{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:06:27Z","timestamp":1789977987752,"version":"4.0.1"},"reference-count":60,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Bladder cancer remains one of the most prevalent urological malignancies, where early detection is critical for improving patient outcomes. Urine cytology provides a non-invasive and cost-effective screening modality; however, the development of automated diagnostic systems is challenged by the scarcity of expert-annotated data and the limited interpretability of deep learning models. To address these challenges, we propose EnBCDet, an explainable self-supervised framework for malignant cell detection in urine cytology images. The proposed approach leverages contrastive self-supervised learning to learn discriminative cytological representations from limited annotations and incorporates a specialized backbone within a single-stage object detection architecture for efficient malignant cell localization. In addition, we introduce a novel entropy-based explanation framework that quantitatively evaluates the information content of activation maps, enabling gradient-free, class-agnostic, and task-independent interpretation of learned feature representations. Experimental evaluation on cytological samples collected from 150 individuals demonstrates that EnBCDet outperforms existing approaches, achieving a mean precision of 0.991 and a mean recall of 0.926 while maintaining computational efficiency. Clinical validation further shows over 90% agreement with expert annotations, highlighting the practical utility of the proposed system. To the best of our knowledge, this is among the first studies to systematically interpret encoder-level representations in self-supervised cytological analysis. The proposed entropy-based framework provides robust insights into backbone feature learning, advancing both diagnostic performance and explainability for computer-aided urine cytology. The analysis code supporting this study is publicly available on GitHub at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/ArathyAvinash\/EnBCDet\">https:\/\/github.com\/ArathyAvinash\/EnBCDet<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/aea429","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T22:48:33Z","timestamp":1788907713000},"page":"055018","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-agnostic explainable contrastive learning model for malignant cell detection in urine cytology"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3337-0676","authenticated-orcid":true,"given":"Arathy Menon","family":"N P","sequence":"first","affiliation":[{"name":"National Institute of Technology Calicut"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8088-1526","authenticated-orcid":true,"given":"Ram S","family":"Iyer","sequence":"additional","affiliation":[{"name":"Rajiv Gandhi Institute of Petroleum Technology"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-2044","authenticated-orcid":false,"given":"Pournami P","family":"N","sequence":"additional","affiliation":[{"name":"National Institute of Technology Calicut"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9924-9046","authenticated-orcid":true,"given":"Jayaraj P","family":"B","sequence":"additional","affiliation":[{"name":"National Institute of Technology Calicut"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Pranab","family":"Dey","sequence":"additional","affiliation":[{"name":"Postgraduate Institute of Medical Education and Research"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"266","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"bpexaea429bib1","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00345-022-04253-3","type":"journal-article","article-title":"Urinary biomarkers for bladder cancer diagnosis and nmibc follow-up: a systematic review","volume":"41","author":"Soorojebally","year":"2023","journal-title":"World J. Urol."},{"key":"bpexaea429bib2","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/j.urolonc.2018.04.013","type":"journal-article","article-title":"Blue light cystoscopy for the diagnosis of bladder cancer: results from the us prospective multicenter registry","volume":"36","author":"Daneshmand","year":"2018","journal-title":"Urol. Oncol.: Semin. Orig. Investig."},{"key":"bpexaea429bib3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23111-1","type":"journal-article","article-title":"Noninvasive studies may have potential to replace cystoscopy in non-muscle invasive bladder cancer follow-up","volume":"12","author":"Lee","year":"2022","journal-title":"Sci. Rep."},{"key":"bpexaea429bib4","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1097\/00005392-199805000-00057","type":"journal-article","article-title":"Back propagation neural network in the discrimination of benign from malignant lower urinary tract lesions","volume":"159","author":"Pantazopoulos","year":"1998","journal-title":"J. Urol."},{"key":"bpexaea429bib5","doi-asserted-by":"publisher","first-page":"1555","DOI":"10.1002\/1097-0142(19840401)53:7<1555::aid-cncr2820530723>3.0.co;2-g","type":"journal-article","article-title":"Urinary cytology and bladder cancer. the cellular features of transitional cell neoplasms","volume":"53","author":"Murphy","year":"1984","journal-title":"Cancer"},{"key":"bpexaea429bib6","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.urolonc.2014.06.008","type":"journal-article","article-title":"Prospective analysis of sensitivity and specificity of urinary cytology and other urinary biomarkers for bladder cancer","volume":"33","author":"Yafi","year":"2015","journal-title":"Urol. Oncol.: Semin. Orig. Investig."},{"key":"bpexaea429bib7","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1111\/iju.15338","type":"journal-article","article-title":"Urinary markers for bladder cancer diagnosis: a review of current status and future challenges","volume":"31","author":"Tomiyama","year":"2024","journal-title":"Int. J. Urol."},{"key":"bpexaea429bib8","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/s13246-023-01341-5","type":"journal-article","article-title":"Dielectric properties of urine in relation to bladder cancer","volume":"47","author":"Zhu","year":"2023","journal-title":"Phys. Eng. Sci. Med."},{"key":"bpexaea429bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104649","type":"journal-article","article-title":"Deepcervix: a deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques","volume":"136","author":"Rahaman","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"bpexaea429bib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115927","type":"journal-article","article-title":"An ensemble deep learning for automatic prediction of papillary thyroid carcinoma using fine needle aspiration cytology","volume":"188","author":"Nguyen","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"bpexaea429bib11","first-page":"pp 1","type":"conference-proceedings","article-title":"A novel transformer-based pipeline for lung cytopathological whole slide image classification","author":"Li","year":"2023"},{"key":"bpexaea429bib12","first-page":"pp 580","type":"conference-proceedings","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"bpexaea429bib13","first-page":"pp 1440","type":"conference-proceedings","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"bpexaea429bib14","first-page":"pp 91","type":"journal-article","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"vol 28","author":"Ren","year":"2015"},{"key":"bpexaea429bib15","first-page":"pp 21","type":"conference-proceedings","article-title":"Ssd: single shot multibox detector","author":"Liu","year":"2016"},{"key":"bpexaea429bib16","article-title":"Overfeat: integrated recognition, localization and detection using convolutional networks","author":"Sermanet","year":"2013","type":"preprint"},{"key":"bpexaea429bib17","first-page":"pp 779","type":"conference-proceedings","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"bpexaea429bib18","first-page":"pp 2980","type":"conference-proceedings","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"bpexaea429bib19","first-page":"pp 10781","type":"conference-proceedings","article-title":"Efficientdet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"bpexaea429bib20","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.euo.2023.11.009","type":"journal-article","article-title":"A fully automated artificial intelligence system to assist pathologists\u2019 diagnosis to predict histologically high-grade urothelial carcinoma from digitized urine cytology slides using deep learning","volume":"7","author":"Tsuji","year":"2024","journal-title":"Eur. Urol. Oncol."},{"key":"bpexaea429bib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jasc.2023.07.007","type":"journal-article","article-title":"Evaluating the feasibility of a deep learning-based atypical cell gallery for clinical diagnosis in urine cytology","volume":"12","author":"Liu","year":"2023","journal-title":"J. Am. Soc. Cytopathol."},{"key":"bpexaea429bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2025.114259","type":"journal-article","article-title":"Interpretable machine learning for urothelial cells classification and risk scoring in urine cytology","volume":"29","author":"Xiong","year":"2026","journal-title":"Science"},{"key":"bpexaea429bib23","doi-asserted-by":"publisher","first-page":"3016","DOI":"10.21873\/invivo.13785","type":"journal-article","article-title":"An artificial intelligence-assisted diagnostic system improves upper urine tract cytology diagnosis","volume":"38","author":"Chang","year":"2024","journal-title":"In Vivo"},{"key":"bpexaea429bib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539","type":"journal-article","article-title":"Self-supervised learning for medical image analysis using image context restoration","volume":"58","author":"Chen","year":"2019","journal-title":"Med. Image Anal."},{"key":"bpexaea429bib25","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.9.6.064503","type":"journal-article","article-title":"Contrastive self-supervised learning from 100 million medical images with optional supervision","volume":"9","author":"Ghesu","year":"2022","journal-title":"J. Med. Imaging"},{"key":"bpexaea429bib26","first-page":"pp 807","type":"conference-proceedings","article-title":"Detectren: vehicle object detection using self-supervised learning based on light-weight network for low-power devices","author":"Fuhrmann","year":"2021"},{"key":"bpexaea429bib27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad092a","type":"journal-article","article-title":"Self-supervised enhanced thyroid nodule detection in ultrasound examination video sequences with multi-perspective evaluation","volume":"68","author":"Liu","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"bpexaea429bib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102879","type":"journal-article","article-title":"Dive into the details of self-supervised learning for medical image analysis","volume":"89","author":"Zhang","year":"2023","journal-title":"Med. Image Anal."},{"key":"bpexaea429bib29","doi-asserted-by":"publisher","first-page":"3695","DOI":"10.1007\/s11063-022-10919-1","type":"journal-article","article-title":"Btswin-unet: 3d u-shaped symmetrical swin transformer-based network for brain tumor segmentation with self-supervised pre-training","volume":"55","author":"Liang","year":"2023","journal-title":"Neural Process. Lett."},{"key":"bpexaea429bib30","first-page":"pp 1597","type":"conference-proceedings","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"bpexaea429bib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102464","type":"journal-article","article-title":"Deepsmile: contrastive self-supervised pre-training benefits msi and hrd classification directly from h&e whole-slide images in colorectal and breast cancer","volume":"79","author":"Schirris","year":"2022","journal-title":"Med. Image Anal."},{"key":"bpexaea429bib32","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100198","type":"journal-article","article-title":"Self supervised contrastive learning for digital histopathology","volume":"7","author":"Ciga","year":"2022","journal-title":"Mach. Learn. Appl."},{"key":"bpexaea429bib33","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","type":"journal-article","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"bpexaea429bib34","first-page":"pp 1135","type":"conference-proceedings","article-title":"why should i trust you?\u201d explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"bpexaea429bib35","doi-asserted-by":"publisher","first-page":"4765","DOI":"10.48550\/arXiv.1705.07874","type":"journal-article","article-title":"A unified approach to interpreting model predictions","volume":"vol 30","author":"Lundberg","year":"2017","journal-title":"Adv. in Neural Inf. Process. Syst."},{"key":"bpexaea429bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2025.101618","type":"journal-article","article-title":"Towards trustworthy ai-driven leukemia diagnosis: A hybrid hierarchical federated learning and explainable ai framework","volume":"53","author":"Pervez","year":"2025","journal-title":"Inform. Med. Unlocked"},{"key":"bpexaea429bib37","article-title":"Free software: MIT license","author":"Tzutalin: labelimg","year":"2015","type":"other"},{"key":"bpexaea429bib38","first-page":"pp 3225","type":"conference-proceedings","article-title":"Contrastive learning for depth prediction","author":"Fan","year":"2023"},{"key":"bpexaea429bib39","first-page":"pp 1857","type":"conference-proceedings","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"Sohn","year":"2016"},{"key":"bpexaea429bib40","first-page":"pp 7132","type":"conference-proceedings","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"bpexaea429bib41","first-page":"pp 1","type":"conference-proceedings","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"bpexaea429bib42","first-page":"pp 1","type":"conference-proceedings","article-title":"An inception based urothelial cell classification network for the detection of bladder carcinoma from urine cytology microscopic images","author":"Arathy Menon","year":"2023"},{"key":"bpexaea429bib43","first-page":"pp 6848","type":"conference-proceedings","article-title":"Shufflenet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"key":"bpexaea429bib44","article-title":"Shenggan: BCCD dataset","type":"other"},{"key":"bpexaea429bib45","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1186\/s12859-022-04824-6","type":"journal-article","article-title":"Accurate classification of white blood cells by coupling pre-trained resnet and densenet with scam mechanism","volume":"23","author":"Chen","year":"2022","journal-title":"BMC Bioinform."},{"key":"bpexaea429bib46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0261848","type":"journal-article","article-title":"WBC-amnet: automatic classification of WBC images using deep feature fusion network based on focalized attention mechanism","volume":"17","author":"Wang","year":"2022","journal-title":"PLoS One"},{"key":"bpexaea429bib47","doi-asserted-by":"publisher","first-page":"5246","DOI":"10.1364\/BOE.462905","type":"journal-article","article-title":"White blood cell classification via a discriminative region detection assisted feature aggregation network","volume":"13","author":"Jiang","year":"2022","journal-title":"Biomed. Opt. Express"},{"key":"bpexaea429bib48","article-title":"YOLO by ultralytics","author":"Jocher","year":"2023","type":"other"},{"key":"bpexaea429bib49","first-page":"pp 1289","type":"conference-proceedings","article-title":"Blood cell detection using deep learning on mobile platforms","author":"Jain","year":"2023"},{"key":"bpexaea429bib50","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2024.1373103","type":"journal-article","article-title":"Utility of faster R-CNN in methodological comparison and evaluation of reticulocytes","volume":"15","author":"Sun","year":"2024","journal-title":"Front. Physiol."},{"key":"bpexaea429bib51","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","type":"journal-article","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"bpexaea429bib52","doi-asserted-by":"publisher","first-page":"8427","DOI":"10.1038\/s41598-025-91720-7","type":"journal-article","article-title":"A two stage blood cell detection and classification algorithm based on improved YOLOv7 and EfficientNetv2","volume":"15","author":"Wang","year":"2025","journal-title":"Sci. Rep."},{"key":"bpexaea429bib53","article-title":"YOLOv5 by ultralytics","author":"Jocher","year":"2020","type":"other"},{"key":"bpexaea429bib54","article-title":"Ultralytics: ultralytics YOLOv8 documentation","year":"2023","type":"other"},{"key":"bpexaea429bib55","first-page":"pp 1","type":"conference-proceedings","article-title":"Yolov9: learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"bpexaea429bib56","doi-asserted-by":"publisher","first-page":"107984","DOI":"10.48550\/arXiv.2405.14458","type":"journal-article","article-title":"Yolov10: Real-time end-to-end object detection","volume":"vol 37","author":"Wang","year":"2024","journal-title":"Adv. in Neural Inf. Process. Syst."},{"key":"bpexaea429bib57","article-title":"Ultralytics: ultralytics YOLO11 documentation","year":"2024","type":"other"},{"key":"bpexaea429bib58","first-page":"pp 1314","type":"conference-proceedings","article-title":"Searching for mobilenetv3","author":"Howard","year":"2019"},{"key":"bpexaea429bib59","first-page":"pp 1","type":"conference-proceedings","article-title":"Heatmap-based explanation of yolov5 object detection with layer-wise relevance propagation","author":"Karasmanoglou","year":"2022"},{"key":"bpexaea429bib60","first-page":"pp 1","type":"conference-proceedings","article-title":"Eigen-cam: class activation map using principal components","author":"Muhammad","year":"2020"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T07:35:00Z","timestamp":1789976100000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aea429"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":60,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,9,21]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/aea429","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"assertion":[{"value":"Task-agnostic explainable contrastive learning model for malignant cell detection in urine cytology","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-06-11","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}