| 1. |
- Eriksson, Jan W, et al.
(författare)
-
Tissue-specific glucose partitioning and fat content in prediabetes and type 2 diabetes: whole-body PET/MRI during hyperinsulinemia
- 2021
-
Ingår i: European journal of endocrinology. - : Bioscientifica. - 0804-4643 .- 1479-683X. ; 184:6, s. 879-899
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: To obtain direct quantifications of glucose turnover, volumes an d fat content of several tissues in the development of type 2 diabetes (T2D) using a novel integrated a pproach for whole-body imaging. Design and methods: Hyperinsulinemic-euglycemic clamps and simultaneous whole-body integrated [18F]FDG-PET/MRI with automated analyses were performed in control (n = 12), prediabetes (n = 16) and T2D (n = 13) subjects matched for age, sex and BMI. Results: Whole-body glucose uptake (Rd) was reduced by approximately 25% in T2D vs control subjects, and partitioning to brain was increased from 3.8% of total Rd in co ntrols to 7.1% in T2D. In liver, subcutaneous AT, thigh muscle, total tissue glucose metabolic rates (MRglu) and their % of total Rd were reduced in T2D compared to contr ol subjects. The prediabetes group had intermediate findings. Total MRglu in heart, visceral AT, gluteus and calf muscle was similar across groups. Whole-body insulin sensitivity asses sed as glucose infusion rate correlated with liver MR glu but inversely with brain MRglu. Liver fat content correlated with MRglu in brain but inversely with MRglu in other tissues. Calf muscle fat was inversely associated with MR glu only in the same muscle group. Conclusions: This integrated imaging approach provides detailed quantification of tissue-specific glucose metabolism. During T2D development, insulin-stimulated glucose disposal is impaired and increasingly shifted away from muscle, liver and fat toward the brain. Altered glucose handling in the brain and liver fat accumulation may aggravate insulin resistance in several organs. © 2021 BioScientifica Ltd.. All rights reserved.
|
|
| 2. |
- Guglielmo, Priscilla, et al.
(författare)
-
Validation of automated whole-body analysis of metabolic and morphological parameters from an integrated FDG-PET/MRI acquisition
- 2020
-
Ingår i: Scientific Reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 10:1
-
Tidskriftsartikel (refereegranskat)abstract
- Automated quantification of tissue morphology and tracer uptake in PET/MR images could streamline the analysis compared to traditional manual methods. To validate a single atlas image segmentation approach for automated assessment of tissue volume, fat content (FF) and glucose uptake (GU) from whole-body [18F]FDG-PET/MR images. Twelve subjects underwent whole-body [18F]FDG-PET/MRI during hyperinsulinemic-euglycemic clamp. Automated analysis of tissue volumes, FF and GU were achieved using image registration to a single atlas image with reference segmentations of 18 volume of interests (VOIs). Manual segmentations by an experienced radiologist were used as reference. Quantification accuracy was assessed with Dice scores, group comparisons and correlations. VOI Dice scores ranged from 0.93 to 0.32. Muscles, brain, VAT and liver showed the highest scores. Pancreas, large and small intestines demonstrated lower segmentation accuracy and poor correlations. Estimated tissue volumes differed significantly in 8 cases. Tissue FFs were often slightly but significantly overestimated. Satisfactory agreements were observed in most tissue GUs. Automated tissue identification and characterization using a single atlas segmentation performs well compared to manual segmentation in most tissues and will be valuable in future studies. In certain tissues, alternative quantification methods or improvements to the current approach is needed.
|
|
| 3. |
- Visvanathar, Robin, et al.
(författare)
-
Exploration of whole-body PET/MRI and clinical variables in type 2 diabetes for data-driven hypothesis generation
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Aim To explore the feasibility of using the automated holistic image analysis approach Imiomics in voxel-level association screening with clinical variables for hypothesis-generation in whole-body [18F]fluorodeoxyglucose (FDG) PET/MR images. Material and methods Three experimental groups consisting of healthy individuals (n=12), individuals with prediabetes (n=16) and individuals with type 2 diabetes (n=13) were examined with simultaneous whole-body PET/MRI during hyperinsulinemic euglycemic clamp. The Imiomics-framework was utilised to create correlation maps between the clinical biomarkers and PET/MRI data. Results Multiple significant moderate-strong associations were detected, the inflammatory biomarkers (P-CRP, B-Leukocytes and B-Neutrophils) were positively associated with visceral adipose tissue (VAT) volume and inversely associated with skeletal muscle Ki. B-monocytes were positively associated with VAT volume, and negatively associated with gluteofemoral SAT volume. Furthermore, insulin sensitivity (M-value) was shown to be negatively associated with brain Ki. Of the plasma lipids, HDL was positively associated with Ki in the liver, VAT and skeletal muscle. Several additional confirmatory and distinct findings are reported. Conclusions An Imiomics-based data-driven exploratory approach allows for rapid and holistic analysis of the massive image datasets generated.
|
|
| 4. |
|
|
| 5. |
- Ahmad, Nouman, et al.
(författare)
-
Automatic segmentation of large-scale CT image datasets for detailed body composition analysis
- 2023
-
Ingår i: BMC BIOINFORMATICS. - : BioMed Central (BMC). - 1471-2105. ; 24:1
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundBody composition (BC) is an important factor in determining the risk of type 2-diabetes and cardiovascular disease. Computed tomography (CT) is a useful imaging technique for studying BC, however manual segmentation of CT images is time-consuming and subjective. The purpose of this study is to develop and evaluate fully automated segmentation techniques applicable to a 3-slice CT imaging protocol, consisting of single slices at the level of the liver, abdomen, and thigh, allowing detailed analysis of numerous tissues and organs.MethodsThe study used more than 4000 CT subjects acquired from the large-scale SCAPIS and IGT cohort to train and evaluate four convolutional neural network based architectures: ResUNET, UNET++, Ghost-UNET, and the proposed Ghost-UNET++. The segmentation techniques were developed and evaluated for automated segmentation of the liver, spleen, skeletal muscle, bone marrow, cortical bone, and various adipose tissue depots, including visceral (VAT), intraperitoneal (IPAT), retroperitoneal (RPAT), subcutaneous (SAT), deep (DSAT), and superficial SAT (SSAT), as well as intermuscular adipose tissue (IMAT). The models were trained and validated for each target using tenfold cross-validation and test sets.ResultsThe Dice scores on cross validation in SCAPIS were: ResUNET 0.964 (0.909-0.996), UNET++ 0.981 (0.927-0.996), Ghost-UNET 0.961 (0.904-0.991), and Ghost-UNET++ 0.968 (0.910-0.994). All four models showed relatively strong results, however UNET++ had the best performance overall. Ghost-UNET++ performed competitively compared to UNET++ and showed a more computationally efficient approach.ConclusionFully automated segmentation techniques can be successfully applied to a 3-slice CT imaging protocol to analyze multiple tissues and organs related to BC. The overall best performance was achieved by UNET++, against which Ghost-UNET++ showed competitive results based on a more computationally efficient approach. The use of fully automated segmentation methods can reduce analysis time and provide objective results in large-scale studies of BC.
|
|
| 6. |
- Ahmad, Nouman, et al.
(författare)
-
Voxel-wise body composition analysis using image registration of a three-slice CT imaging protocol : methodology and proof-of-concept studies
- 2024
-
Ingår i: Biomedical engineering online. - : Springer Nature. - 1475-925X. ; 23:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background Computed tomography (CT) is an imaging modality commonly used for studies of internal body structures and very useful for detailed studies of body composition. The aim of this study was to develop and evaluate a fully automatic image registration framework for inter-subject CT slice registration. The aim was also to use the results, in a set of proof-of-concept studies, for voxel-wise statistical body composition analysis (Imiomics) of correlations between imaging and non-imaging data.Methods The current study utilized three single-slice CT images of the liver, abdomen, and thigh from two large cohort studies, SCAPIS and IGT. The image registration method developed and evaluated used both CT images together with image-derived tissue and organ segmentation masks. To evaluate the performance of the registration method, a set of baseline 3-single-slice CT images (from 2780 subjects including 8285 slices) from the SCAPIS and IGT cohorts were registered. Vector magnitude and intensity magnitude error indicating inverse consistency were used for evaluation. Image registration results were further used for voxel-wise analysis of associations between the CT images (as represented by tissue volume from Hounsfield unit and Jacobian determinant) and various explicit measurements of various tissues, fat depots, and organs collected in both cohort studies.Results Our findings demonstrated that the key organs and anatomical structures were registered appropriately. The evaluation parameters of inverse consistency, such as vector magnitude and intensity magnitude error, were on average less than 3 mm and 50 Hounsfield units. The registration followed by Imiomics analysis enabled the examination of associations between various explicit measurements (liver, spleen, abdominal muscle, visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), thigh SAT, intermuscular adipose tissue (IMAT), and thigh muscle) and the voxel-wise image information.Conclusion The developed and evaluated framework allows accurate image registrations of the collected three single-slice CT images and enables detailed voxel-wise studies of associations between body composition and associated diseases and risk factors.
|
|
| 7. |
|
|
| 8. |
- Asplund, Teo, et al.
(författare)
-
A new approach to mathematical morphology on one dimensional sampled signals
- 2016
-
Ingår i: Proceedings of the 23rd International Conference on Pattern Recognition ICPR 2016. - Piscataway, NJ : IEEE Communications Society. - 9781509048472 ; , s. 3904-3909
-
Konferensbidrag (refereegranskat)abstract
- We present a new approach to approximate continuous-domain mathematical morphology operators. The approach is applicable to irregularly sampled signals. We define a dilation under this new approach, where samples are duplicated and shifted according to the flat, continuous structuring element. We define the erosion by adjunction, and the opening and closing by composition. These new operators will significantly increase precision in image measurements. Experiments show that these operators indeed approximate continuous-domain operators better than the standard operators on sampled one-dimensional signals, and that they may be applied to signals using structuring elements smaller than the distance between samples. We also show that we can apply the operators to scan lines of a two-dimensional image to filter horizontal and vertical linear structures.
|
|
| 9. |
- Asplund, Teo, et al.
(författare)
-
Adaptive Mathematical Morphology on Irregularly Sampled Signals in Two Dimensions
- 2020
-
Ingår i: Mathematical Morphology : Theory and Applications. - : Walter de Gruyter. - 2353-3390. ; 4:1, s. 108-126
-
Tidskriftsartikel (refereegranskat)abstract
- This paper proposes a way of better approximating continuous, two-dimensional morphologyin the discrete domain, by allowing for irregularly sampled input and output signals. We generalizeprevious work to allow for a greater variety of structuring elements, both flat and non-flat. Experimentallywe show improved results over regular, discrete morphology with respect to the approximation ofcontinuous morphology. It is also worth noting that the number of output samples can often be reducedwithout sacrificing the quality of the approximation, since the morphological operators usually generateoutput signals with many plateaus, which, intuitively do not need a large number of samples to be correctlyrepresented. Finally, the paper presents some results showing adaptive morphology on irregularlysampled signals.
|
|
| 10. |
|
|
| 11. |
- Asplund, Teo, et al.
(författare)
-
Mathematical Morphology on Irregularly Sampled Data Applied to Segmentation of 3D Point Clouds of Urban Scenes
- 2019
-
Ingår i: International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing. - Cham : Springer Nature. - 9783030208660 - 9783030208677
-
Konferensbidrag (refereegranskat)abstract
- This paper proposes an extension of mathematical morphology on irregularly sampled signals to 3D point clouds. The proposed method is applied to the segmentation of urban scenes to show its applicability to the analysis of point cloud data. Applying the proposed operators has the desirable side-effect of homogenizing signals that are sampled heterogeneously. In experiments we show that the proposed segmentation algorithm yields good results on the Paris-rue-Madame database and is robust in terms of sampling density, i.e. yielding similar labelings for more sparse samplings of the same scene.
|
|
| 12. |
- Asplund, Teo, et al.
(författare)
-
Mathematical Morphology on Irregularly Sampled Signals
- 2017
-
Ingår i: Computer Vision – ACCV 2016 Workshops. - Cham : Springer. - 9783319544267 - 9783319544274 ; , s. 506-520
-
Konferensbidrag (refereegranskat)abstract
- This paper introduces a new operator that can be used to ap-proximate continuous-domain mathematical morphology on irregularly sampled surfaces. We define a new way of approximating the continuous domain dilation by duplicating and shifting samples according to a flat continuous structuring element. We show that the proposed algorithm can better approximate continuous dilation, and that dilations may be sampled irregularly to achieve a smaller sampling without greatly com-promising the accuracy of the result.
|
|
| 13. |
- Asplund, Teo
(författare)
-
Precise Image-Based Measurements through Irregular Sampling
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Mathematical morphology is a theory that is applicable broadly in signal processing, but in this thesis we focus mainly on image data. Fundamental concepts of morphology include the structuring element and the four operators: dilation, erosion, closing, and opening. One way of thinking about the role of the structuring element is as a probe, which traverses the signal (e.g. the image) systematically and inspects how well it "fits" in a certain sense that depends on the operator.Although morphology is defined in the discrete as well as in the continuous domain, often only the discrete case is considered in practice. However, commonly digital images are a representation of continuous reality and thus it is of interest to maintain a correspondence between mathematical morphology operating in the discrete and in the continuous domain. Therefore, much of this thesis investigates how to better approximate continuous morphology in the discrete domain. We present a number of issues relating to this goal when applying morphology in the regular, discrete case, and show that allowing for irregularly sampled signals can improve this approximation, since moving to irregularly sampled signals frees us from constraints (namely those imposed by the sampling lattice) that harm the correspondence in the regular case. The thesis develops a framework for applying morphology in the irregular case, using a wide range of structuring elements, including non-flat structuring elements (or structuring functions) and adaptive morphology. This proposed framework is then shown to better approximate continuous morphology than its regular, discrete counterpart.Additionally, the thesis contains work dealing with regularly sampled images using regular, discrete morphology and weighting to improve results. However, these cases can be interpreted as specific instances of irregularly sampled signals, thus naturally connecting them to the overarching theme of irregular sampling, precise measurements, and mathematical morphology.
|
|
| 14. |
|
|
| 15. |
- Banerjee, Subhashis, et al.
(författare)
-
Deep Curriculum Learning for Follow-up MRI Registration in Glioblastoma
- 2023
-
Ingår i: Medical Imaging 2023. - : SPIE -Society of Photo-Optical Instrumentation Engineers. - 9781510660335 - 9781510660342
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation inthe surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training forthe network. Weak supervision helps the network to concentrate more focus on the tumor region and resectioncavity through a saliency detection network. Qualitative and quantitative experimental results show the proposedregistration network outperformed two popular state-of-the-art methods.
|
|
| 16. |
- Banerjee, Subhashis, et al.
(författare)
-
Lifelong Learning with Dynamic Convolutions for Glioma Segmentation from Multi-Modal MRI
- 2023
-
Ingår i: Medical imaging 2023. - : SPIE - International Society for Optical Engineering. - 9781510660335 - 9781510660342
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel solution for catastrophic forgetting in lifelong learning (LL) using Dynamic Convolution Neural Network (Dy-CNN). The proposed dynamic convolution layer can adapt convolution filters by learning kernel coefficients or weights based on the input image. The suitability of the proposed Dy-CNN in a lifelong sequential learning-based scenario with multi-modal MR images is experimentally demonstrated for the segmentation of Glioma tumors from multi-modal MR images. Experimental results demonstrated the superiority of the Dy-CNN-based segmenting network in terms of learning through multi-modal MRI images and better convergence of lifelong learning-based training.
|
|
| 17. |
- Banerjee, Subhashis, et al.
(författare)
-
Segmentation of Intracranial Aneurysm Remnant in MRA using Dual-Attention Atrous Net
- 2021
-
Ingår i: 25th International Conference on Pattern Recognition (ICPR). - 9781728188089 ; , s. 9265-9272
-
Konferensbidrag (refereegranskat)abstract
- Due to the advancement of non-invasive medical imaging modalities like Magnetic Resonance Angiography (MRA), an increasing number of Intracranial Aneurysm (IA) cases are being reported in recent years. The IAs are typically treated by so-called endovascular coiling, where blood flow in the IA is prevented by embolization with a platinum coil. Accurate quantification of the IA Remnant (IAR), i.e. the volume with blood flow present post treatment is the utmost important factor in choosing the right treatment planning. This is typically done by manually segmenting the aneurysm remnant from the MRA volume. Since manual segmentation of volumetric images is a labour-intensive and error-prone process, development of an automatic volumetric segmentation method is required. Segmentation of small structures such as IA, that may largely vary in size, shape, and location is considered extremely difficult. Similar intensity distribution of IAs and surrounding blood vessels makes it more challenging and susceptible to false positive. In this paper we propose a novel 3D CNN architecture called Dual-Attention Atrous Net (DAtt-ANet), which can efficiently segment IAR volumes from MRA images by reconciling features at different scales using the proposed Parallel Atrous Unit (PAU) along with the use of self-attention mechanism for extracting fine-grained features and intra-class correlation. The proposed DAtt-ANet model is trained and evaluated on a clinical MRA image dataset of IAR consisting of 46 subjects. We compared the proposed DAtt-ANet with five state-of-the-art CNN models based on their segmentation performance. The proposed DAtt-ANet outperformed all other methods and was able to achieve a five-fold cross-validation DICE score of 0.73 +/- 0.06.
|
|
| 18. |
- Banerjee, Subhashis, et al.
(författare)
-
Streamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring
- 2024
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 14:1
-
Tidskriftsartikel (refereegranskat)abstract
- Radiological imaging to examine intracranial blood vessels is critical for preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) can provide radiologists with a more detailed and precise view of these vessels. This paper introduces a domain generalized artificial intelligence (AI) solution for volumetric monitoring of cerebrovascular structures from multi-center MRAs. Our approach utilizes a multi-task deep convolutional neural network (CNN) with a topology-aware loss function to learn voxel-wise segmentation of the cerebrovascular tree. We use Decorrelation Loss to achieve domain regularization for the encoder network and auxiliary tasks to provide additional regularization and enable the encoder to learn higher-level intermediate representations for improved performance. We compare our method to six state-of-the-art 3D vessel segmentation methods using retrospective TOF-MRA datasets from multiple private and public data sources scanned at six hospitals, with and without vascular pathologies. The proposed model achieved the best scores in all the qualitative performance measures. Furthermore, we have developed an AI-assisted Graphical User Interface (GUI) based on our research to assist radiologists in their daily work and establish a more efficient work process that saves time.
|
|
| 19. |
- Banerjee, Subhashis, et al.
(författare)
-
Topology-Aware Learning for Volumetric Cerebrovascular Segmentation
- 2022
-
Ingår i: 2022 IEEE International Symposium on Biomedical Imaging (IEEE ISBI 2022). - : IEEE. - 9781665429238 ; , s. 1-4
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a topology-aware learning strategy for volumetric segmentation of intracranial cerebrovascular structures. We propose a multi-task deep CNN along with a topology-aware loss function for this purpose. Along with the main task (i.e. segmentation), we train the model to learn two related auxiliary tasks viz. learning the distance transform for the voxels on the surface of the vascular tree and learning the vessel centerline. This provides additional regularization and allows the encoder to learn higher-level intermediate representations to boost the performance of the main task. We compare the proposed method with six state-of-the-art deep learning-based 3D vessel segmentation methods, by using a public Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) dataset. Experimental results demonstrate that the proposed method has the best performance in this particular context.
|
|
| 20. |
- Benedek, Nagy, et al.
(författare)
-
A Weight Sequence Distance Function
- 2013
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a family of weighted neighborhood sequence distance functions defined on the square grid is presented. With this distance function, the allowed weight between any two adjacent pixels along a path is given by a weight sequence. We build on our previous results, where only two or three unique weights are considered, and present a framework that allows any number of weights. We show that the rotational dependency can be very low when as few as three or four unique weights are used. An algorithm for computing the distance transform (DT) that can be used for image processing applications is also presented.
|
|
| 21. |
|
|
| 22. |
- Bengtsson Bernander, Karl, et al.
(författare)
-
Replacing data augmentation with rotation-equivariant CNNs in image-based classification of oral cancer
- 2021
-
Ingår i: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. - Cham : Springer International Publishing. - 9783030934194 - 9783030934200 ; , s. 24-33
-
Konferensbidrag (refereegranskat)abstract
- We present how replacing convolutional neural networks with a rotation-equivariant counterpart can be used to reduce the amount of training images needed for classification of whether a cell is cancerous or not. Our hypothesis is that data augmentation schemes by rotation can be replaced, thereby increasing weight sharing and reducing overfitting. The dataset at hand consists of single cell images. We have balanced a subset of almost 9.000 images from healthy patients and patients diagnosed with cancer. Results show that classification accuracy is improved and overfitting reduced if compared to an ordinary convolutional neural network. The results are encouraging and thereby an advancing step towards making screening of patients widely used for the application of oral cancer.
|
|
| 23. |
|
|
| 24. |
- Bianchi, Kevin, et al.
(författare)
-
Dual B-spline Snake for Interactive Myocardial Segmentation
- 2013
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel interactive segmentation formalism based on two coupledB-Spline snake models to efficiently and simultaneously extract myocardial walls fromshort-axis magnetic resonance images. The main added value of this model is interactionas it is possible to quickly and intuitively correct the result in complex cases withoutrestarting the whole segmentation working flow. During this process, energies computedfrom the images guide the user to the best position of the model.
|
|
| 25. |
- Breznik, Eva, et al.
(författare)
-
Effects of distance transform choice in training with boundary loss
- 2021
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Convolutional neural networks are the method of choice for many medical imaging tasks, in particular segmentation. Recently, efforts have been made to include distance measures in the network training, as for example the introduction of boundary loss, calculated via a signed distance transform. Using boundary loss for segmentation can alleviate issues with imbalance and irregular shapes, leading to a better segmentation boundary. It is originally based on the Euclidean distance transform. In this paper we investigate the effects of employing various definitions of distance when using the boundary loss for medical image segmentation. Our results show a promising behaviour in training with non-Euclidean distances, and suggest a possible new use of the boundary loss in segmentation problems.
|
|
| 26. |
- Breznik, Eva
(författare)
-
Image Processing and Analysis Methods for Biomedical Applications
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- With new technologies and developments medical images can be acquired more quickly and at a larger scale than ever before. However, increased amount of data induces an overhead in the human labour needed for its inspection and analysis. To support clinicians in decision making and enable swifter examinations, computerized methods can be utilized to automate the more time-consuming tasks. For such use, methods need be highly accurate, fast, reliable and interpretable. In this thesis we develop and improve methods for image segmentation, retrieval and statistical analysis, with applications in imaging-based diagnostic pipelines. Individual objects often need to first be extracted/segmented from the image before they can be analysed further. We propose methodological improvements for deep learning-based segmentation methods using distance maps, with the focus on fully-supervised 3D patch-based training and training on 2D slices under point supervision. We show that using a directly interpretable distance prior helps to improve segmentation accuracy and training stability.For histological data in particular, we propose and extensively evaluate a contrastive learning and bag of words-based pipeline for cross-modal image retrieval. The method is able to recover correct matches from the database across modalities and small transformations with improved accuracy compared to the competitors. In addition, we examine a number of methods for multiplicity correction on statistical analyses of correlation using medical images. Evaluation strategies are discussed and anatomy-observing extensions to the methods are developed as a way of directly decreasing the multiplicity issue in an interpretable manner, providing improvements in error control. The methods presented in this thesis were developed with clinical applications in mind and provide a strong base for further developments and future use in medical practice.
|
|
| 27. |
|
|
| 28. |
- Breznik, Eva, et al.
(författare)
-
Multiple comparison correction methods for whole-body magnetic resonance imaging
- 2020
-
Ingår i: Journal of Medical Imaging. - : SPIE-Intl Soc Optical Eng. - 2329-4302 .- 2329-4310. ; 7:1
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Voxel-level hypothesis testing on images suffers from test multiplicity. Numerous correction methods exist, mainly applied and evaluated on neuroimaging and synthetic datasets. However, newly developed approaches like Imiomics, using different data and less common analysis types, also require multiplicity correction for more reliable inference. To handle the multiple comparisons in Imiomics, we aim to evaluate correction methods on whole-body MRI and correlation analyses, and to develop techniques specifically suited for the given analyses. Approach: We evaluate the most common familywise error rate (FWER) limiting procedures on whole-body correlation analyses via standard (synthetic no-activation) nominal error rate estimation as well as smaller prior-knowledge based stringency analysis. Their performance is compared to our anatomy-based method extensions. Results: Results show that nonparametric methods behave better for the given analyses. The proposed prior-knowledge based evaluation shows that the devised extensions including anatomical priors can achieve the same power while keeping the FWER closer to the desired rate. Conclusions: Permutation-based approaches perform adequately and can be used within Imiomics. They can be improved by including information on image structure. We expect such method extensions to become even more relevant with new applications and larger datasets.
|
|
| 29. |
- Brunner, David, et al.
(författare)
-
Efficient Parallel Thinning of 3d Objects on the Body-centered Cubic Lattice
- 2022
-
Ingår i: Computer-Aided Design. - : Elsevier. - 0010-4485 .- 1879-2685. ; 151
-
Tidskriftsartikel (refereegranskat)abstract
- We consider thinning methods to extract one dimensional skeletons from discrete objects defined on the body-centered cubic (bcc) lattice. In Strand (2004), a condition has been given that guarantees the preservation of the object's topology in such a thinning process. In this paper, we present stronger conditions that even allow the topological invariant point removal in a parallelized process. These conditions for p-simplicity can be efficiently evaluated which leads to a very fast thinning process. We show that p-simplicity is a new concept that cannot be obtained by adapting the checking plane conditions of Tsao and Fu to the bcc lattice. Furthermore, we introduce distance information and an optional pruning mechanism into the thinning process to improve the quality of the resulting skeletons. The presented results show that our method generates high quality skeletons that reproduce the symmetries of the models even under the condition of added noise and contain only very few spurious branches. The presented running times demonstrate the linear run-time behavior of our algorithm and the speedup that is achieved by the parallelization. (C) 2022 Elsevier Ltd. All rights reserved.
|
|
| 30. |
|
|
| 31. |
- Dhara, Ashis Kumar, et al.
(författare)
-
Segmentation of Post-operative Glioblastoma in MRI by U-Net with Patient-specific Interactive Refinement
- 2019
-
Ingår i: Brainlesion. - Cham : Springer. - 9783030117221 - 9783030117238 ; , s. 115-122
-
Konferensbidrag (refereegranskat)abstract
- Accurate volumetric change estimation of glioblastoma is very important for post-surgical treatment follow-up. In this paper, an interactive segmentation method was developed and evaluated with the aim to guide volumetric estimation of glioblastoma. U-Net based fully convolutional network is used for initial segmentation of glioblastoma from post contrast MR images. The max flow algorithm is applied on the probability map of U-Net to update the initial segmentation and the result is displayed to the user for interactive refinement. Network update is performed based on the corrected contour by considering patient specific learning to deal with large context variations among different images. The proposed method is evaluated on a clinical MR image database of 15 glioblastoma patients with longitudinal scan data. The experimental results depict an improvement of segmentation performance due to patient specific fine-tuning. The proposed method is computationally fast and efficient as compared to state-of-the-art interactive segmentation tools. This tool could be useful for post-surgical treatment follow-up with minimal user intervention.
|
|
| 32. |
- Ekström, Simon, 1991-, et al.
(författare)
-
Deformable Image Registration of Volumetric Whole-body MRI: An Evaluation
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Whole-body imaging presents a variety of interesting applications and combining these information rich images with image registration enables detailed large scale analysis. Whole-body image registration, with the large variability present in human anatomy, introduces a range of challenges that need to be dealt with. This paper aims to present two new extensions to a previously published registration method based on compositive updates and voxel-wise regularization. The new extensions are evaluated against a previously presented pipeline for whole-body registration and a learning-based approach using the Voxel Morph framework. The methods are evaluated on Dice overlap, smoothness of produced displacement fields, and the inverse consistency error. The presented extensions are shown to improve upon previous method both in terms of computation time and registration quality. The voxel-wise regularization produces a mean Dice overlap of 0.828 for the 10 segmented regions and a mean computation time of 320 seconds per subject. The learning-based approach had an inference time of only 3 seconds but a training time of 16 hours per reference subject. This approach produced a mean Dice overlap of only 0.797 but it was shown that the issues in overlap score were limited to the kidneys. In conclusion, both the extensions and VoxelMorph has presented great promise for the task of whole-body registration compared to previous method. However, the choice of method will be highly dependent upon the task. VoxelMorph provides results of lower quality and reduced flexibility but a computation time of only a few seconds.
|
|
| 33. |
- Ekström, Simon, 1991-
(författare)
-
Efficient GPU-based Image Registration : for Detailed Large-Scale Whole-body Analysis
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Imaging has become an important aspect of medicine, enabling visualization of internals in a non-invasive manner. The rapid advancement and adoption of imaging techniques have led to a demand for tools able to take advantage of the information that is produced. Medical image analysis aims to extract relevant information from acquired images to aid diagnostics in healthcare and increase the understanding within medical research. The main subject of this thesis, image registration, is a widely used tool in image analysis that can be employed to find a spatial transformation aligning a set of images. One application, that is described in detail in this thesis, is the use of image registration for large-scale analysis of whole-body images through the utilization of the correspondences defined by the resulting transformations. To produce detailed results, the correspondences, i.e. transformations, need to be of high resolution and the quality of the result has a direct impact on the quality of the analysis. Also, this type of application aims to analyze large cohorts and the value of a registration method is not only weighted by its ability to produce an accurate result but also by its efficiency. This thesis presents two contributions on the subject; a new method for efficient image registration with the ability to produce dense deformable transformations, and the application of the presented method in large-scale analysis of a whole-body dataset acquired using an integrated positron emission tomography (PET) and magnetic resonance imaging (MRI) system. In this thesis, it is shown that efficient and detailed image registration can be performed by employing graph cuts and a heuristic where the optimization is performed on subregions of the image. The performance can be improved further by the efficient utilization of a graphics processing unit (GPU). It is also shown that the method can be employed to produce a model on health based on a PET-MRI dataset which can be utilized to automatically detect pathology in the imaging.
|
|
| 34. |
- Ekström, Simon, 1991-, et al.
(författare)
-
Fast graph-cut based optimization for practical dense deformable registration of volume images
- 2020
-
Ingår i: Computerized Medical Imaging and Graphics. - : Elsevier. - 0895-6111 .- 1879-0771. ; 84
-
Tidskriftsartikel (refereegranskat)abstract
- Deformable image registration is a fundamental problem in medical image analysis, with applications such as longitudinal studies, population modeling, and atlas-based image segmentation. Registration is often phrased as an optimization problem, i.e., finding a deformation field that is optimal according to a given objective function. Discrete, combinatorial, optimization techniques have successfully been employed to solve the resulting optimization problem. Specifically, optimization based on α-expansion with minimal graph cuts has been proposed as a powerful tool for image registration. The high computational cost of the graph-cut based optimization approach, however, limits the utility of this approach for registration of large volume images. Here, we propose to accelerate graph-cut based deformable registration by dividing the image into overlapping sub-regions and restricting the α-expansion moves to a single sub-region at a time. We demonstrate empirically that this approach can achieve a large reduction in computation time - from days to minutes - with only a small penalty in terms of solution quality. The reduction in computation time provided by the proposed method makes graph-cut based deformable registration viable for large volume images. Graph-cut based image registration has previously been shown to produce excellent results, but the high computational cost has hindered the adoption of the method for registration of large medical volume images. Our proposed method lifts this restriction, requiring only a small fraction of the computational cost to produce results of comparable quality.
|
|
| 35. |
- Ekström, Simon, 1991-, et al.
(författare)
-
Faster dense deformable image registration by utilizing both CPU and GPU
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Purpose: Image registration is an important aspect of medical image analysis and a key component in many analysis concepts. Applications include fusion of multimodal images, multi-atlas segmentation, and whole-body analysis. Deformable image registration is often computationally expensive, and the need for efficient registration methods is highlighted by the emergence of large-scale image databases, e.g., the UK Biobank, providing imaging from 100 000 participants.Approach: We present a heterogeneous computing approach, utilizing both the CPU and the GPU, to accelerate a previously proposed image registration method. The parallelizable task of computing the matching criterion is offloaded to the GPU, where it can be computed efficiently, while the more complex optimization task is performed on the CPU. To lessen the impact of data synchronization between the CPU and GPU we propose a pipeline model, effectively overlapping computational tasks with data synchronization. The performance is evaluated on a brain labeling task and compared with a CPU implementation of the same method and the popular Advanced Normalization Tools (ANTs) software.Results: The proposed method presents a speed-up by a factor of 4 and 8 against the CPU implementation and the ANTs software respectively. A significant improvement in labeling quality was also observed, with measured mean Dice overlaps of 0.712 and 0.701 for our method and ANTs respectively.Conclusions: We showed that the proposed method compares favorably to the ANTs software yielding both a significant speed-up and an improvement in labeling quality. The registration method together with the proposed parallelization strategy is implemented as an open-source software package, deform.
|
|
| 36. |
- Ekström, Simon, 1991-, et al.
(författare)
-
Faster dense deformable image registration by utilizing both CPU and GPU
- 2021
-
Ingår i: Journal of Medical Imaging. - 2329-4302 .- 2329-4310. ; 8:1
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Image registration is an important aspect of medical image analysis and a key component in many analysis concepts. Applications include fusion of multimodal images, multi-atlas segmentation, and whole-body analysis. Deformable image registration is often computationally expensive, and the need for efficient registration methods is highlighted by the emergence of large-scale image databases, e.g., the UK Biobank, providing imaging from 100,000 participants. Approach: We present a heterogeneous computing approach, utilizing both the CPU and the graphics processing unit (GPU), to accelerate a previously proposed image registration method. The parallelizable task of computing the matching criterion is offloaded to the GPU, where it can be computed efficiently, while the more complex optimization task is performed on the CPU. To lessen the impact of data synchronization between the CPU and GPU, we propose a pipeline model, effectively overlapping computational tasks with data synchronization. The performance is evaluated on a brain labeling task and compared with a CPU implementation of the same method and the popular advanced normalization tools (ANTs) software. Results: The proposed method presents a speed-up by factors of 4 and 8 against the CPU implementation and the ANTs software, respectively. A significant improvement in labeling quality was also observed, with measured mean Dice overlaps of 0.712 and 0.701 for our method and ANTs, respectively. Conclusions: We showed that the proposed method compares favorably to the ANTs software yielding both a significant speed-up and an improvement in labeling quality. The registration method together with the proposed parallelization strategy is implemented as an open-source software package, deform.
|
|
| 37. |
- Engelsen Etterlin, Pernille, et al.
(författare)
-
Osteochondrosis, Synovial Fossae, and Articular Indentations in the Talus and Distal Tibia of Growing Domestic Pigs and Wild Boars
- 2017
-
Ingår i: Veterinary pathology. - : SAGE Publications. - 0300-9858 .- 1544-2217. ; 54:3, s. 445-456
-
Tidskriftsartikel (refereegranskat)abstract
- Articular osteochondrosis (OC) often develops in typical locations within joints, and the characterization of OC distribution in the pig tarsus is incomplete. Prevalence of OC is high in domestic pigs but is presumed to be low in wild boars. Postmortem and computed tomography (CT) examinations of the talus and distal tibia from 40 domestic pigs and 39 wild boars were evaluated for the locations and frequencies of OC, synovial fossae, and other articular indentations, and frequency distribution maps were made. All domestic pigs but only 5 wild boars (13%) had OC on the talus. In domestic pigs, OC consistently affected the axial aspect of the medial trochlea tali in 11 (28%) joints and the distomedial talus in 26 (65%) joints. In wild boars, all OC lesions consistently affected the distomedial talus. On the articular surface of the distal tibia, all domestic pigs and 34 wild boars (87%) had synovial fossae and 7 domestic pigs (18%) had superficial cartilage fibrillation opposite an OC lesion (kissing lesion). Other articular indentations occurred in the intertrochlear groove of the talus in all domestic pigs and 13 wild boars (33%) and were less common on the trochlea tali. The prevalence of tarsal OC in wild boars is low. In domestic pigs and wild boars, OC is typically localized to the distomedial talus and in domestic pigs also to the medial trochlea tali. Further investigations into the reasons for the low OC prevalence in wild boars may help in developing strategies to reduce OC incidence in domestic pigs.
|
|
| 38. |
|
|
| 39. |
|
|
| 40. |
- Fransson, Samuel, et al.
(författare)
-
Intrafractional motion models based on principal components in Magnetic Resonance guided prostate radiotherapy
- 2021
-
Ingår i: Physics and Imaging in Radiation Oncology. - : Elsevier. - 2405-6316. ; 20, s. 17-22
-
Tidskriftsartikel (refereegranskat)abstract
- Background and purpose: Devices that combine an MR-scanner with a Linac for radiotherapy, referred to as MR-Linac systems, introduce the possibility to acquire high resolution images prior and during treatment. Hence, there is a possibility to acquire individualised learning sets for motion models for each fraction and the construction of intrafractional motion models. We investigated the feasibility for a principal component analysis (PCA) based, intrafractional motion model of the male pelvic region.Materials and methods: 4D-scans of nine healthy male volunteers were utilized, FOV covering the entire pelvic region including prostate, bladder and rectum with manual segmentation of each organ at each time frame. Deformable image registration with an optical flow algorithm was performed for each subject with the first time frame as reference. PCA was performed on a subset of the resulting displacement vector fields to construct individualised motion models evaluated on the remaining fields.Results: The registration algorithm produced accurate registration result, in general DICE overlap >0.95 across all time frames. Cumulative variance of the eigen values from the PCA showed that 50% or more of the motion is explained in the first component for all subjects. However, the size and direction for the components differed between subjects. Adding more than two components did not improve the accuracy significantly and the model was able to explain motion down to about 1 mm.onclusions: An individualised intrafractional male pelvic motion model is feasible. Geometric accuracy was about 1 mm based on 1-2 principal components.
|
|
| 41. |
- Fransson, Samuel, 1991-
(författare)
-
Machine Learning in Magnetic Resonance-Guided Adaptive Radiotherapy
- 2024
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In radiotherapy, treatments are frequently distributed over multiple weeks, and the radiation dose delivered across several sessions. A significant hurdle in this approach is the anatomical changes that occur between the planning stage and subsequent treatment sessions, leading to uncertainties in the treatment. The MR-Linac system, which combines a linear accelerator with an MRI scanner, addresses this issue by allowing for daily adjustments to the treatment plan based on the patient's current anatomy. However, the process for making these adjustments, involving image fusion, re-contouring, and plan re-optimization, can be quite elaborate and time-consuming. This project aimed to identify opportunities within the daily treatment routine where machine learning and deep learning could streamline the process, thereby enhancing efficiency, with a focus on prostate cancer treatments due to their frequent occurrence at our facility. We leveraged deep learning to train patient-specific models for segmenting anatomical structures in daily MRI scans, matching the accuracy of existing deformable image registration techniques. Furthermore, we extended this concept to segmenting structures and predicting radiation dose distributions, offering a swift assessment of potential dose distribution before engaging in the more complex manual workflow. This could aid in selecting the most suitable adaptation method more quickly. Additionally, we developed motion models for intrafractional motion and for segmenting images at lower resolutions to facilitate a target tracking process. Throughout this project, we showed how machine learning and deep learning techniques could contribute to optimizing the daily MR-Linac workflow.
|
|
| 42. |
- Fransson, Samuel, et al.
(författare)
-
Patient specific deep learning based segmentation for magnetic resonance guided prostate radiotherapy
- 2022
-
Ingår i: Physics and Imaging in Radiation Oncology. - : Elsevier. - 2405-6316. ; 23, s. 38-42
-
Tidskriftsartikel (refereegranskat)abstract
- Background and Purpose: Treatments on combined Magnetic Resonance (MR) scanners and Linear Accelerators (Linacs) for radiotherapy, called MR-Linacs, often require daily contouring. Currently, deformable image registration (DIR) algorithms propagate contours from reference scans, however large shape and size changes can be troublesome. Artificial neural network (ANN) based contouring may alleviate this issue, however generally requires large datasets for training. Mitigating the problem of scarcity of data, we propose patient specific networks trained on a single dataset for each patient, for contouring onto the following datasets in an adaptive MR-Linacworkflow. Materials and Methods: MR-scans from 17 prostate patients treated on an MR-Linac with contours of Clinical Target Volume (CTV), bladder and rectum were utilized. U-net shaped models were trained based on the image from the first fraction of each patient, and subsequently applied onto the following treatment images. Results were compared with manual contours in terms of the Dice coefficient and Added Path Length (APL). As benchmark, contours propagated through the clinical DIR algorithm were similarly evaluated. Results: In Dice coefficient the ANN output was 0.92 +/- 0.03, 0.93 +/- 0.07 and 0.84 +/- 0.10 while for DIR 0.95 +/- 0.03, 0.93 +/- 0.08, 0.88 +/- 0.06 for CTV, bladder and rectum respectively. Similarly, APL where 3109 +/- 1642, 7250 +/- 4234 and 5041 +/- 2666 for ANN and 1835 +/- 1621, 7236 +/- 4287 and 4170 +/- 2920 voxels for DIR. Conclusions: Patient specific ANN models trained on images from the first fraction of a prostate MR-Linac treatment showed similar accuracy when applied to the subsequent fraction images as a clinically implemented DIR method.
|
|
| 43. |
|
|
| 44. |
- Gustavson, Stefan, 1965-, et al.
(författare)
-
Anti-aliased Euclidean distance transform
- 2011
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655 .- 1872-7344. ; 32:2, s. 252-257
-
Tidskriftsartikel (refereegranskat)abstract
- We present a modified distance measure for use with distance transforms of anti-aliased, area sampled grayscale images of arbitrary binary contours. The modified measure can be used in any vector-propagation Euclidean distance transform. Our test implementation in the traditional SSED8 algorithm shows a considerable improvement in accuracy and homogeneity of the distance field compared to a traditional binary image transform. At the expense of a 10× slowdown for a particular image resolution, we achieve an accuracy comparable to a binary transform on a supersampled image with 16 × 16 higher resolution, which would require 256 times more computations and memory.
|
|
| 45. |
- Issac Niwas, Swamidoss, et al.
(författare)
-
Automated classification of immunostaining patterns in breast tissue from the Human Protein Atlas
- 2013
-
Ingår i: Journal of Pathology Informatics. - : Elsevier BV. - 2229-5089 .- 2153-3539. ; 4:14
-
Tidskriftsartikel (refereegranskat)abstract
- Background:The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/). It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA) are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples.Materials and Methods:The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM) features, complex wavelet co-occurrence matrix (CWCM) features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM)-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM) and linear discriminant analysis (LDA) classifier). Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue.Results:We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert.Conclusions:Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for quantification of staining patterns in histopathology have many applications, ranging from antibody quality control to tumor grading.
|
|
| 46. |
- Jansen, Marielle J A, et al.
(författare)
-
Patient-specific fine-tuning of CNNs for follow-up lesion quantification
- 2020
-
Ingår i: Journal of Medical Imaging.
-
Tidskriftsartikel (refereegranskat)abstract
- Convolutional neural network (CNN) methods have been proposed to quantify lesions in medical imaging. Commonly more than one imaging examination is available for a patient, but the serial information in these images often remains unused. CNNbased methods have the potential to extract valuable information from previously acquired imaging to better quantify current imaging of the same patient. A pre-trained CNN can be updated with a patient’s previously acquired imaging: patient-specific fine-tuning. In this work, we studied the improvement in performance of lesion quantification methods on MR images after fine-tuning compared to a base CNN. We applied the method to two different approaches: the detection of liver metastases and the segmentation of brain white matter hyperintensities (WMH). The patient-specific fine-tuned CNN has a better performance than the base CNN. For the liver metastases, the median true positive rate increases from 0.67 to 0.85. For the WMH segmentation, the mean Dice similarity coefficient increases from 0.82 to 0.87. In this study we showed that patient-specific fine-tuning has potential to improve the lesion quantification performance of general CNNs by exploiting the patient’s previously acquired imaging
|
|
| 47. |
- Jansen, Marielle J. A., et al.
(författare)
-
Patient-specific fine-tuning of convolutional neural networks for follow-up lesion quantification
- 2020
-
Ingår i: Journal of Medical Imaging. - : SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS. - 2329-4302 .- 2329-4310. ; 7:6
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Convolutional neural network (CNN) methods have been proposed to quantify lesions in medical imaging. Commonly, more than one imaging examination is available for a patient, but the serial information in these images often remains unused. CNN-based methods have the potential to extract valuable information from previously acquired imaging to better quantify lesions on current imaging of the same patient.Approach: A pretrained CNN can be updated with a patient's previously acquired imaging: patient-specific fine-tuning (FT). In this work, we studied the improvement in performance of lesion quantification methods on magnetic resonance images after FT compared to a pretrained base CNN. We applied the method to two different approaches: the detection of liver metastases and the segmentation of brain white matter hyperintensities (WMH).Results: The patient-specific fine-tuned CNN has a better performance than the base CNN. For the liver metastases, the median true positive rate increases from 0.67 to 0.85. For the WMH segmentation, the mean Dice similarity coefficient increases from 0.82 to 0.87.Conclusions: We showed that patient-specific FT has the potential to improve the lesion quantification performance of general CNNs by exploiting a patient's previously acquired imaging.
|
|
| 48. |
- Jönsson, Hanna, et al.
(författare)
-
An image registration method for voxel-wise analysis of whole-body oncological PET-CT
- 2022
-
Ingår i: Scientific Reports. - : Springer Nature. - 2045-2322. ; 12
-
Tidskriftsartikel (refereegranskat)abstract
- Whole-body positron emission tomography-computed tomography (PET-CT) imaging in oncology provides comprehensive information of each patient's disease status. However, image interpretation of volumetric data is a complex and time-consuming task. In this work, an image registration method targeted towards computer-aided voxel-wise analysis of whole-body PET-CT data was developed. The method used both CT images and tissue segmentation masks in parallel to spatially align images step-by-step. To evaluate its performance, a set of baseline PET-CT images of 131 classical Hodgkin lymphoma (cHL) patients and longitudinal image series of 135 head and neck cancer (HNC) patients were registered between and within subjects according to the proposed method. Results showed that major organs and anatomical structures generally were registered correctly. Whole-body inverse consistency vector and intensity magnitude errors were on average less than 5 mm and 45 Hounsfield units respectively in both registration tasks. Image registration was feasible in time and the nearly automatic pipeline enabled efficient image processing. Metabolic tumor volumes of the cHL patients and registration-derived therapy-related tissue volume change of the HNC patients mapped to template spaces confirmed proof-of-concept. In conclusion, the method established a robust point-correspondence and enabled quantitative visualization of group-wise image features on voxel level.
|
|
| 49. |
- Kullberg, Joel, 1979-, et al.
(författare)
-
Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies
- 2017
-
Ingår i: Scientific Reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 7
-
Tidskriftsartikel (refereegranskat)abstract
- Computed Tomography (CT) allows detailed studies of body composition and its association with metabolic and cardiovascular disease. The purpose of this work was to develop and validate automated and manual image processing techniques for detailed and efficient analysis of body composition from CT data. The study comprised 107 subjects examined in the Swedish CArdioPulmonary BioImage Study (SCAPIS) using a 3-slice CT protocol covering liver, abdomen, and thighs. Algorithms were developed for automated assessment of liver attenuation, visceral (VAT) and subcutaneous (SAT) abdominal adipose tissue, thigh muscles, subcutaneous, subfascial (SFAT) and intermuscular adipose tissue. These were validated using manual reference measurements. SFAT was studied in selected subjects were the fascia lata could be visually identified (approx. 5%). In addition, precision of manual measurements of intra-(IPAT) and retroperitoneal adipose tissue (RPAT) and deep-and superficial SAT was evaluated using repeated measurements. Automated measurements correlated strongly to manual reference measurements. The SFAT depot showed the weakest correlation (r = 0.744). Automated VAT and SAT measurements were slightly, but significantly overestimated (<= 4.6%, p <= 0.001). Manual segmentation of abdominal sub-depots showed high repeatability (CV <= 8.1%, r >= 0.930). We conclude that the low dose CT-scanning and automated analysis makes the setup suitable for large-scale studies.
|
|
| 50. |
- Kundu, Swagata, et al.
(författare)
-
3-D Attention-SEV-Net for Segmentation of Post-operative Glioblastoma with Interactive Correction of Over-Segmentation
- 2023
-
Ingår i: Pattern Recognition and Machine Intelligence, PREMI 2023. - : Springer. - 9783031451690 - 9783031451706 ; , s. 380-387
-
Konferensbidrag (refereegranskat)abstract
- Accurate localization and volumetric quantification of postoperative glioblastoma are of profound importance for clinical applications like post-surgery treatment planning, monitoring of tumor regrowth, and radiotherapy map planning. Manual delineation consumes more time and error prone thus automated 3-D quantification of brain tumors using deep learning algorithms from MRI scans has been used in recent years. The shortcoming with automated segmentation is that it often over-segments or under-segments the tumor regions. An interactive deep-learning tool will enable radiologists to correct the over-segmented and under-segmented voxels. In this paper, we proposed a network named Attention-SEV-Net which outperforms state-of-the-art network architectures. We also developed an interactive graphical user interface, where the initial 3-D segmentation of contrast-enhanced tumor can be interactively corrected to remove falsely detected isolated tumor regions. Attention-SEV-Net is trained with BraTS-2021 training data set and tested on Uppsala University post-operative glioblastoma dataset. The methodology outperformed state-of-the-art networks like U-Net, VNet, Attention U-Net and Residual U-Net. The mean dice score achieved is 0.6682 and the mean Hausdorff distance-95 got is 8.96mm for the Uppsala University dataset.
|
|
