exhibit performance variations across medical centres, patient subgroups, and even within the same centre over time. While collecting more data and retraining the algorithms seems like a straightforward solution, it is a costly and time-consuming process. Moreover, retraining DL systems with regulatory approvals is complex due to existing regulations. Another limitation of DL models is their inability to provide confidence estimates for predictions, leaving users in the dark about their reliability. Finally, establishing a close collaboration between the research community, vendors, and pathology labs is crucial for producing effective DL systems for patient care. However, this collaboration faces challenges like miscommunication, misalignment of goals, and misunderstanding priorities.This thesis presents various approaches that could tackle the generalisation and reliability challenges faced by diagnostic DL systems for digital pathology with a strong emphasis on the clinical needs. To address the generalisation issues, an unsupervised approach to quantify expected changes in a model’s performance between two datasets is proposed. This approach can serve as an initial validation step before deploying diagnostic DL systems in clinical practice, reducing annotation costs. Additionally, an unsupervised framework based on generative models is proposed to identify substantially different inputs, known as out-of-distribution (OOD) samples. Detecting OOD samples plays a crucial role in enhancing the reliability of DL algorithms. Furthermore, several studies are conducted to explore what benefits uncertainty estimation could bring. Firstly, various uncertainty estimation approaches are extensively evaluated, focusing on identifying incorrect predictions and generalisability issues between medical centres and specific patient groups. In addition, the results reveal that combining uncertainty estimation methods with DL outputs leads to a more robust classification score, enhancing the overall performance and reliability of the classification process. Another study demonstrates that spatial uncertainty aggregation improves the effectiveness of uncertainty estimation in tumour segmentation tasks. This is evaluated on the detection of false negatives which may reduce the risk of missing tumour cells. Finally, the clinical prerequisites for developing and validating diagnostic DL systems for digital pathology are discussed, along with an overview of explainable AI techniques.In conclusion, multiple approaches to facilitate the adoption of DL systems in clinical practice, addressing reliability, generalisability, and clinical needs aspects are discussed in this thesis. I believe that the extensive efforts in the research community will have a positive impact on the development, validation, and deployment of DL systems in digital pathology labs, empowering pathologists with trustworthy AI tools.
|
|
| 43. |
- Pocevičiūtė, Milda, et al.
(författare)
-
Survey of XAI in digital pathology
- 2020
-
Ingår i: Artificial intelligence and machine learning for digital pathology. - Cham : Springer. - 9783030504021 ; , s. 56-88
-
Bokkapitel (refereegranskat)abstract
- Artificial intelligence (AI) has shown great promise for diagnostic imaging assessments. However, the application of AI to support medical diagnostics in clinical routine comes with many challenges. The algorithms should have high prediction accuracy but also be transparent, understandable and reliable. Thus, explainable artificial intelligence (XAI) is highly relevant for this domain. We present a survey on XAI within digital pathology, a medical imaging sub-discipline with particular characteristics and needs. The review includes several contributions. Firstly, we give a thorough overview of current XAI techniques of potential relevance for deep learning methods in pathology imaging, and categorise them from three different aspects. In doing so, we incorporate uncertainty estimation methods as an integral part of the XAI landscape. We also connect the technical methods to the specific prerequisites in digital pathology and present findings to guide future research efforts. The survey is intended for both technical researchers and medical professionals, one of the objectives being to establish a common ground for cross-disciplinary discussions.
|
|
| 44. |
- Pocevičiūtė, Milda, et al.
(författare)
-
Unsupervised Anomaly Detection In Digital Pathology Using GANs
- 2021
-
Ingår i: 2021 IEEE 18th International Symposium On Biomedical Imaging (ISBI). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781665429474 - 9781665412469 ; , s. 1878-1882
-
Konferensbidrag (refereegranskat)abstract
- Machine learning (ML) algorithms are optimized for the distribution represented by the training data. For outlier data, they often deliver predictions with equal confidence, even though these should not be trusted. In order to deploy ML-based digital pathology solutions in clinical practice, effective methods for detecting anomalous data are crucial to avoid incorrect decisions in the outlier scenario. We propose a new unsupervised learning approach for anomaly detection in histopathology data based on generative adversarial networks (GANs). Compared to the existing GAN-based methods that have been used in medical imaging, the proposed approach improves significantly on performance for pathology data. Our results indicate that histopathology imagery is substantially more complex than the data targeted by the previous methods. This complexity requires not only a more advanced GAN architecture but also an appropriate anomaly metric to capture the quality of the reconstructed images.
|
|
| 45. |
- Skoglund, Karin, 1980-, et al.
(författare)
-
Annotations, ontologies, and whole slide images : Development of an annotated ontology-driven whole slide image library of normal and abnormal human tissue
- 2019
-
Ingår i: Journal of Pathology Informatics. - : Medknow Publications. - 2229-5089 .- 2153-3539. ; 10:22
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: Digital pathology is today a widely used technology, and the digitalization of microscopic slides into whole slide images (WSIs) allows the use of machine learning algorithms as a tool in the diagnostic process. In recent years, “deep learning” algorithms for image analysis have been applied to digital pathology with great success. The training of these algorithms requires a large volume of high-quality images and image annotations. These large image collections are a potent source of information, and to use and share the information, standardization of the content through a consistent terminology is essential. The aim of this project was to develop a pilot dataset of exhaustive annotated WSI of normal and abnormal human tissue and link the annotations to appropriate ontological information. Materials and Methods: Several biomedical ontologies and controlled vocabularies were investigated with the aim of selecting the most suitable ontology for this project. The selection criteria required an ontology that covered anatomical locations, histological subcompartments, histopathologic diagnoses, histopathologic terms, and generic terms such as normal, abnormal, and artifact. WSIs of normal and abnormal tissue from 50 colon resections and 69 skin excisions, diagnosed 2015-2016 at the Department of Clinical Pathology in Linköping, were randomly collected. These images were manually and exhaustively annotated at the level of major subcompartments, including normal or abnormal findings and artifacts. Results: Systemized nomenclature of medicine clinical terms (SNOMED CT) was chosen, and the annotations were linked to its codes and terms. Two hundred WSI were collected and annotated, resulting in 17,497 annotations, covering a total area of 302.19 cm2, equivalent to 107,7 gigapixels. Ninety-five unique SNOMED CT codes were used. The time taken to annotate a WSI varied from 45 s to over 360 min, a total time of approximately 360 h. Conclusion: This work resulted in a dataset of 200 exhaustive annotated WSIs of normal and abnormal tissue from the colon and skin, and it has informed plans to build a comprehensive library of annotated WSIs. SNOMED CT was found to be the best ontology for annotation labeling. This project also demonstrates the need for future development of annotation tools in order to make the annotation process more efficient.
|
|
| 46. |
- Skoglund, Karin, 1980-, et al.
(författare)
-
Colon data from the Visual Sweden project DROID
- 2019
-
Annan publikationabstract
- The dataset consists of 101 H&E-stained colon whole slide images (WSI) - 52 abnormal and 49 benign cases. All significant abnormal findings identified are outlined and categorized into 15 types such as hyperplastic polyp, high grade adenocarcinoma and necrosis. Other tissue components such as mucosa, submucosa, as well as the surgical margin are delineated to create a complete histological map. In total, 756 separate annotations have been made to segment the different tissue structures and link them to ontological information.
|
|
| 47. |
- Stacke, Karin, et al.
(författare)
-
A Closer Look at Domain Shift for Deep Learning in Histopathology
- 2019
-
Konferensbidrag (refereegranskat)abstract
- Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images. We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to. Most centrally, we present a novel measure for evaluating the distance between domains in the context of the learned representation of a particular model. This measure can reveal how sensitive a model is to domain variations, and can be used to detect new data that a model will have problems generalizing to. The results show how learning is heavily influenced by the preparation of training data, and that the latent representation used to do classification is sensitive to changes in data distribution, especially when training without augmentation or normalization.
|
|
| 48. |
- Stacke, Karin, 1990-
(författare)
-
Deep Learning for Digital Pathology in Limited Data Scenarios
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The impressive technical advances seen for machine learning algorithms in combination with the digitalization of medical images in the radiology and pathology departments show great promise in introducing powerful image analysis tools for image diagnostics. In particular, deep learning, a subfield within machine learning, has shown great success, advancing fields such as image classification and detection. However, these types of algorithms are only used to a very small extent in clinical practice. One reason is that the unique nature of radiology and pathology images and the clinical setting in which they are acquired poses challenges not seen in other image domains. Differences relate to capturing methods, as well as the image contents. In addition, these datasets are not only unique on a per-image basis but as a collective dataset. Characteristics such as size, class balance, and availability of annotated labels make creating robust and generalizable deep learning methods a challenge. This thesis investigates how deep learning models can be trained for applications in this domain, with particular focus on histopathology data. We investigate how domain shift between different scanners causes performance drop, and present ways of mitigating this. We also present a method to detect when domain shift occurs between different datasets. Another hurdle is the shortage of labeled data for medical applications, and this thesis looks at two different approaches to solving this problem. The first approach investigates how labeled data from one organ and cancer type can boost cancer classification in another organ where labeled data is scarce. The second approach looks at a specific type of unsupervised learning method, self-supervised learning, where the model is trained on unlabeled data. For both of these approaches, we present strategies to handle low-data regimes that may greatly increase the availability to build deep learning models for a wider range of applications. Furthermore, deep learning technology enables us to go beyond traditional medical domains, and combine the data from both radiology and pathology. This thesis presents a method for improved cancer characterization on contrast-enhanced CT by incorporating corresponding pathology data during training. The method shows the potential of im-proving future healthcare by intergraded diagnostics made possible by machine-learning technology.
|
|
| 49. |
|
|
| 50. |
- Stacke, Karin, 1990-, et al.
(författare)
-
Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications
- 2022
-
Ingår i: The Journal of Machine Learning for Biomedical Imaging. - : Melba (The Journal of Machine Learning for Biomedical Imaging). - 2766-905X. ; 1
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Unsupervised learning has made substantial progress over the last few years, especially by means of contrastive self-supervised learning. The dominating dataset for benchmarking self-supervised learning has been ImageNet, for which recent methods are approaching the performance achieved by fully supervised training. The ImageNet dataset is however largely object-centric, and it is not clear yet what potential those methods have on widely different datasets and tasks that are not object-centric, such as in digital pathology.While self-supervised learning has started to be explored within this area with encouraging results, there is reason to look closer at how this setting differs from natural images and ImageNet. In this paper we make an in-depth analysis of contrastive learning for histopathology, pin-pointing how the contrastive objective will behave differently due to the characteristics of histopathology data. Using SimCLR and H&E stained images as a representative setting for contrastive self-supervised learning in histopathology, we bring forward a number of considerations, such as view generation for the contrastive objectiveand hyper-parameter tuning. In a large battery of experiments, we analyze how the downstream performance in tissue classification will be affected by these considerations. The results point to how contrastive learning can reduce the annotation effort within digital pathology, but that the specific dataset characteristics need to be considered. To take full advantage of the contrastive learning objective, different calibrations of view generation and hyper-parameters are required. Our results pave the way for realizing the full potential of self-supervised learning for histopathology applications. Code and trained models are available at https://github.com/k-stacke/ssl-pathology.
|
|
