{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Seesawad N"],"funding":["NSRF via the Program Management Unit for Human Resources &amp;amp; Institutional Development, Research and Innovation","New Discovery and Frontier Research"],"pagination":["514-523"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11268940"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["5"],"pubmed_abstract":["<i>Background:</i> Deep learning models for patch classification in whole-slide images (WSIs) have shown promise in assisting follicular lymphoma grading. However, these models often require pathologists to identify centroblasts and manually provide refined labels for model optimization. <i>Objective:</i> To address this limitation, we propose <i>PseudoCell</i>, an object detection framework for automated centroblast detection in WSI, eliminating the need for extensive pathologist's refined labels. <i>Methods:</i> <i>PseudoCell</i> leverages a combination of pathologist-provided centroblast labels and pseudo-negative labels generated from undersampled false-positive predictions based on cell morphology features. This approach reduces the reliance on time-consuming manual annotations. <i>Re"],"journal":["IEEE open journal of engineering in medicine and biology"],"pubmed_title":["PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection."],"pmcid":["PMC11268940"],"funding_grant_id":["B38G670007","R016420005"],"pubmed_authors":["Hnoohom N","Sudhawiyangkul T","Thuwajit C","Ittichaiwong P","Boonsakan P","Veerakanjana K","Seesawad N","Charngkaew K","Wilaiprasitporn T","Sripodok S","Pongpaibul A","Thuwajit P","Angkathunyakul N","Yuenyong S","Sawangjai P"],"additional_accession":[]},"is_claimable":false,"name":"PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection.","description":"<i>Background:</i> Deep learning models for patch classification in whole-slide images (WSIs) have shown promise in assisting follicular lymphoma grading. However, these models often require pathologists to identify centroblasts and manually provide refined labels for model optimization. <i>Objective:</i> To address this limitation, we propose <i>PseudoCell</i>, an object detection framework for automated centroblast detection in WSI, eliminating the need for extensive pathologist's refined labels. <i>Methods:</i> <i>PseudoCell</i> leverages a combination of pathologist-provided centroblast labels and pseudo-negative labels generated from undersampled false-positive predictions based on cell morphology features. This approach reduces the reliance on time-consuming manual annotations. <i>Re","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024","modification":"2026-04-08T18:48:33.434Z","creation":"2025-04-05T13:57:21.913Z"},"accession":"S-EPMC11268940","cross_references":{"pubmed":["39050971"],"doi":["10.1109/OJEMB.2024.3407351"]}}