{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T22:54:06Z","timestamp":1794005646831,"version":"4.8.0"},"reference-count":37,"publisher":"Cambridge University Press (CUP)","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"unspecified","delay-in-days":198,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100013342","name":"NIHR Imperial Biomedical Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013342","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biol. Imaging"],"published-print":{"date-parts":[[2023]]},"abstract":"<jats:title>Abstract<\/jats:title>\n\t  <jats:p>Non-alcoholic fatty liver disease (NAFLD) is now the leading cause of chronic liver disease, affecting approximately 30% of people worldwide. Histopathology reading of fibrosis patterns is crucial to diagnosing NAFLD. In particular, separating mild from severe stages corresponds to a critical transition as it correlates with clinical outcomes. Deep Learning for digitized histopathology whole-slide images (WSIs) can reduce high inter- and intra-rater variability. We demonstrate a novel solution to score fibrosis severity on a retrospective cohort of 152 Sirius-Red WSIs, with fibrosis stage annotated at slide level by an expert pathologist. We exploit multiple instance learning and multiple-inferences to address the sparsity of pathological signs. We achieved an accuracy of <jats:inline-formula>\n\t      <jats:alternatives>\n\t\t<jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S2633903X23000144_inline1.png\"\/>\n\t\t<jats:tex-math>$ 78.98\\pm 5.86\\% $<\/jats:tex-math>\n\t      <\/jats:alternatives>\n\t    <\/jats:inline-formula>, an F1 score of <jats:inline-formula>\n\t      <jats:alternatives>\n\t\t<jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S2633903X23000144_inline2.png\"\/>\n\t\t<jats:tex-math>$ 77.99\\pm 5.64\\%, $<\/jats:tex-math>\n\t      <\/jats:alternatives>\n\t    <\/jats:inline-formula> and an AUC of <jats:inline-formula>\n\t      <jats:alternatives>\n\t\t<jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S2633903X23000144_inline3.png\"\/>\n\t\t<jats:tex-math>$ 0.87\\pm 0.06 $<\/jats:tex-math>\n\t      <\/jats:alternatives>\n\t    <\/jats:inline-formula>. These results set new state-of-the-art benchmarks for this application.<\/jats:p>","DOI":"10.1017\/s2633903x23000144","type":"journal-article","created":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T13:59:26Z","timestamp":1689688766000},"source":"Crossref","is-referenced-by-count":9,"title":["Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning"],"prefix":"10.1017","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9949-0024","authenticated-orcid":false,"given":"Sneha N.","family":"Naik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4746-7065","authenticated-orcid":false,"given":"Roberta","family":"Forlano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinelopi","family":"Manousou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Goldin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elsa D.","family":"Angelini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"S2633903X23000144_r15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_57"},{"key":"S2633903X23000144_r29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2020.06.025"},{"key":"S2633903X23000144_r20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP49548.2020.9163489"},{"key":"S2633903X23000144_r14","unstructured":"14. Li, J , Li, W , Gertych, A , Knudsen, BS , Speier, W & Arnold, CW (2019) An attention-based multi-resolution model for prostate whole slide imageclassification and localization. Preprint, arXiv:1905.13208."},{"key":"S2633903X23000144_r33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhepr.2022.100443"},{"key":"S2633903X23000144_r13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0508-1"},{"key":"S2633903X23000144_r28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2019.12.025"},{"key":"S2633903X23000144_r12","unstructured":"12. Ilse, M , Tomczak, J & Welling, M (2018) Attention-based deep multiple instance learning. In Proceedings of the 35th International Conference on Machine Learning, PMLR 80, pp. 2127\u20132136."},{"key":"S2633903X23000144_r17","unstructured":"17. Xie, C , Muhammad, H , Vanderbilt, CM , et al. (2020) Beyond classification: whole slide tissue histopathology analysis by end-to-end part learning. In Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121, pp. 843\u2013856."},{"key":"S2633903X23000144_r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106153"},{"key":"S2633903X23000144_r24","first-page":"291","article-title":"Quantification of histochemical staining by color deconvolution","volume":"23","author":"Ruifrok","year":"2001","journal-title":"Anal Quant Cytol Histol"},{"key":"S2633903X23000144_r8","doi-asserted-by":"publisher","DOI":"10.1172\/JCI24282"},{"key":"S2633903X23000144_r2","doi-asserted-by":"publisher","DOI":"10.1002\/hep.28431"},{"key":"S2633903X23000144_r16","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"S2633903X23000144_r23","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"S2633903X23000144_r6","doi-asserted-by":"publisher","DOI":"10.1002\/hep.20701"},{"key":"S2633903X23000144_r34","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0582-9"},{"key":"S2633903X23000144_r37","doi-asserted-by":"publisher","DOI":"10.1007\/s11154-021-09681-x"},{"key":"S2633903X23000144_r32","doi-asserted-by":"publisher","DOI":"10.1016\/j.anndiagpath.2020.151518"},{"key":"S2633903X23000144_r7","doi-asserted-by":"publisher","DOI":"10.1080\/17474124.2018.1415756"},{"key":"S2633903X23000144_r9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107034"},{"key":"S2633903X23000144_r5","doi-asserted-by":"publisher","DOI":"10.1111\/j.1572-0241.1999.01377.x"},{"key":"S2633903X23000144_r31","doi-asserted-by":"publisher","DOI":"10.1002\/hep.31750"},{"key":"S2633903X23000144_r22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102885"},{"key":"S2633903X23000144_r4","doi-asserted-by":"publisher","DOI":"10.1136\/flgastro-2018-101139"},{"key":"S2633903X23000144_r26","unstructured":"26. Cho, H , Lim, S , Choi, G & Min, H (2017) Neural stain-style transfer learning using GAN for histopathological images. arXiv:1710.08543."},{"key":"S2633903X23000144_r18","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585"},{"key":"S2633903X23000144_r11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993788"},{"key":"S2633903X23000144_r25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2016.05.003"},{"key":"S2633903X23000144_r10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101813"},{"key":"S2633903X23000144_r1","doi-asserted-by":"publisher","DOI":"10.1186\/s13098-020-00570-y"},{"key":"S2633903X23000144_r27","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.2983206"},{"key":"S2633903X23000144_r35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"S2633903X23000144_r19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93000-8_106"},{"key":"S2633903X23000144_r30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2022.05.027"},{"key":"S2633903X23000144_r36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-99400-y"},{"key":"S2633903X23000144_r3","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-022-00711-5"}],"container-title":["Biological Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S2633903X23000144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T08:37:46Z","timestamp":1692261466000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S2633903X23000144\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":37,"alternative-id":["S2633903X23000144"],"URL":"https:\/\/doi.org\/10.1017\/s2633903x23000144","relation":{},"ISSN":["2633-903X"],"issn-type":[{"value":"2633-903X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"article-number":"e17"}}