2020/08/29 by Odyssée Merveille, Merveille, Odyssee, Thomas Lampert +9
Computer Science · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Medical Image Segmentation Techniques
paper · pdf · doi:10.48550/arxiv.2008.13050
openalex publication_date 2020/08/29 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Objective: This article presents an automatic image processing framework to\nextract quantitative high-level information describing the micro-environment of\nglomeruli in consecutive whole slide images (WSIs) processed with different\nstaining modalities of patients with chronic kidney rejection after kidney\ntransplantation. Methods: This four-step framework consists of: 1) approximate\nrigid registration, 2) cell and anatomical structure segmentation 3) fusion of\ninformation from different stainings using a newly developed registration\nalgorithm 4) feature extraction. Results: Each step of the framework is\nvalidated independently both quantitatively and qualitatively by pathologists.\nAn illustration of the different types of features that can be extracted is\npresented. Conclusion: The proposed generic framework allows for the analysis\nof the micro-environment surrounding large structures that can be segmented\n(either manually or automatically). It is independent of the segmentation\napproach and is therefore applicable to a variety of biomedical research\nquestions. Significance: Chronic tissue remodelling processes after kidney\ntransplantation can result in interstitial fibrosis and tubular atrophy (IFTA)\nand glomerulosclerosis. This pipeline provides tools to quantitatively analyse,\nin the same spatial context, information from different consecutive WSIs and\nhelp researchers understand the complex underlying mechanisms leading to IFTA\nand glomerulosclerosis.\n