{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T13:42:15Z","timestamp":1791639735953,"version":"4.3.4"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EPSRC DTP - EP\/W524682"],"award-info":[{"award-number":["EPSRC DTP - EP\/W524682"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BioStatus Ltd","award":["NA"],"award-info":[{"award-number":["NA"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Fluorescent microscopy using the DRAQ5 and Eosin probes has been shown in the literature to be capable of producing rapid tissue characterization through synthetic H&amp;E-like pseudoimages, which can be potentially utilized in the clinic. This study focuses on developing deep learning models for classification and segmentation of prostate tissue labeled with DRAQ5&amp;Eosin. The fluorophores provide highly specific features of nuclear and cytoplasmic content that allows for enhanced spatial resolution and multi-parametric analytics. The inter-dependencies of image acquisition and configuration variability on AI predictive accuracy is systematically interrogated. We are thus able to establish limits on experimental and analytical robustness in automated Gleason Grading (1\u20135) tissue samples of prostate cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>A labeling technique based on a far-red DNA probe DRAQ5, and Eosin allowed us to generate a two-channel fluorescent readout of prostatic tissue samples. Deep learning networks were employed to classify and segment DRAQ5 and Eosin fluorescent image regions into healthy and high\/low grade cancerous tissue. A subset of images were acquired with variable microscopy configurations (focus, noise, zoom, lens) to evaluate the robustness of the proposed experimental-analytical pipeline and reproducibility of predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Machine Leaning classifiers of High Grade Cancer (Gleason pattern 4 or 5) vs Healthy, Low Grade Cancer (Gleason pattern 3) vs Healthy, and High Grade Cancer vs Low Grade Cancer achieved an area under the curve of 0.9314, 0.8398, and 0.7715 respectively. Pixel wide cancer segmentation attained DICE scores of 0.8436, 0.5138, and 0.705 for background, healthy, and cancerous tissue respectively. The segmentation model also displayed robustness against a broad range of induced acquisition variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Overall, DRAQ5 and Eosin labeling in combination with AI tools demonstrate a potential pipeline used in diagnostic clinical application when employing fluorescent imaging. Future research could expand and bring this combined fluorescent biomarker and AI methodology to the clinic.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0345014","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:03:27Z","timestamp":1774555407000},"page":"e0345014","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Prostate cancer tissue mapping and stratification using DRAQ5 and Eosin fluorescent labels integrated with AI classification and segmentation algorithms"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8791-8227","authenticated-orcid":true,"given":"Michail Georgios","family":"Papachristos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1452-8813","authenticated-orcid":true,"given":"Emiliano","family":"Spezi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0871-939X","authenticated-orcid":true,"given":"Carolina","family":"Fuentes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioulia","family":"Evangelou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David Hywel","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fiyinfoluwa","family":"Akinade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie","family":"Wiltshire","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachel J.","family":"Errington","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitris","family":"Parthimos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,26]]},"reference":[{"issue":"3","key":"pone.0345014.ref001","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"F Bray","year":"2024","journal-title":"CA: a cancer journal for clinicians"},{"issue":"10","key":"pone.0345014.ref002","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2017-017729","article-title":"Prostate-specific antigen (PSA) testing of men in UK general practice: a 10-year longitudinal cohort study","volume":"7","author":"GJ Young","year":"2017","journal-title":"BMJ Open"},{"issue":"9","key":"pone.0345014.ref003","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1097\/01.pas.0000173646.99337.b1","article-title":"The 2005 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason Grading of Prostatic Carcinoma","volume":"29","author":"ISUP Grading Committee","year":"2005","journal-title":"Am J Surg Pathol"},{"issue":"1","key":"pone.0345014.ref004","doi-asserted-by":"crossref","first-page":"15","DOI":"10.4103\/0973-029X.33958","article-title":"Comparison of three different methods of tissue processing","volume":"11","author":"B Sivapathasundharam","year":"2007","journal-title":"J Oral Maxillofac Pathol"},{"issue":"3","key":"pone.0345014.ref005","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.21037\/tau-20-1237","article-title":"Current and future perspectives of digital microscopy with fluorescence confocal microscope for prostate tissue interpretation: a narrative review","volume":"10","author":"B Rocco","year":"2021","journal-title":"Transl Androl Urol"},{"issue":"2","key":"pone.0345014.ref006","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.ajpath.2021.10.010","article-title":"Slide over: advances in slide-free optical microscopy as drivers of diagnostic pathology","volume":"192","author":"Y Liu","year":"2022","journal-title":"Am J Pathol"},{"issue":"7","key":"pone.0345014.ref007","doi-asserted-by":"crossref","first-page":"0084","DOI":"10.1038\/s41551-017-0084","article-title":"Light-sheet microscopy for slide-free non-destructive pathology of large clinical specimens","volume":"1","author":"AK Glaser","year":"2017","journal-title":"Nat Biomed Eng"},{"issue":"3","key":"pone.0345014.ref008","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1111\/bju.14754","article-title":"Ex vivo fluorescence confocal microscopy: the first application for real-time pathological examination of prostatic tissue","volume":"124","author":"S Puliatti","year":"2019","journal-title":"BJU Int"},{"issue":"10","key":"pone.0345014.ref009","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0165530","article-title":"DRAQ5 and Eosin ('D&E\u2019) as an Analog to Hematoxylin and Eosin for Rapid Fluorescence Histology of Fresh Tissues","volume":"11","author":"KN Elfer","year":"2016","journal-title":"PLoS One"},{"issue":"3","key":"pone.0345014.ref010","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1038\/modpathol.2013.158","article-title":"Fluorescence confocal microscopy for pathologists","volume":"27","author":"M Ragazzi","year":"2014","journal-title":"Mod Pathol"},{"issue":"2","key":"pone.0345014.ref011","first-page":"17","article-title":"Application of laser scanning confocal microscopy in the soft tissue exquisite structure for 3D scan","volume":"8","author":"Z Zhang","year":"2018","journal-title":"Int J Burns Trauma"},{"issue":"4","key":"pone.0345014.ref012","doi-asserted-by":"crossref","first-page":"52","DOI":"10.21037\/cco-23-150","article-title":"Current applications of ex-vivo fluorescent confocal microscope in urological practice: a systematic review of literature","volume":"13","author":"A Eissa","year":"2024","journal-title":"Chin Clin Oncol"},{"key":"pone.0345014.ref013","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/S0022-1759(99)00116-7","article-title":"A novel cell permeant and far red-fluorescing DNA probe, DRAQ5, for blood cell discrimination by flow cytometry","volume":"229","author":"PJ Smith","year":"1999","journal-title":"J Immunol Methods"},{"issue":"4","key":"pone.0345014.ref014","doi-asserted-by":"crossref","DOI":"10.1002\/jbio.202000207","article-title":"Exploring the utility of Deep Red Anthraquinone 5 for digital staining of ex vivo confocal micrographs of optically sectioned skin","volume":"14","author":"VK Ortner","year":"2021","journal-title":"J Biophotonics"},{"key":"pone.0345014.ref015","volume-title":"Bancroft\u2019s theory and practice of histological techniques E-Book","author":"KS Suvarna","year":"2018"},{"issue":"2","key":"pone.0345014.ref016","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.anndiagpath.2009.12.005","article-title":"Productivity standards for histology laboratories","volume":"14","author":"RJ Buesa","year":"2010","journal-title":"Ann Diagn Pathol"},{"issue":"12","key":"pone.0345014.ref017","doi-asserted-by":"crossref","first-page":"1370","DOI":"10.3390\/e22121370","article-title":"Multistage segmentation of prostate cancer tissues using sample entropy texture analysis","volume":"22","author":"T Ali","year":"2020","journal-title":"Entropy (Basel)"},{"key":"pone.0345014.ref018","unstructured":"Bulten W, Pinckaers H, van Boven H, Vink R, de Bel T, van Ginneken B. Automated gleason grading of prostate biopsies using deep learning. 2019. https:\/\/arxiv.org\/abs\/1907.07980"},{"issue":"4","key":"pone.0345014.ref019","doi-asserted-by":"crossref","first-page":"356","DOI":"10.3390\/e21040356","article-title":"First-stage prostate cancer identification on histopathological images: hand-driven versus automatic learning","volume":"21","author":"G Garc\u00eda","year":"2019","journal-title":"Entropy (Basel)"},{"issue":"4","key":"pone.0345014.ref020","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1109\/TMI.2018.2875868","article-title":"Path R-CNN for Prostate Cancer Diagnosis and Gleason Grading of Histological Images","volume":"38","author":"W Li","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"issue":"3","key":"pone.0345014.ref021","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1038\/s41379-020-0640-y","article-title":"Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists","volume":"34","author":"W Bulten","year":"2021","journal-title":"Mod Pathol"},{"key":"pone.0345014.ref022","doi-asserted-by":"crossref","first-page":"100378","DOI":"10.1016\/j.jpi.2024.100378","article-title":"Validation and three years of clinical experience in using an artificial intelligence algorithm as a second read system for prostate cancer diagnosis-real-world experience","volume":"15","author":"JC Santa-Rosario","year":"2024","journal-title":"J Pathol Inform"},{"key":"pone.0345014.ref023","doi-asserted-by":"crossref","DOI":"10.5334\/ojb.46","article-title":"The Wales Cancer Bank (WCB)","volume":"5","author":"A Parry-Jones","year":"2018","journal-title":"Open Journal of Bioresources"},{"issue":"1","key":"pone.0345014.ref024","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1038\/s41598-018-37257-4","article-title":"Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard","volume":"9","author":"W Bulten","year":"2019","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0345014.ref025","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","article-title":"Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge","volume":"28","author":"W Bulten","year":"2022","journal-title":"Nat Med"},{"issue":"7","key":"pone.0345014.ref026","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1038\/nmeth.2019","article-title":"Fiji: an open-source platform for biological-image analysis","volume":"9","author":"J Schindelin","year":"2012","journal-title":"Nat Methods"},{"key":"pone.0345014.ref027","volume-title":"Python reference manual","author":"G Van Rossum","year":"1995"},{"key":"pone.0345014.ref028","unstructured":"Inc A. Anaconda software distribution. Anaconda Documentation. 2020."},{"key":"pone.0345014.ref029","first-page":"87","article-title":"Jupyter Notebooks\u2013a publishing format for reproducible computational workflows","volume-title":"Positioning and power in academic publishing: Players, agents and agendas","author":"T Kluyver","year":"2016"},{"key":"pone.0345014.ref030","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: large-scale machine learning on heterogeneous systems. 2015."},{"key":"pone.0345014.ref031","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. 2015. p. 234\u201341.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"8","key":"pone.0345014.ref032","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.1109\/TMI.2016.2529665","article-title":"Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images","volume":"35","author":"A Vahadane","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0345014.ref033","unstructured":"McKerns MM, Strand L, Sullivan T, Fang A, Aivazis MA. Building a framework for predictive science. 2012. https:\/\/arxiv.org\/abs\/1202.1056"},{"key":"pone.0345014.ref034","unstructured":"McKerns M, Aivazis M. Pathos: a framework for heterogeneous computing. 2010. https:\/\/uqfoundation.github.io\/project\/pathos"},{"key":"pone.0345014.ref035","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.453","article-title":"scikit-image: image processing in Python","volume":"2","author":"S van der Walt","year":"2014","journal-title":"PeerJ"},{"key":"pone.0345014.ref036","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In: 2015 IEEE International Conference on Computer Vision (ICCV). 2015. p. 1026\u201334. https:\/\/doi.org\/10.1109\/iccv.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"pone.0345014.ref037","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"N Otsu","year":"1975","journal-title":"Automatica"},{"key":"pone.0345014.ref038","article-title":"The OpenCV Library","author":"G Bradski","year":"2000","journal-title":"Dr Dobb\u2019s Journal of Software Tools"},{"key":"pone.0345014.ref039","unstructured":"Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, 2010. p. 249\u201356."},{"key":"pone.0345014.ref040","unstructured":"Gavrikov P, Patapati S. visualkeras. 2020. https:\/\/github.com\/paulgavrikov\/visualkeras"},{"key":"pone.0345014.ref041","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 770\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0345014.ref042","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, 2009. 248\u201355.","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"7825","key":"pone.0345014.ref043","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"issue":"5","key":"pone.0345014.ref044","doi-asserted-by":"crossref","first-page":"545","DOI":"10.23736\/S2724-6051.23.05538-6","article-title":"Artificial intelligence evaluation of confocal microscope prostate images: our preliminary experience","volume":"75","author":"G Bianchi","year":"2023","journal-title":"Minerva Urol Nephrol"},{"issue":"21","key":"pone.0345014.ref045","doi-asserted-by":"crossref","first-page":"5378","DOI":"10.3390\/cancers13215378","article-title":"Significant Inter- and Intralaboratory Variation in Gleason Grading of Prostate Cancer: A Nationwide Study of 35,258 Patients in The Netherlands","volume":"13","author":"RN Flach","year":"2021","journal-title":"Cancers (Basel)"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:03:36Z","timestamp":1774555416000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345014"}},"subtitle":[],"editor":[{"given":"Xiaohui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0345014","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,26]]}}}