| 1. |
- Wieslander, Håkan
(författare)
-
Application, Optimisation and Evaluation of Deep Learning for Biomedical Imaging
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Microscopy imaging is a powerful technique when studying biology at a cellular and sub-cellular level. When combined with digital image analysis it creates an invaluable tool for investigating complex biological processes and phenomena. However, imaging at the cell and sub-cellular level tends to generate large amounts of data which can be difficult to analyse, navigate and store. Despite these difficulties, large data volumes mean more information content which is beneficial for computational methods like machine learning, especially deep learning. The union of microscopy imaging and deep learning thus provides numerous opportunities for advancing our scientific understanding and uncovering interesting and useful biological insights.The work in this thesis explores various means for optimising information extraction from microscopy data utilising image analysis with deep learning. The focus is on three different imaging modalities: bright-field; fluorescence; and transmission electron microscopy. Within these modalities different learning-based image analysis and processing techniques are explored, ranging from image classification and detection to image restoration and translation. The main contributions are: (i) a computational method for diagnosing oral and cervical cancer based on smear samples and bright-field microscopy; (ii) a hierarchical analysis of whole-slide tissue images from fluorescence microscopy and introducing a confidence based measure for pixel classifications; (iii) an image restoration model for motion-degraded images from transmission electron microscopy with an evaluation of model overfitting on underlying textures; and (iv) an image-to-image translation (virtual staining) of cell images from bright-field to fluorescence microscopy, optimised for biological feature relevance. A common theme underlying all the investigations in this thesis is that the evaluation of the methods used is in relation to the biological question at hand.
|
|
| 2. |
- Gupta, Ankit, et al.
(författare)
-
Is brightfield all you need for MoA prediction?
- 2022
-
Konferensbidrag (refereegranskat)abstract
- Fluorescence staining techniques, such as Cell Painting, together with fluorescence microscopy have proven invaluable for visualizing and quantifying the effects that drugs and other perturbations have on cultured cells. However, fluorescence microscopy is expensive, time-consuming, and labor-intensive, and the stains applied can be cytotoxic, interfering with the activity under study. The simplest form of microscopy, brightfield microscopy, lacks these downsides, but the images produced have low contrast and the cellular compartments are difficult to discern. Nevertheless, by harnessing deep learning, these brightfield images may still be sufficient for various predictive purposes. In this study, we compared the predictive performance of models trained on fluorescence images to those trained on brightfield images for predicting the mechanism of action (MoA) of different drugs. We also extracted CellProfiler features from the fluorescence images and used them to benchmark the performance. Overall, we found comparable and correlated predictive performance for the two imaging modalities. This is promising for future studies of MoAs in time-lapse experiments.
|
|
| 3. |
- Beháňová, Andrea, et al.
(författare)
-
Spatial Statistics for Understanding Tissue Organization
- 2022
-
Ingår i: Frontiers in Physiology. - : Frontiers Media S.A.. - 1664-042X. ; 13
-
Forskningsöversikt (refereegranskat)abstract
- Interpreting tissue architecture plays an important role in gaining a better understanding of healthy tissue development and disease. Novel molecular detection and imaging techniques make it possible to locate many different types of objects, such as cells and/or mRNAs, and map their location across the tissue space. In this review, we present several methods that provide quantification and statistical verification of observed patterns in the tissue architecture. We categorize these methods into three main groups: Spatial statistics on a single type of object, two types of objects, and multiple types of objects. We discuss the methods in relation to four hypotheses regarding the methods' capability to distinguish random and non-random distributions of objects across a tissue sample, and present a number of openly available tools where these methods are provided. We also discuss other spatial statistics methods compatible with other types of input data.
|
|
| 4. |
- Bekkhus, Tove, et al.
(författare)
-
Automated detection of vascular remodeling in human tumor draining lymph nodes by the deep learning tool HEV-finder
- 2022
-
Ingår i: Journal of Pathology. - : John Wiley & Sons. - 0022-3417 .- 1096-9896. ; 258:1, s. 4-11
-
Tidskriftsartikel (refereegranskat)abstract
- Vascular remodeling is common in human cancer and has potential as future biomarkers for prediction of disease progression and tumor immunity status. It can also affect metastatic sites, including the tumor-draining lymph nodes (TDLNs). Dilation of the high endothelial venules (HEVs) within TDLNs has been observed in several types of cancer. We recently demonstrated that it is a premetastatic effect that can be linked to tumor invasiveness in breast cancer. Manual visual assessment of changes in vascular morphology is a tedious and difficult task, limiting high-throughput analysis. Here we present a fully automated approach for detection and classification of HEV dilation. By using 12,524 manually classified HEVs, we trained a deep-learning model and created a graphical user interface for visualization of the results. The tool, named the HEV-finder, selectively analyses HEV dilation in specific regions of the lymph nodes. We evaluated the HEV-finder's ability to detect and classify HEV dilation in different types of breast cancer compared to manual annotations. Our results constitute a successful example of large-scale, fully automated, and user-independent, image-based quantitative assessment of vascular remodeling in human pathology and lay the ground for future exploration of HEV dilation in TDLNs as a biomarker.
|
|
| 5. |
- Edfeldt, Gabriella, et al.
(författare)
-
Regular Use of Depot Medroxyprogesterone Acetate Causes Thinning of the Superficial Lining and Apical Distribution of Human Immunodeficiency Virus Target Cells in the Human Ectocervix
- 2022
-
Ingår i: Journal of Infectious Diseases. - : Oxford University Press. - 0022-1899 .- 1537-6613. ; 225:7, s. 1151-1161
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundThe hormonal contraceptive depot medroxyprogesterone acetate (DMPA) may be associated with an increased risk of acquiring human immunodeficiency virus (HIV). We hypothesize that DMPA use influences the ectocervical tissue architecture and HIV target cell localization.MethodsQuantitative image analysis workflows were developed to assess ectocervical tissue samples collected from DMPA users and control subjects not using hormonal contraception.ResultsCompared to controls, the DMPA group exhibited a significantly thinner apical ectocervical epithelial layer and a higher proportion of CD4+CCR5+ cells with a more superficial location. This localization corresponded to an area with a nonintact E-cadherin net structure. CD4+Langerin+ cells were also more superficially located in the DMPA group, although fewer in number compared to the controls. Natural plasma progesterone levels did not correlate with any of these parameters, whereas estradiol levels were positively correlated with E-cadherin expression and a more basal location for HIV target cells of the control group.ConclusionsDMPA users have a less robust epithelial layer and a more apical distribution of HIV target cells in the human ectocervix, which could confer a higher risk of HIV infection. Our results highlight the importance of assessing intact genital tissue samples to gain insights into HIV susceptibility factors.
|
|
| 6. |
- Gupta, Ankit, et al.
(författare)
-
SimSearch : A Human-in-The-Loop Learning Framework for Fast Detection of Regions of Interest in Microscopy Images
- 2022
-
Ingår i: IEEE journal of biomedical and health informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 2168-2194 .- 2168-2208. ; 26:8, s. 4079-4089
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: Large-scale microscopy-based experiments often result in images with rich but sparse information content. An experienced microscopist can visually identify regions of interest (ROIs), but this becomes a cumbersome task with large datasets. Here we present SimSearch, a framework for quick and easy user-guided training of a deep neural model aimed at fast detection of ROIs in large-scale microscopy experiments. Methods: The user manually selects a small number of patches representing different classes of ROIs. This is followed by feature extraction using a pre-trained deep-learning model, and interactive patch selection pruning, resulting in a smaller set of clean (user approved) and larger set of noisy (unapproved) training patches of ROIs and background. The pre-trained deep-learning model is thereafter first trained on the large set of noisy patches, followed by refined training using the clean patches. Results: The framework is evaluated on fluorescence microscopy images from a large-scale drug screening experiment, brightfield images of immunohistochemistry-stained patient tissue samples, and malaria-infected human blood smears, as well as transmission electron microscopy images of cell sections. Compared to state-of-the-art and manual/visual assessment, the results show similar performance with maximal flexibility and minimal a priori information and user interaction. Conclusions: SimSearch quickly adapts to different data sets, which demonstrates the potential to speed up many microscopy-based experiments based on a small amount of user interaction. Significance: SimSearch can help biologists quickly extract informative regions and perform analyses on large datasets helping increase the throughput in a microscopy experiment.
|
|
| 7. |
- Marco Salas, Sergio, et al.
(författare)
-
De novo spatiotemporal modelling of cell-type signatures in the developmental human heart using graph convolutional neural networks
- 2022
-
Ingår i: PloS Computational Biology. - : Public Library of Science (PLoS). - 1553-734X .- 1553-7358. ; 18:8
-
Tidskriftsartikel (refereegranskat)abstract
- With the emergence of high throughput single cell techniques, the understanding of the molecular and cellular diversity of mammalian organs have rapidly increased. In order to understand the spatial organization of this diversity, single cell data is often integrated with spatial data to create probabilistic cell maps. However, targeted cell typing approaches relying on existing single cell data achieve incomplete and biased maps that could mask the true diversity present in a tissue slide. Here we applied a de novo technique to spatially resolve and characterize cellular diversity of in situ sequencing data during human heart development. We obtained and made accessible well defined spatial cell-type maps of fetal hearts from 4.5 to 9 post conception weeks, not biased by probabilistic cell typing approaches. With our analysis, we could characterize previously unreported molecular diversity within cardiomyocytes and epicardial cells and identified their characteristic expression signatures, comparing them with specific subpopulations found in single cell RNA sequencing datasets. We further characterized the differentiation trajectories of epicardial cells, identifying a clear spatial component on it. All in all, our study provides a novel technique for conducting de novo spatial-temporal analyses in developmental tissue samples and a useful resource for online exploration of cell-type differentiation during heart development at sub-cellular image resolution.
|
|
| 8. |
- Wang, Y., et al.
(författare)
-
Improved breast cancer histological grading using deep learning
- 2022
-
Ingår i: Annals of Oncology. - : Elsevier. - 0923-7534 .- 1569-8041. ; 33:1, s. 89-98
-
Tidskriftsartikel (refereegranskat)abstract
- Background: The Nottingham histological grade (NHG) is a well-established prognostic factor for breast cancer that is broadly used in clinical decision making. However, similar to 50% of patients are classified as grade 2, an intermediate risk group with low clinical value. To improve risk stratification of NHG 2 breast cancer patients, we developed and validated a novel histological grade model (DeepGrade) based on digital whole-slide histopathology images (WSIs) and deep learning.Patients and methods: In this observational retrospective study, routine WSIs stained with haematoxylin and eosin from 1567 patients were utilised for model optimisation and validation. Model generalisability was further evaluated in an external test set with 1262 patients. NHG 2 cases were stratified into two groups, DG2-high and DG2-low, and the prognostic value was assessed. The main outcome was recurrence-free survival.Results: DeepGrade provides independent prognostic information for stratification of NHG 2 cases in the internal test set, where DG2-high showed an increased risk for recurrence (hazard ratio [HR] 2.94, 95% confidence interval [CI] 1.24-6.97, P = 0.015) compared with the DG2-low group after adjusting for established risk factors (independent test data). DG2-low also shared phenotypic similarities with NHG 1, and DG2-high with NHG 3, suggesting that the model identifies morphological patterns in NHG 2 that are associated with more aggressive tumours. The prognostic value of DeepGrade was further assessed in the external test set, confirming an increased risk for recurrence in DG2-high (HR 1.91, 95% CI 1.11-3.29, P = 0.019).Conclusions: The proposed model-based stratification of patients with NHG 2 tumours is prognostic and adds clinically relevant information over routine histological grading. The methodology offers a cost-effective alternative to molecular profiling to extract information relevant for clinical decisions.
|
|
| 9. |
|
|
