{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T04:22:27Z","timestamp":1747196547095,"version":"3.40.5"},"reference-count":60,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T00:00:00Z","timestamp":1722384000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Smoke exposure is associated with bladder cancer (BC). However, little is known about whether the histologic changes of BC can predict the status of smoke exposure. Given this knowledge gap, the current study investigated the potential association between histology images and smoke exposure status. A total of 483 whole-slide histology images of 285 unique cases of BC were available from multiple centers for BC diagnosis. A deep learning model was developed to predict the smoke exposure status and externally validated on BC cases. The development set consisted of 66 cases from two centers. The external validation consisted of 94 cases from remaining centers for patients who either never smoked cigarettes or were active smokers at the time of diagnosis. The threshold for binary categorization was fixed to the median confidence score (65) of the development set. On external validation, AUC was used to assess the randomness of predicted smoke status; we utilized latent feature presentation to determine common histologic patterns for smoke exposure status and mixed effect logistic regression models determined the parameter independence from BC grade, gender, time to diagnosis, and age at diagnosis. We used 2,000-times bootstrap resampling to estimate the 95% Confidence Interval (CI) on the external validation set. The results showed an AUC of 0.67 (95% CI: 0.58\u20130.76), indicating non-randomness of model classification, with a specificity of 51.2% and sensitivity of 82.2%. Multivariate analyses revealed that our model provided an independent predictor for smoke exposure status derived from histology images, with an odds ratio of 1.710 (95% CI: 1.148\u20132.54). Common histologic patterns of BC were found in active or never smokers. In conclusion, deep learning reveals histopathologic features of BC that are predictive of smoke exposure and, therefore, may provide valuable information regarding smoke exposure status.<\/jats:p>","DOI":"10.1371\/journal.pone.0305135","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T19:51:42Z","timestamp":1722455502000},"page":"e0305135","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning identifies histopathologic changes in bladder cancers associated with smoke exposure status"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0861-3138","authenticated-orcid":true,"given":"Okyaz","family":"Eminaga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hubert","family":"Lau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene","family":"Shkolyar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eva","family":"Wardelmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1025-9089","authenticated-orcid":true,"given":"Mahmoud","family":"Abbas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"issue":"1","key":"pone.0305135.ref001","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3322\/caac.21654","article-title":"Cancer Statistics, 2021.","volume":"71","author":"RL Siegel","year":"2021","journal-title":"CA Cancer J Clin."},{"issue":"7","key":"pone.0305135.ref002","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1001\/jama.2011.1142","article-title":"Association between smoking and risk of bladder cancer among men and women","volume":"306","author":"ND Freedman","year":"2011","journal-title":"JAMA"},{"issue":"10292","key":"pone.0305135.ref003","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1016\/S0140-6736(21)01169-7","article-title":"Spatial, temporal, and demographic patterns in prevalence of smoking tobacco use and attributable disease burden in 204 countries and territories, 1990\u20132019: a systematic analysis from the Global Burden of Disease Study 2019.","volume":"397","author":"Collaborators GBDT.","year":"2021","journal-title":"Lancet"},{"issue":"3","key":"pone.0305135.ref004","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1023\/A:1018453104303","article-title":"Aromatic amines and cancer","volume":"8","author":"P Vineis","year":"1997","journal-title":"Cancer Causes Control"},{"issue":"2","key":"pone.0305135.ref005","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1016\/S0022-5347(01)62973-2","article-title":"Alterations of the p53 gene in occupational bladder cancer in workers exposed to aromatic amines","volume":"160","author":"MJ Droller","year":"1998","journal-title":"J Urol"},{"issue":"5","key":"pone.0305135.ref006","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1002\/1097-0142(19890901)64:5<983::AID-CNCR2820640502>3.0.CO;2-9","article-title":"Histologic changes in the urinary bladder in relation to cigarette smoking and use of artificial sweeteners","volume":"64","author":"O Auerbach","year":"1989","journal-title":"Cancer"},{"issue":"1","key":"pone.0305135.ref007","first-page":"303","article-title":"Pathology as related to tryptophan metabolite excretion, occupational history, and smoking habits in patients with bladder cancer","volume":"43","author":"GH Friedell","year":"1969","journal-title":"J Natl Cancer Inst"},{"issue":"3","key":"pone.0305135.ref008","doi-asserted-by":"crossref","first-page":"e0194039","DOI":"10.1371\/journal.pone.0194039","article-title":"Smoking intensity and bladder cancer aggressiveness at diagnosis","volume":"13","author":"ALA Barbosa","year":"2018","journal-title":"PLoS One"},{"issue":"5","key":"pone.0305135.ref009","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1016\/j.urology.2015.05.040","article-title":"Heavy Cigarette Smoking and Aggressive Bladder Cancer at Initial Presentation","volume":"86","author":"EJ Pietzak","year":"2015","journal-title":"Urology"},{"issue":"4","key":"pone.0305135.ref010","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1002\/ijc.26068","article-title":"Cigarette smoking and subtypes of bladder cancer","volume":"130","author":"X Jiang","year":"2012","journal-title":"Int J Cancer"},{"issue":"2","key":"pone.0305135.ref011","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.urolonc.2014.06.002","article-title":"The effect of smoking and timing of smoking cessation on clinical outcome in non-muscle-invasive bladder cancer","volume":"33","author":"AJ Grotenhuis","year":"2015","journal-title":"Urol Oncol"},{"key":"pone.0305135.ref012","article-title":"editors. Inception-v4, inception-resnet and the impact of residual connections on learning","author":"C Szegedy","year":"2017","journal-title":"Thirty-first AAAI conference on artificial intelligence"},{"issue":"7553","key":"pone.0305135.ref013","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning.","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"issue":"1","key":"pone.0305135.ref014","doi-asserted-by":"crossref","first-page":"e1002730","DOI":"10.1371\/journal.pmed.1002730","article-title":"Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study","volume":"16","author":"JN Kather","year":"2019","journal-title":"PLoS Med"},{"issue":"1","key":"pone.0305135.ref015","doi-asserted-by":"crossref","first-page":"3395","DOI":"10.1038\/s41598-018-21758-3","article-title":"Deep learning based tissue analysis predicts outcome in colorectal cancer","volume":"8","author":"D Bychkov","year":"2018","journal-title":"Sci Rep"},{"key":"pone.0305135.ref016","doi-asserted-by":"crossref","first-page":"101820","DOI":"10.1016\/j.compmedimag.2020.101820","article-title":"Deep learning powers cancer diagnosis in digital pathology","volume":"88","author":"Y He","year":"2021","journal-title":"Comput Med Imaging Graph"},{"issue":"11","key":"pone.0305135.ref017","doi-asserted-by":"crossref","first-page":"3367","DOI":"10.1016\/j.celrep.2019.11.017","article-title":"A Deep Learning Framework for Predicting Response to Therapy in Cancer.","volume":"29","author":"T Sakellaropoulos","year":"2019","journal-title":"Cell Rep"},{"issue":"5","key":"pone.0305135.ref018","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.ccell.2020.09.014","article-title":"Predicting drug response and synergy using a deep learning model of human cancer cells","volume":"38","author":"BM Kuenzi","year":"2020","journal-title":"Cancer cell"},{"issue":"6 Suppl","key":"pone.0305135.ref019","doi-asserted-by":"crossref","first-page":"329S","DOI":"10.1016\/S0197-2456(00)00100-8","article-title":"Design and evolution of the data management systems in the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial.","volume":"21","author":"MA Hasson","year":"2000","journal-title":"Control Clin Trials."},{"issue":"6 Suppl","key":"pone.0305135.ref020","doi-asserted-by":"crossref","first-page":"273S","DOI":"10.1016\/S0197-2456(00)00098-2","article-title":"Design of the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial.","volume":"21","author":"PC Prorok","year":"2000","journal-title":"Control Clin Trials."},{"article-title":"Learning OpenCV: Computer vision with the OpenCV library: \" O\u2019Reilly Media, Inc.\";","year":"2008","author":"G Bradski","key":"pone.0305135.ref021"},{"issue":"1","key":"pone.0305135.ref022","first-page":"1997","article-title":"Neural architecture search: A survey","volume":"20","author":"T Elsken","year":"2019","journal-title":"The Journal of Machine Learning Research"},{"key":"pone.0305135.ref023","article-title":"Plexus Convolutional Neural Network (PlexusNet): A novel neural network architecture for histologic image analysis.","author":"O Eminaga","year":"2019","journal-title":"arXiv preprint arXiv:190809067."},{"key":"pone.0305135.ref024","article-title":"Adam: A method for stochastic optimization.","author":"DP Kingma","year":"2014","journal-title":"arXiv preprint arXiv:14126980."},{"key":"pone.0305135.ref025","article-title":"Attention-based deep multiple instance learning","author":"M Ilse","year":"2018","journal-title":"International conference on machine learning"},{"issue":"3","key":"pone.0305135.ref026","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s00259-022-06036-9","article-title":"Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study","volume":"50","author":"L Zhao","year":"2023","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"6","key":"pone.0305135.ref027","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images.","volume":"5","author":"MY Lu","year":"2021","journal-title":"Nat Biomed Eng"},{"issue":"1","key":"pone.0305135.ref028","first-page":"1","article-title":"lmerTest package: tests in linear mixed effects models","volume":"82","author":"A Kuznetsova","year":"2017","journal-title":"Journal of statistical software"},{"issue":"10","key":"pone.0305135.ref029","doi-asserted-by":"crossref","first-page":"e2","DOI":"10.23915\/distill.00002","article-title":"How to use t-SNE effectively.","volume":"1","author":"M Wattenberg","year":"2016","journal-title":"Distill."},{"issue":"1","key":"pone.0305135.ref030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1741-7015-8-17","article-title":"Current sample size conventions: flaws, harms, and alternatives","volume":"8","author":"P. Bacchetti","year":"2010","journal-title":"BMC medicine."},{"issue":"5","key":"pone.0305135.ref031","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1046\/j.1365-2435.2003.00782.x","article-title":"How much power is enough? Against the development of an arbitrary convention for statistical power calculations","volume":"17","author":"J. di Stephano","year":"2003","journal-title":"Functional Ecology"},{"key":"pone.0305135.ref032","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/s10654-016-0149-3","article-title":"Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations","volume":"31","author":"S Greenland","year":"2016","journal-title":"European journal of epidemiology"},{"journal-title":"Design sensitivity: Statistical power for experimental research: sage","year":"1990","author":"MW Lipsey","key":"pone.0305135.ref033"},{"volume-title":"Statistical power analysis: A simple and general model for traditional and modern hypothesis tests:","year":"2014","author":"B Myors","key":"pone.0305135.ref034"},{"journal-title":"Deep learning with Python: Simon and Schuster","year":"2017","author":"F. Chollet","key":"pone.0305135.ref035"},{"issue":"1","key":"pone.0305135.ref036","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1145\/2786984.2786995","article-title":"Scikit-learn: Machine learning without learning the machinery.","volume":"19","author":"G Varoquaux","year":"2015","journal-title":"GetMobile: Mobile Computing and Communications."},{"key":"pone.0305135.ref037","article-title":"Fitting linear mixed-effects models using lme4.","author":"D Bates","year":"2014","journal-title":"arXiv preprint arXiv:14065823."},{"issue":"5","key":"pone.0305135.ref038","doi-asserted-by":"crossref","first-page":"3873","DOI":"10.3892\/ol.2017.5867","article-title":"Biological interaction of cigarette smoking on the association between genetic polymorphisms involved in inflammation and the risk of lung cancer: A case-control study in Japan.","volume":"13","author":"Y Yamamoto","year":"2017","journal-title":"Oncol Lett"},{"issue":"11","key":"pone.0305135.ref039","doi-asserted-by":"crossref","DOI":"10.1093\/jnci\/dju294","article-title":"Cigarette smoking and variations in systemic immune and inflammation markers","volume":"106","author":"MS Shiels","year":"2014","journal-title":"J Natl Cancer Inst"},{"issue":"2","key":"pone.0305135.ref040","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1177\/0022034511421200","article-title":"Cigarette smoking and inflammation: cellular and molecular mechanisms","volume":"91","author":"J Lee","year":"2012","journal-title":"J Dent Res"},{"issue":"1","key":"pone.0305135.ref041","doi-asserted-by":"crossref","first-page":"S11","DOI":"10.1186\/1476-069X-11-S1-S11","article-title":"Bladder cancer, a review of the environmental risk factors.","volume":"11","author":"S Letasiova","year":"2012","journal-title":"Environ Health."},{"issue":"48","key":"pone.0305135.ref042","doi-asserted-by":"crossref","first-page":"7435","DOI":"10.1038\/sj.onc.1205803","article-title":"Tobacco smoke carcinogens, DNA damage and p53 mutations in smoking-associated cancers","volume":"21","author":"GP Pfeifer","year":"2002","journal-title":"Oncogene"},{"issue":"7","key":"pone.0305135.ref043","first-page":"E1560","article-title":"E-cigarette smoke damages DNA and reduces repair activity in mouse lung, heart, and bladder as well as in human lung and bladder cells","volume":"115","author":"H-W Lee","year":"2018","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"5","key":"pone.0305135.ref044","doi-asserted-by":"crossref","first-page":"8791","DOI":"10.18632\/oncotarget.14456","article-title":"Cigarette smoke induced urocystic epithelial mesenchymal transition via MAPK pathways.","volume":"8","author":"D Yu","year":"2017","journal-title":"Oncotarget.PubMed Central PMCID"},{"issue":"1","key":"pone.0305135.ref045","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1186\/s12931-020-01426-9","article-title":"Shp2 positively regulates cigarette smoke-induced epithelial mesenchymal transition by mediating MMP-9 production.","volume":"21","author":"YN Liu","year":"2020","journal-title":"Respir Res."},{"key":"pone.0305135.ref046","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.toxlet.2021.12.014","article-title":"Knockdown of long noncoding RNA MIAT attenuates cigarette smoke-induced airway remodeling by downregulating miR-29c-3p-HIF3A axis","volume":"357","author":"W Gu","year":"2022","journal-title":"Toxicol Lett"},{"issue":"4","key":"pone.0305135.ref047","doi-asserted-by":"crossref","first-page":"eaaw6938","DOI":"10.1126\/sciadv.aaw6938","article-title":"Single-cell morphology encodes metastatic potential.","volume":"6","author":"PH Wu","year":"2020","journal-title":"Sci Adv."},{"issue":"1","key":"pone.0305135.ref048","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.stem.2010.12.012","article-title":"DNA-damage response in tissue-specific and cancer stem cells","volume":"8","author":"C Blanpain","year":"2011","journal-title":"Cell Stem Cell"},{"issue":"10","key":"pone.0305135.ref049","doi-asserted-by":"crossref","first-page":"e1494677","DOI":"10.1080\/2162402X.2018.1494677","article-title":"Smoker and non-smoker lung adenocarcinoma is characterized by distinct tumor immune microenvironments","volume":"7","author":"X Li","year":"2018","journal-title":"Oncoimmunology"},{"issue":"5","key":"pone.0305135.ref050","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/S0302-2838(02)00358-5","article-title":"Keratinising squamous metaplasia of the bladder: natural history and rationalization of management based on review of 54 years experience.","volume":"42","author":"MS Khan","year":"2002","journal-title":"Eur Urol."},{"issue":"3","key":"pone.0305135.ref051","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1159\/000151398","article-title":"Keratinizing squamous metaplasia of the bladder: a review.","volume":"81","author":"I Ahmad","year":"2008","journal-title":"Urol Int"},{"issue":"23","key":"pone.0305135.ref052","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.1056\/NEJM197806082982303","article-title":"The relations between structural changes in small airways and pulmonary-function tests","volume":"298","author":"M Cosio","year":"1978","journal-title":"N Engl J Med"},{"issue":"1","key":"pone.0305135.ref053","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1136\/thx.2005.052191","article-title":"Surveillance for the detection of early lung cancer in patients with bronchial dysplasia","volume":"62","author":"P Jeremy George","year":"2007","journal-title":"Thorax"},{"issue":"1","key":"pone.0305135.ref054","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.urolonc.2012.11.020","article-title":"Squamous cell carcinogenesis and squamous cell carcinoma of the urinary bladder: a contemporary review with focus on nonbilharzial squamous cell carcinoma","volume":"32","author":"S Rausch","year":"2014","journal-title":"Urol Oncol"},{"issue":"13","key":"pone.0305135.ref055","first-page":"3853","article-title":"Epidemiological characteristics of squamous cell carcinoma and adenocarcinoma of the bladder","volume":"48","author":"AF Kantor","year":"1988","journal-title":"Cancer Res"},{"issue":"11","key":"pone.0305135.ref056","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1002\/(SICI)1097-0142(19991201)86:11<2337::AID-CNCR23>3.0.CO;2-6","article-title":"Influence of smoking status on the disease-related outcomes of patients with tobacco-associated superficial transitional cell carcinoma of the bladder","volume":"86","author":"N Fleshner","year":"1999","journal-title":"Cancer"},{"issue":"2","key":"pone.0305135.ref057","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1097\/00001648-199403000-00012","article-title":"Associations between bladder cancer risk factors and tumor stage and grade at diagnosis","volume":"5","author":"SR Sturgeon","year":"1994","journal-title":"Epidemiology"},{"key":"pone.0305135.ref058","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"R Caruana","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"pone.0305135.ref059","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"M Tan","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"pone.0305135.ref060","doi-asserted-by":"crossref","first-page":"e8668","DOI":"10.1136\/bmj.e8668","article-title":"Differential dropout and bias in randomised controlled trials: when it matters and when it may not","volume":"346","author":"ML Bell","year":"2013","journal-title":"BMJ"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0305135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T19:52:20Z","timestamp":1722455540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0305135"}},"subtitle":[],"editor":[{"given":"Yuchen","family":"Qiu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,7,31]]},"references-count":60,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0305135","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2024,7,31]]}}}