{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:20:11Z","timestamp":1788844811635,"version":"build-2803163510"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,7,16]],"date-time":"2020-07-16T00:00:00Z","timestamp":1594857600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,7,16]],"date-time":"2020-07-16T00:00:00Z","timestamp":1594857600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U24CA199374"],"award-info":[{"award-number":["U24CA199374"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01CA220401"],"award-info":[{"award-number":["U01CA220401"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["UL1TR001420"],"award-info":[{"award-number":["UL1TR001420"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013699","name":"Ohio State University Comprehensive Cancer Center \u2013 Arthur G. James Cancer Hospital and Richard J. Solove Research Institute","doi-asserted-by":"publisher","award":["Intramural Research Award Pelotonia"],"award-info":[{"award-number":["Intramural Research Award Pelotonia"]}],"id":[{"id":"10.13039\/100013699","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Diagn Pathol"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Identification of bladder layers is a necessary prerequisite to bladder cancer diagnosis and prognosis. We present a method of multi-class image segmentation, which recognizes urothelium, lamina propria, muscularis propria, and muscularis mucosa layers as well as regions of red blood cells, cauterized tissue, and inflamed tissue from images of hematoxylin and eosin stained slides of bladder biopsies.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>Segmentation is carried out using a U-Net architecture. The number of layers was either, eight, ten, or twelve and combined with a weight initializers of He uniform, He normal, Glorot uniform, and Glorot normal. The most optimal of these parameters was found by through a seven-fold training, validation, and testing of a dataset of 39 whole slide images of T1 bladder biopsies.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The most optimal model was a twelve layer U-net using He normal initializer. Initial visual evaluation by an experienced pathologist on an independent set of 15 slides segmented by our method yielded an average score of 8.93 \u00b1 0.6 out of 10 for segmentation accuracy. It took only 23\u2009min for the pathologist to review 15 slides (1.53\u2009min\/slide) with the computer annotations. To assess the generalizability of the proposed model, we acquired an additional independent set of 53 whole slide images and segmented them using our method. Visual examination by a different experienced pathologist yielded an average score of 8.87 \u00b1 0.63 out of 10 for segmentation accuracy.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Our preliminary findings suggest that predictions of our model can minimize the time needed by pathologists to annotate slides. Moreover, the method has the potential to identify the bladder layers accurately. Further development can assist the pathologist with the diagnosis of T1 bladder cancer.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13000-020-01002-1","type":"journal-article","created":{"date-parts":[[2020,7,16]],"date-time":"2020-07-16T10:03:28Z","timestamp":1594893808000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Semantic segmentation to identify bladder layers from H&amp;E Images"],"prefix":"10.1186","volume":"15","author":[{"given":"Muhammad Khalid Khan","family":"Niazi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enes","family":"Yazgan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas E.","family":"Tavolara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wencheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheryl T.","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anil","family":"Parwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Metin N.","family":"Gurcan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,16]]},"reference":[{"issue":"1","key":"1002_CR1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21590","volume":"70","author":"RL Siegel","year":"2020","unstructured":"Siegel RL, Miller KD, Jemal A. Cancer statistics, 2020. CA Cancer J Clin. 2020;70(1):7\u201330.","journal-title":"CA Cancer J Clin"},{"issue":"6","key":"1002_CR2","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1200\/JCO.2014.57.6967","volume":"33","author":"W Martin-Doyle","year":"2015","unstructured":"Martin-Doyle W, Leow JJ, Orsola A, Chang SL, Bellmunt J. Improving selection criteria for early cystectomy in high-grade t1 bladder cancer: a meta-analysis of 15,215 patients. J Clin Oncol. 2015;33(6):643\u201350.","journal-title":"J Clin Oncol"},{"issue":"2","key":"1002_CR3","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.eururo.2011.10.026","volume":"61","author":"BW van Rhijn","year":"2012","unstructured":"van Rhijn BW, et al. A new and highly prognostic system to discern T1 bladder cancer substage. Eur Urol. 2012;61(2):378\u201384.","journal-title":"Eur Urol"},{"issue":"1","key":"1002_CR4","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.eursup.2010.01.005","volume":"9","author":"PJ Bostrom","year":"2010","unstructured":"Bostrom PJ, et al. Staging and staging errors in bladder cancer. Eur Urol Suppl. 2010;9(1):2\u20139.","journal-title":"Eur Urol Suppl"},{"issue":"7679","key":"1002_CR5","doi-asserted-by":"publisher","first-page":"S34","DOI":"10.1038\/551S34a","volume":"551","author":"C Berdik","year":"2017","unstructured":"Berdik C. Unlocking bladder cancer. Nature. 2017;551(7679):S34\u20135.","journal-title":"Nature"},{"issue":"1","key":"1002_CR6","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.eururo.2008.07.031","volume":"55","author":"A Shabsigh","year":"2009","unstructured":"Shabsigh A, et al. Defining early morbidity of radical cystectomy for patients with bladder cancer using a standardized reporting methodology. Eur Urol. 2009;55(1):164\u201376.","journal-title":"Eur Urol"},{"issue":"9","key":"1002_CR7","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/s11934-016-0625-z","volume":"17","author":"R Veeratterapillay","year":"2016","unstructured":"Veeratterapillay R, Heer R, Johnson MI, Persad R, Bach C. High-Risk Non-Muscle-Invasive Bladder Cancer\u2014Therapy Options During Intravesical BCG Shortage. Curr Urol Rep. 2016;17(9):68.","journal-title":"Curr Urol Rep"},{"issue":"3","key":"1002_CR8","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.eururo.2014.12.007","volume":"67","author":"G Novara","year":"2015","unstructured":"Novara G, et al. Systematic Review and Cumulative Analysis of Perioperative Outcomes and Complications After Robot-assisted Radical Cystectomy. Eur Urol. 2015;67(3):376\u2013401.","journal-title":"Eur Urol"},{"issue":"1","key":"1002_CR9","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.juro.2013.07.062","volume":"191","author":"NE Mohamed","year":"2014","unstructured":"Mohamed NE, et al. Muscle invasive bladder cancer: examining survivor burden and unmet needs. J Urol. 2014;191(1):48\u201353.","journal-title":"J Urol"},{"key":"1002_CR10","doi-asserted-by":"crossref","unstructured":"Niazi MKK, Tavolara T, Arole V, Parwani A, Lee C, Gurcan M. MP58-06 automated staging of t1 bladder cancer using digital pathologic h&e images: a deep learning approach. J Urol. 2018;199{4S):e775.","DOI":"10.1016\/j.juro.2018.02.1838"},{"key":"1002_CR11","doi-asserted-by":"crossref","unstructured":"Niazi MKK, Tavolara TE, Arole V, Parwani AV, Lee C, Gurcan MN. Automated T1 bladder risk stratification based on depth of lamina propria invasion from H and E tissue biopsies: a deep learning approach. In: Medical Imaging 2018: Digital Pathology, vol. 10581. Bellingham: International Society for Optics and Photonics; 2018. p. 105810H..","DOI":"10.1117\/12.2294552"},{"key":"1002_CR12","first-page":"161","volume":"11","author":"J Bellot","year":"1993","unstructured":"Bellot J. Pathologists of the French Association of Urology Cancer Committee: Lamina propria microinvasion of bladder tumors, incidence on stage allocation (pTa vs pT 1): recommended approach. World J Urol. 1993;11:161\u20134.","journal-title":"World J Urol"},{"issue":"4","key":"1002_CR13","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1111\/j.1464-410X.1988.tb04361.x","volume":"62","author":"P Abel","year":"1988","unstructured":"Abel P, Henderson D, Bennett M, Hall R, Williams G. Differing interpretations by pathologists of the pT category and grade of transitional cell cancer of the bladder. Br J Urol. 1988;62(4):339\u201342.","journal-title":"Br J Urol"},{"issue":"1","key":"1002_CR14","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.juro.2008.03.038","volume":"180","author":"T Cai","year":"2008","unstructured":"Cai T, et al. Can early single dose instillation of epirubicin improve bacillus Calmette-Guerin efficacy in patients with nonmuscle invasive high risk bladder cancer? Results from a prospective, randomized, double-blind controlled study. J Urol. 2008;180(1):110\u20135.","journal-title":"J Urol"},{"issue":"1","key":"1002_CR15","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1046\/j.1464-410x.2000.00356.x","volume":"85","author":"I Tosoni","year":"2000","unstructured":"Tosoni I, et al. Clinical significance of interobserver differences in the staging and grading of superficial bladder cancer. BJU Int. 2000;85(1):48\u201353.","journal-title":"BJU Int"},{"issue":"5","key":"1002_CR16","doi-asserted-by":"publisher","first-page":"e253","DOI":"10.1016\/S1470-2045(19)30154-8","volume":"20","author":"MKK Niazi","year":"2019","unstructured":"Niazi MKK, Parwani AV, Gurcan MN. Digital pathology and artificial intelligence. Lancet Oncol. 2019;20(5):e253\u201361.","journal-title":"Lancet Oncol"},{"key":"1002_CR17","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: Springer; 2015. p. 234\u201341.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1002_CR18","first-page":"6980","volume":"1412","author":"DP Kingma","year":"2014","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv. 2014;1412:6980.","journal-title":"arXiv preprint arXiv"},{"key":"1002_CR19","first-page":"05746","volume":"1801","author":"V Iglovikov","year":"2018","unstructured":"Iglovikov V, Shvets A. Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation. arXiv preprint arXiv. 2018;1801:05746.","journal-title":"arXiv preprint arXiv"},{"key":"1002_CR20","unstructured":"Hanin B, Rolnick D. How to start training: The effect of initialization and architecture. Adv Neural Inf Proces Syst. 2018:571\u201381."}],"container-title":["Diagnostic Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13000-020-01002-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13000-020-01002-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13000-020-01002-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T23:07:53Z","timestamp":1626390473000},"score":1,"resource":{"primary":{"URL":"https:\/\/diagnosticpathology.biomedcentral.com\/articles\/10.1186\/s13000-020-01002-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,16]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1002"],"URL":"https:\/\/doi.org\/10.1186\/s13000-020-01002-1","relation":{},"ISSN":["1746-1596"],"issn-type":[{"value":"1746-1596","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,16]]},"assertion":[{"value":"24 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Our datasets of digitized whole slide H&E images of T1 bladder biopsies were collected with the approval by the Ohio State University IRB.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"87"}}