{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Amgad M"],"funding":["National Cancer Institute","NCI NIH HHS","U.S. National Institutes of Health"],"pagination":["513-519"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10142876"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["38(2)"],"pubmed_abstract":["Motivation
Nucleus detection, segmentation and classification are fundamental to high-resolution mapping of the tumor microenvironment using whole-slide histopathology images. The growing interest in leveraging the power of deep learning to achieve state-of-the-art performance often comes at the cost of explainability, yet there is general consensus that explainability is critical for trustworthiness and widespread clinical adoption. Unfortunately, current explainability paradigms that rely on pixel saliency heatmaps or superpixel importance scores are not well-suited for nucleus classification. Techniques like Grad-CAM or LIME provide explanations that are indirect, qualitative and/or nonintuitive to pathologists.Results
In this article, we present techniques to enable sca"],"journal":["Bioinformatics (Oxford, England)"],"pubmed_title":["Explainable nucleus classification using Decision Tree Approximation of Learned Embeddings."],"pmcid":["PMC10142876"],"funding_grant_id":["U01CA220401","U24CA19436201","U01 CA220401"],"pubmed_authors":["Elsebaie MAT","Atteya LA","Amgad M","Hussein H","Mohammed KH","Hafiz E","Manthey D","Elfandy H","Mobadersany P","Gutman DA","Cooper LAD"],"additional_accession":[]},"is_claimable":false,"name":"Explainable nucleus classification using Decision Tree Approximation of Learned Embeddings.","description":"Motivation
Nucleus detection, segmentation and classification are fundamental to high-resolution mapping of the tumor microenvironment using whole-slide histopathology images. The growing interest in leveraging the power of deep learning to achieve state-of-the-art performance often comes at the cost of explainability, yet there is general consensus that explainability is critical for trustworthiness and widespread clinical adoption. Unfortunately, current explainability paradigms that rely on pixel saliency heatmaps or superpixel importance scores are not well-suited for nucleus classification. Techniques like Grad-CAM or LIME provide explanations that are indirect, qualitative and/or nonintuitive to pathologists.Results
In this article, we present techniques to enable sca","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Jan","modification":"2025-04-05T11:27:47.348Z","creation":"2025-04-05T11:27:47.348Z"},"accession":"S-EPMC10142876","cross_references":{"pubmed":["34586355"],"doi":["10.1093/bioinformatics/btab670"]}}