{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:14:14Z","timestamp":1782861254635,"version":"3.54.5"},"reference-count":20,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Histopathology"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:sec><jats:title>Aims<\/jats:title><jats:p>Accurately and efficiently identifying mitotic figures (MFs) is crucial for diagnosing and grading various cancers, including glioblastoma (GBM), a highly aggressive brain tumour requiring precise and timely intervention. Traditional manual counting of MFs in whole slide images (WSIs) is labour\u2010intensive and prone to interobserver variability. Our study introduces a deep active learning framework that addresses these challenges with minimal human intervention.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods and results<\/jats:title><jats:p>We utilized a dataset of GBM WSIs from The Cancer Genome Atlas (TCGA). Our framework integrates convolutional neural networks (CNNs) with an active learning strategy. Initially, a CNN is trained on a small, annotated dataset. The framework then identifies uncertain samples from the unlabelled data pool, which are subsequently reviewed by experts. These ambiguous cases are verified and used for model retraining. This iterative process continues until the model achieves satisfactory performance. Our approach achieved 81.75% precision and 82.48% recall for MF detection. For MF subclass classification, it attained an accuracy of 84.1%. Furthermore, this approach significantly reduced annotation time \u2010 approximately 900\u2009min across 66 WSIs \u2010 cutting the effort nearly in half compared to traditional methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Our deep active learning framework demonstrates a substantial improvement in both efficiency and accuracy for MF detection and classification in GBM WSIs. By reducing reliance on large annotated datasets, it minimizes manual effort while maintaining high performance. This methodology can be generalized to other medical imaging tasks, supporting broader applications in the healthcare domain.<\/jats:p><\/jats:sec>","DOI":"10.1111\/his.15506","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T01:26:00Z","timestamp":1751592360000},"page":"536-547","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling"],"prefix":"10.1111","volume":"87","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1290-1936","authenticated-orcid":false,"given":"Eric","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science Western University  London Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"August","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Pathology and Lab Medicine Western University  London Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pramath","family":"Kakodkar","sequence":"additional","affiliation":[{"name":"Department of Pathology and Lab Medicine University of Saskatchewan  Saskatoon Saskatchewan Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yayuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Pathology and Lab Medicine University of Saskatchewan  Saskatoon Saskatchewan Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science Western University  London Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of Computer Science Western University  London Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4928-2742","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Pathology and Lab Medicine Western University  London Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,7,3]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1188\/16.CJON.S1.2-8"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-016-1545-1"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.31.1.8"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2013-0093-CP"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/make5040083"},{"key":"e_1_2_10_7_1","unstructured":"JocherG ChaurasiaA JingQ.Ultralytics YOLO. 2023. Ultralytics."},{"key":"e_1_2_10_8_1","unstructured":"LiuE HanY LingC.AI4Path. Western University."},{"key":"e_1_2_10_9_1","first-page":"105","article-title":"Adaptive thresholding technique for segmentation and Juxtapleural nodules inclusion in lung segments","volume":"8","author":"Rehman MZ","year":"2016","journal-title":"Int J Bio\u2010Sci Bio\u2010Technol"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","unstructured":"MacenkoM NiethammerM MarronJSet\u00a0al.A method for normalizing histology slides for quantitative analysis. In 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro 1107\u20131110. 2009.https:\/\/doi.org\/10.1109\/ISBI.2009.5193250.","DOI":"10.1109\/ISBI.2009.5193250"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/jmi.12001"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"LinT\u2010Y GoyalP GirshickR HeK Doll\u00e1rP.Focal loss for dense object detection. In 2017 IEEE International Conference on Computer Vision (ICCV) 2999\u20133007. 2017.https:\/\/doi.org\/10.1109\/ICCV.2017.324.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_10_13_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization. 2017. Preprint at 10.48550\/arXiv.1412.6980."},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"e_1_2_10_15_1","unstructured":"A gentle introduction to early stopping to avoid overtraining neural networks \u2010 machinelearningmastery.com.https:\/\/machinelearningmastery.com\/early\u2010stopping\u2010to\u2010avoid\u2010overtraining\u2010neural\u2010network\u2010models\/."},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2020.04.010"},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","unstructured":"GhiasiG CuiY SrinivasAet\u00a0al.Simple copy\u2010paste is a strong data augmentation method for instance segmentation. 2021. Preprint at 10.48550\/arXiv.2012.07177.","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"e_1_2_10_18_1","unstructured":"RenS HeK GirshickR SunJ.Faster R\u2010CNN: towards real\u2010time object detection with region proposal networks. 2016. Preprint at 10.48550\/arXiv.1506.01497."},{"key":"e_1_2_10_19_1","unstructured":"What is YOLOv5: a deep look into the internal features of the popular object detector.https:\/\/arxiv.org\/html\/2407.20892v1."},{"key":"e_1_2_10_20_1","unstructured":"What is Mean Average Precision (mAP) in Object Detection?Roboflow Blog. 2020.https:\/\/blog.roboflow.com\/mean\u2010average\u2010precision\/."},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-50681-5"}],"container-title":["Histopathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/his.15506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T18:17:05Z","timestamp":1758219425000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/his.15506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":20,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1111\/his.15506"],"URL":"https:\/\/doi.org\/10.1111\/his.15506","archive":["Portico"],"relation":{},"ISSN":["0309-0167","1365-2559"],"issn-type":[{"value":"0309-0167","type":"print"},{"value":"1365-2559","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,3]]},"assertion":[{"value":"2025-03-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}