{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T16:28:19Z","timestamp":1794932899266,"version":"4.9.1"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009318","name":"Helmholtz Association","doi-asserted-by":"publisher","award":["Project DIADEM, ZT-1-PF-5 139"],"award-info":[{"award-number":["Project DIADEM, ZT-1-PF-5 139"]}],"id":[{"id":"10.13039\/501100009318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Type 2 diabetes (T2D) is a chronic disease currently affecting around 500 million people worldwide with often severe health consequences. Yet, histopathological analyses are still inadequate to infer the glycaemic state of a person based on morphological alterations linked to impaired insulin secretion and\n                    <jats:italic>\u03b2<\/jats:italic>\n                    -cell failure in T2D. Giga-pixel microscopy can capture subtle morphological changes, but data complexity exceeds human analysis capabilities. In response, we generate a dataset of pancreas whole-slide images from living donors with multiple chromogenic and multiplex immunofluorescence stainings and train deep learning models to predict the T2D status. Using explainable AI, we make the learned relationships interpretable, quantify them as biomarkers, and assess their association with T2D. Remarkably, the highest prediction performance is achieved by simultaneously focusing on islet\n                    <jats:italic>\u03b1<\/jats:italic>\n                    - and\n                    <jats:italic>\u03b4<\/jats:italic>\n                    -cells and neuronal axons, alongside subtle pancreatic alterations in T2D donors such as larger adipocyte clusters, altered islet-adipocyte proximity and smaller islets. This data-driven approach provides a foundation for future research into relevant diagnostic and therapeutic targets, refining several hypotheses regarding tissue alterations associated with T2D.\n                  <\/jats:p>","DOI":"10.1038\/s41467-026-69295-2","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T20:53:52Z","timestamp":1770670432000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Explainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetes"],"prefix":"10.1038","volume":"17","author":[{"given":"Lukas","family":"Klein","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Ziegler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felicia","family":"Gerst","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanni","family":"Morgenroth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karol","family":"Gotkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eyke","family":"Sch\u00f6niger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8462-3832","authenticated-orcid":false,"given":"Martin","family":"Heni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Kipke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Friedland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annika","family":"Seiler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ellen","family":"Geibelt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hajime","family":"Yamazaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans-Ulrich","family":"H\u00e4ring","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvia","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Nadalin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfred","family":"K\u00f6nigsrainer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andre L.","family":"Mihaljevic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Hartmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5496-293X","authenticated-orcid":false,"given":"Falko","family":"Fend","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Aust","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Weitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5544-099X","authenticated-orcid":false,"given":"Reiner","family":"Jumpertz-von Schwartzenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"Distler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klaus","family":"Maier-Hein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1407-9023","authenticated-orcid":false,"given":"Andreas L.","family":"Birkenfeld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susanne","family":"Ullrich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul F.","family":"J\u00e4ger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3519-5886","authenticated-orcid":false,"given":"Fabian","family":"Isensee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3653-8107","authenticated-orcid":false,"given":"Michele","family":"Solimena","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6120-0191","authenticated-orcid":false,"given":"Robert","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"key":"69295_CR1","unstructured":"International Diabetes Federation. IDF Diabetes Atlas Vol. 11th edn. https:\/\/diabetesatlas.org\/resources\/idf-diabetes-atlas-2025\/ (International Diabetes Federation, 2025)."},{"key":"69295_CR2","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1007\/s00125-013-3155-y","volume":"57","author":"L Krogvold","year":"2014","unstructured":"Krogvold, L. et al. Pancreatic biopsy by minimal tail resection in live adult patients at the onset of type 1 diabetes: experiences from the DiViD study. Diabetologia 57, 841\u2013843 (2014).","journal-title":"Diabetologia"},{"key":"69295_CR3","doi-asserted-by":"publisher","first-page":"241","DOI":"10.2337\/diabetes.48.2.241","volume":"48","author":"SE Kahn","year":"1999","unstructured":"Kahn, S. E., Andrikopoulos, S. & Verchere, C. B. Islet amyloid: a long-recognized but underappreciated pathological feature of type 2 diabetes. Diabetes 48, 241\u2013253 (1999).","journal-title":"Diabetes"},{"key":"69295_CR4","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1152\/physrev.00042.2009","volume":"91","author":"P Westermark","year":"2011","unstructured":"Westermark, P., Andersson, A. & Westermark, G. T. Islet amyloid polypeptide, islet amyloid, and Diabetes mellitus. Physiol. Rev. 91, 795\u2013826 (2011).","journal-title":"Physiol. Rev."},{"key":"69295_CR5","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1210\/er.2007-0037","volume":"29","author":"L Haataja","year":"2008","unstructured":"Haataja, L., Gurlo, T., Huang, C. J. & Butler, P. C. Islet amyloid in type 2 diabetes, and the toxic oligomer hypothesis. Endocr. Rev. 29, 303\u2013316 (2008).","journal-title":"Endocr. Rev."},{"key":"69295_CR6","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/S2213-8587(20)30022-X","volume":"8","author":"GC Weir","year":"2020","unstructured":"Weir, G. C., Gaglia, J. & Bonner-Weir, S. Inadequate beta-cell mass is essential for the pathogenesis of type 2 diabetes.  Lancet Diab. Endocrinol. 8, 249\u2013256 (2020).","journal-title":"Lancet Diab. Endocrinol."},{"key":"69295_CR7","doi-asserted-by":"publisher","first-page":"2356","DOI":"10.2337\/db06-1650","volume":"56","author":"JA Ehses","year":"2007","unstructured":"Ehses, J. A. et al. Increased number of islet-associated macrophages in type 2 diabetes. Diabetes 56, 2356\u20132370 (2007).","journal-title":"Diabetes"},{"key":"69295_CR8","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1007\/s00125-009-1410-z","volume":"52","author":"SJ Richardson","year":"2009","unstructured":"Richardson, S. J., Willcox, A., Bone, A. J., Foulis, A. K. & Morgan, N. G. Islet-associated macrophages in type 2 diabetes. Diabetologia 52, 1686\u20131688 (2009).","journal-title":"Diabetologia"},{"key":"69295_CR9","doi-asserted-by":"publisher","first-page":"624","DOI":"10.2337\/diabetes.53.3.624","volume":"53","author":"S Deng","year":"2004","unstructured":"Deng, S. et al. Structural and functional abnormalities in the islets isolated from type 2 diabetic subjects. Diabetes 53, 624\u2013632 (2004).","journal-title":"Diabetes"},{"key":"69295_CR10","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1089\/ars.2007.1610","volume":"9","author":"MR Hayden","year":"2007","unstructured":"Hayden, M. R. & Sowers, J. R. Isletopathy in type 2 Diabetes mellitus: implications of islet RAS, islet fibrosis, islet amyloid, remodeling, and oxidative stress. Antioxid. Redox Signal. 9, 891\u2013910 (2007).","journal-title":"Antioxid. Redox Signal."},{"key":"69295_CR11","doi-asserted-by":"publisher","first-page":"S172","DOI":"10.2337\/diabetes.50.2007.S172","volume":"50","author":"C Sempoux","year":"2001","unstructured":"Sempoux, C., Guiot, Y., Dubois, D., Moulin, P. & Rahier, J. Human type 2 diabetes: morphological evidence for abnormal beta-cell function. Diabetes 50, S172\u2013S172 (2001).","journal-title":"Diabetes"},{"key":"69295_CR12","doi-asserted-by":"publisher","first-page":"107469","DOI":"10.1016\/j.celrep.2020.03.033","volume":"31","author":"CM Cohrs","year":"2020","unstructured":"Cohrs, C. M. et al. Dysfunction of persisting beta cells is a key feature of early type 2 diabetes pathogenesis. Cell Rep. 31, 107469 (2020).","journal-title":"Cell Rep."},{"key":"69295_CR13","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/S2213-8587(20)30119-4","volume":"8","author":"RR Holman","year":"2020","unstructured":"Holman, R. R., Clark, A. & Rorsman, P. Beta-cell secretory dysfunction: a key cause of type 2 diabetes.  Lancet Diab. Endocrinol. 8, 370 (2020).","journal-title":"Lancet Diab. Endocrinol."},{"key":"69295_CR14","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","volume":"28","author":"W Bulten","year":"2022","unstructured":"Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28, 154\u2013163 (2022).","journal-title":"Nat. Med."},{"key":"69295_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-44188-w","volume":"15","author":"M Shaban","year":"2024","unstructured":"Shaban, M. et al. MAPS: pathologist-level cell type annotation from tissue images through machine learning. Nat. Commun. 15, 28 (2024).","journal-title":"Nat. Commun."},{"key":"69295_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-40219-0","volume":"13","author":"MM Rahaman","year":"2023","unstructured":"Rahaman, M. M., Millar, E. K. A. & Meijering, E. Breast cancer histopathology image-based gene expression prediction using spatial transcriptomics data and deep learning. Sci. Rep. 13, 13604 (2023).","journal-title":"Sci. Rep."},{"key":"69295_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41523-023-00518-1","volume":"9","author":"D Mandair","year":"2023","unstructured":"Mandair, D., Reis-Filho, J. S. & Ashworth, A. Biological insights and novel biomarker discovery through deep learning approaches in breast cancer histopathology. npj Breast Cancer 9, 1\u201311 (2023).","journal-title":"npj Breast Cancer"},{"key":"69295_CR18","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/j.molmet.2019.06.006","volume":"27","author":"M Barovic","year":"2019","unstructured":"Barovic, M. et al. Metabolically phenotyped pancreatectomized patients as living donors for the study of islets in health and diabetes. Mol. Metab. 27, S1\u2013S6 (2019).","journal-title":"Mol. Metab."},{"key":"69295_CR19","doi-asserted-by":"publisher","first-page":"2240","DOI":"10.1007\/s00125-017-4385-1","volume":"60","author":"F Gerst","year":"2017","unstructured":"Gerst, F. et al. Metabolic crosstalk between fatty pancreas and fatty liver: effects on local inflammation and insulin secretion. Diabetologia 60, 2240\u20132251 (2017).","journal-title":"Diabetologia"},{"key":"69295_CR20","doi-asserted-by":"publisher","first-page":"4373","DOI":"10.1210\/jc.2018-00791","volume":"103","author":"F Gerst","year":"2018","unstructured":"Gerst, F. et al. The expression of aldolase B in islets is negatively associated with insulin secretion in humans.  J. Clin. Endocrinol. Metab. 103, 4373\u20134383 (2018).","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"69295_CR21","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1038\/s42255-022-00607-8","volume":"4","author":"AL Gloyn","year":"2022","unstructured":"Gloyn, A. L. et al. Every islet matters: improving the impact of human islet research. Nat. Metab. 4, 970\u2013977 (2022).","journal-title":"Nat. Metab."},{"key":"69295_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.molmet.2019.05.001","volume":"25","author":"F Gerst","year":"2019","unstructured":"Gerst, F. et al. What role do fat cells play in pancreatic tissue? Mol. Metab. 25, 1\u201310 (2019).","journal-title":"Mol. Metab."},{"key":"69295_CR23","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T. G., Lathrop, R. H. & Lozano-P\u00e9rez, T. Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89, 31\u201371 (1997).","journal-title":"Artif. Intell."},{"key":"69295_CR24","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A. & Zelnik, L. ImageNet-21K pretraining for the masses. In Proc. Neural Information Processing Systems Track on Datasets and Benchmarks, Vol 1, https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/hash\/98f13708210194c475687be6106a3b84-Abstract-round1.html (2021)."},{"key":"69295_CR25","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555\u2013570 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"69295_CR26","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S. & Wolf, L. Transformer Interpretability Beyond Attention Visualization. In Proc. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 782\u2013791 (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"69295_CR27","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1038\/s42256-021-00343-w","volume":"3","author":"G Erion","year":"2021","unstructured":"Erion, G., Janizek, J. D., Sturmfels, P., Lundberg, S. M. & Lee, S.-I. Improving performance of deep learning models with axiomatic attribution priors and expected gradients. Nat. Mach. Intell. 3, 620\u2013631 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"69295_CR28","doi-asserted-by":"publisher","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C.\"Why Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201916, 1135\u20131144, https:\/\/doi.org\/10.1145\/2939672.2939778 (Association for Computing Machinery, 2016).","DOI":"10.1145\/2939672.2939778"},{"key":"69295_CR29","unstructured":"Sundararajan, M., Taly, A. & Yan, Q.Axiomatic Attribution for Deep Networks. In Proc. 34th International Conference on Machine Learning - Volume 70, ICML\u201917, 3319\u20133328 (JMLR.org, 2017)."},{"key":"69295_CR30","unstructured":"Vaswani, A. et al. Attention is all you need. Advances in neural information processing systems 30, (2017)."},{"key":"69295_CR31","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1016\/j.cmet.2016.08.018","volume":"24","author":"Y Xin","year":"2016","unstructured":"Xin, Y. et al. RNA sequencing of single human islet cells reveals type 2 diabetes genes. Cell Metab. 24, 608\u2013615 (2016).","journal-title":"Cell Metab."},{"key":"69295_CR32","doi-asserted-by":"publisher","first-page":"eaaz9124","DOI":"10.1126\/sciadv.aaz9124","volume":"6","author":"A Alvarsson","year":"2020","unstructured":"Alvarsson, A. et al. A 3D atlas of the dynamic and regional variation of pancreatic innervation in diabetes. Sci. Adv. 6, eaaz9124 (2020).","journal-title":"Sci. Adv."},{"key":"69295_CR33","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1007\/s00125-022-05691-9","volume":"65","author":"RF Hampton","year":"2022","unstructured":"Hampton, R. F., Jimenez-Gonzalez, M. & Stanley, S. A. Unravelling innervation of pancreatic islets. Diabetologia 65, 1069\u20131084 (2022).","journal-title":"Diabetologia"},{"key":"69295_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53348-5","volume":"15","author":"A M\u00fcller","year":"2024","unstructured":"M\u00fcller, A. et al. Structure, interaction and nervous connectivity of beta cell primary cilia. Nat. Commun. 15, 9168 (2024).","journal-title":"Nat. Commun."},{"key":"69295_CR35","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s00125-024-06104-9","volume":"67","author":"M Heni","year":"2024","unstructured":"Heni, M. The insulin resistant brain: impact on whole-body metabolism and body fat distribution. Diabetologia 67, 1181\u20131191 (2024).","journal-title":"Diabetologia"},{"key":"69295_CR36","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1038\/s44318-025-00383-7","volume":"44","author":"CI Nilsson","year":"2025","unstructured":"Nilsson, C. I. et al. Somatostatin triggers local cAMP and Ca2+ signaling in primary cilia to modulate pancreatic beta-cell function.  EMBO J. 44, 1663\u20131691 (2025).","journal-title":"EMBO J."},{"key":"69295_CR37","doi-asserted-by":"publisher","first-page":"3027\u20133036.e3","DOI":"10.1016\/j.celrep.2019.02.056","volume":"26","author":"O Kluth","year":"2019","unstructured":"Kluth, O. et al. Decreased expression of cilia genes in pancreatic islets as a risk factor for type 2 diabetes in mice and humans. Cell Rep. 26, 3027\u20133036.e3 (2019).","journal-title":"Cell Rep."},{"key":"69295_CR38","doi-asserted-by":"publisher","first-page":"154414","DOI":"10.1016\/j.metabol.2020.154414","volume":"114","author":"F Cinti","year":"2021","unstructured":"Cinti, F. et al. Noradrenergic fibers are associated with beta-cell dedifferentiation and impaired beta-cell function in humans. Metabolism 114, 154414 (2021).","journal-title":"Metabolism"},{"key":"69295_CR39","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1007\/s00125-017-4409-x","volume":"61","author":"S-C Tang","year":"2018","unstructured":"Tang, S.-C. et al. Human pancreatic neuro-insular network in health and fatty infiltration. Diabetologia 61, 168\u2013181 (2018).","journal-title":"Diabetologia"},{"key":"69295_CR40","doi-asserted-by":"publisher","first-page":"e27445","DOI":"10.1371\/journal.pone.0027445","volume":"6","author":"G Kilimnik","year":"2011","unstructured":"Kilimnik, G. et al. Altered islet composition and disproportionate loss of large islets in patients with Type 2 diabetes. PLoS ONE 6, e27445 (2011).","journal-title":"PLoS ONE"},{"key":"69295_CR41","doi-asserted-by":"publisher","first-page":"267","DOI":"10.4161\/isl.3.5.15939","volume":"3","author":"A Steffen","year":"2011","unstructured":"Steffen, A., Ludwig, B., Krautz, C., Bornstein, S. & Solimena, M. Functional assessment of automatically sorted pancreatic islets using large particle flow cytometry. Islets 3, 267\u2013270 (2011).","journal-title":"Islets"},{"key":"69295_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4161\/isl.3.1.14131","volume":"3","author":"Y Fujita","year":"2011","unstructured":"Fujita, Y. et al. Large human islets secrete less insulin per islet equivalent than smaller islets in vitro. Islets 3, 1\u20135 (2011).","journal-title":"Islets"},{"key":"69295_CR43","doi-asserted-by":"publisher","first-page":"87","DOI":"10.4161\/isl.24780","volume":"5","author":"B Farhat","year":"2013","unstructured":"Farhat, B. et al. Small human islets comprised of more beta-cells with higher insulin content than large islets. Islets 5, 87\u201394 (2013).","journal-title":"Islets"},{"key":"69295_CR44","doi-asserted-by":"crossref","unstructured":"Dong, X. et al. Associations of intrapancreatic fat deposition with incident diseases of the exocrine and endocrine pancreas: A UK biobank prospective cohort study. Off. J. Am. Coll. Gastroenterol. 119, https:\/\/journals.lww.com\/ajg\/fulltext\/2024\/06000\/associations_of_intrapancreatic_fat_deposition.29.aspx (2024).","DOI":"10.14309\/ajg.0000000000002792"},{"key":"69295_CR45","doi-asserted-by":"publisher","first-page":"3518","DOI":"10.1210\/clinem\/dgaa435","volume":"105","author":"R Wagner","year":"2020","unstructured":"Wagner, R. et al. Pancreatic steatosis associates with impaired insulin secretion in genetically predisposed individuals.  J. Clin. Endocrinol. Metab. 105, 3518\u20133525 (2020).","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"69295_CR46","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.2337\/db23-0009","volume":"73","author":"JJ Wright","year":"2023","unstructured":"Wright, J. J. et al. Exocrine pancreas in type 1 and type 2 diabetes: different patterns of fibrosis, metaplasia, angiopathy, and adiposity. Diabetes 73, 1140\u20131152 (2023).","journal-title":"Diabetes"},{"key":"69295_CR47","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1007\/s00125-025-06392-9","volume":"68","author":"N Zhang","year":"2025","unstructured":"Zhang, N. et al. Intrapancreatic adipocytes and beta cell dedifferentiation in human type 2 diabetes. Diabetologia 68, 1242\u20131260 (2025).","journal-title":"Diabetologia"},{"key":"69295_CR48","doi-asserted-by":"publisher","first-page":"102067","DOI":"10.1016\/j.molmet.2024.102067","volume":"91","author":"E Lorza-Gil","year":"2025","unstructured":"Lorza-Gil, E. et al. Incretin-responsive human pancreatic adipose tissue organoids: a functional model for fatty pancreas research. Mol. Metab. 91, 102067 (2025).","journal-title":"Mol. Metab."},{"key":"69295_CR49","doi-asserted-by":"publisher","first-page":"e146999","DOI":"10.1172\/jci.insight.146999","volume":"6","author":"B Dietz","year":"2021","unstructured":"Dietz, B. et al. Detection of diabetes from whole-body MRI using deep learning. JCI Insight 6, e146999 (2021).","journal-title":"JCI Insight"},{"key":"69295_CR50","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1002\/dmrr.1073","volume":"26","author":"M Heni","year":"2010","unstructured":"Heni, M. et al. Pancreatic fat is negatively associated with insulin secretion in individuals with impaired fasting glucose and\/or impaired glucose tolerance: a nuclear magnetic resonance study. Diab. Metab. Res. Rev. 26, 200\u2013205 (2010).","journal-title":"Diab. Metab. Res. Rev."},{"key":"69295_CR51","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1007\/s00535-020-01683-x","volume":"55","author":"H Yamazaki","year":"2020","unstructured":"Yamazaki, H. et al. Longitudinal association of fatty pancreas with the incidence of type-2 diabetes in lean individuals: a 6-year computed tomography-based cohort study. J. Gastroenterol. 55, 712\u2013721 (2020).","journal-title":"J. Gastroenterol."},{"key":"69295_CR52","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25221-2","volume":"12","author":"K de Haan","year":"2021","unstructured":"de Haan, K. et al. Deep learning-based transformation of H&E stained tissues into special stains. Nat. Commun. 12, 4884 (2021).","journal-title":"Nat. Commun."},{"key":"69295_CR53","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1111\/dom.13520","volume":"21","author":"M Shimizu","year":"2019","unstructured":"Shimizu, M. et al. Evaluation of the effects of dapagliflozin, a sodium-glucose co-transporter-2 inhibitor, on hepatic steatosis and fibrosis using transient elastography in patients with type 2 diabetes and non-alcoholic fatty liver disease. Diab. Obes. Metab. 21, 285\u2013292 (2019).","journal-title":"Diab. Obes. Metab."},{"key":"69295_CR54","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1038\/s42255-021-00420-9","volume":"3","author":"L Wigger","year":"2021","unstructured":"Wigger, L. et al. Multi-omics profiling of living human pancreatic islet donors reveals heterogeneous beta cell trajectories towards type 2 diabetes. Nat. Metab. 3, 1017\u20131031 (2021).","journal-title":"Nat. Metab."},{"key":"69295_CR55","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1161\/01.CIR.96.1.69","volume":"96","author":"G Davi","year":"1997","unstructured":"Davi, G. et al. Diabetes mellitus, hypercholesterolemia, and hypertension but not vascular disease per Se are associated with persistent platelet activation in vivo. Circulation 96, 69\u201375 (1997).","journal-title":"Circulation"},{"key":"69295_CR56","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1080\/09537100701609019","volume":"18","author":"EC M.D","year":"2007","unstructured":"M.D, E. C., Kucuktag, S. & Basyigit, S. Platelet activation in subjects with impaired glucose tolerance. Platelets 18, 591\u2013594 (2007).","journal-title":"Platelets"},{"key":"69295_CR57","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1038\/s41577-023-00834-4","volume":"23","author":"M Scherlinger","year":"2023","unstructured":"Scherlinger, M., Richez, C., Tsokos, G. C., Boilard, E. & Blanco, P. The role of platelets in immune-mediated inflammatory diseases. Nat. Rev. Immunol. 23, 495\u2013510 (2023).","journal-title":"Nat. Rev. Immunol."},{"key":"69295_CR58","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-021-09080-0","volume":"22","author":"T Korpela","year":"2022","unstructured":"Korpela, T. et al. Pancreatic fibrosis, acinar atrophy and chronic inflammation in surgical specimens associated with survival in patients with resectable pancreatic ductal adenocarcinoma. BMC Cancer 22, 23 (2022).","journal-title":"BMC Cancer"},{"key":"69295_CR59","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1111\/dme.14154","volume":"37","author":"SA Campbell","year":"2020","unstructured":"Campbell, S. A., Light, P. E. & Simpson, S. H. Costarting sitagliptin with metformin is associated with a lower likelihood of disease progression in newly treated people with type 2 diabetes: a cohort study. Diabet. Med. 37, 1715\u20131722 (2020).","journal-title":"Diabet. Med."},{"key":"69295_CR60","doi-asserted-by":"publisher","first-page":"3262","DOI":"10.1007\/s00125-012-2716-9","volume":"55","author":"P Marchetti","year":"2012","unstructured":"Marchetti, P. et al. A local glucagon-like peptide 1 (GLP-1) system in human pancreatic islets. Diabetologia 55, 3262\u20133272 (2012).","journal-title":"Diabetologia"},{"key":"69295_CR61","doi-asserted-by":"publisher","first-page":"e202010039","DOI":"10.1083\/jcb.202010039","volume":"220","author":"A Mueller","year":"2020","unstructured":"Mueller, A. et al. 3D FIB-SEM reconstruction of microtubule-organelle interaction in whole primary mouse beta cells. J. Cell Biol. 220, e202010039 (2020).","journal-title":"J. Cell Biol."},{"key":"69295_CR62","doi-asserted-by":"publisher","first-page":"5277","DOI":"10.1038\/s44319-024-00321-4","volume":"25","author":"F D\u00edaz-Castro","year":"2024","unstructured":"D\u00edaz-Castro, F., Morselli, E. & Claret, M. Interplay between the brain and adipose tissue: a metabolic conversation. EMBO Rep. 25, 5277\u20135293 (2024).","journal-title":"EMBO Rep."},{"key":"69295_CR63","doi-asserted-by":"publisher","unstructured":"Babbar, R. et al. Prediction of glucose tolerance without an oral glucose tolerance test. Front. Endocrinol. 9, https:\/\/doi.org\/10.3389\/fendo.2018.00082\/full (2018).","DOI":"10.3389\/fendo.2018.00082\/full"},{"key":"69295_CR64","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.2337\/diacare.21.12.2191","volume":"21","author":"JC Levy","year":"1998","unstructured":"Levy, J. C., Matthews, D. R. & Hermans, M. P. Correct homeostasis model assessment (HOMA) evaluation uses the computer program. Diab. Care 21, 2191\u20132192 (1998).","journal-title":"Diab. Care"},{"key":"69295_CR65","doi-asserted-by":"crossref","unstructured":"American Diabetes Association. 2. Classification and diagnosis of diabetes: standards of medical care in diabetes-2021. Diabetes Care 44, S15\u2013S33 (2020).","DOI":"10.2337\/dc21-S002"},{"key":"69295_CR66","doi-asserted-by":"publisher","unstructured":"Filiot, A. et al. Scaling self-supervised learning for histopathology with masked image modeling. https:\/\/doi.org\/10.1101\/2023.07.21.23292757v2 (2023).","DOI":"10.1101\/2023.07.21.23292757v2"},{"key":"69295_CR67","doi-asserted-by":"publisher","unstructured":"Courtiol, P., Tramel, E. W., Sanselme, M. & Wainrib, G. Classification and disease localization in histopathology using only global labels: a weakly-supervised approach. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1802.02212 (2020).","DOI":"10.48550\/arXiv.1802.02212"},{"key":"69295_CR68","doi-asserted-by":"publisher","unstructured":"Hendrycks, D. & Gimpel, K. Gaussian Error Linear Units (GELUs). Preprint at https:\/\/doi.org\/10.48550\/arXiv.1606.08415 (2023).","DOI":"10.48550\/arXiv.1606.08415"},{"key":"69295_CR69","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: visualising image classification models and saliency maps. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1312.6034 (2014).","DOI":"10.48550\/arXiv.1312.6034"},{"key":"69295_CR70","unstructured":"Balduzzi, D. et al. The Shattered Gradients Problem: If resnets are the answer, then what is the question? In Proc. 34th International Conference on Machine Learning, 342\u2013350 (PMLR, 2017)."},{"key":"69295_CR71","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P. & Frasconi, P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5, 157\u2013166 (1994).","journal-title":"IEEE Trans. Neural Netw."},{"key":"69295_CR72","unstructured":"Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In Proc. 34th International Conference on Machine Learning, Vol 70, ICML\u201917, 3145\u20133153 (JMLR.org, 2017)."},{"key":"69295_CR73","doi-asserted-by":"publisher","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F. B. & Wattenberg, M. SmoothGrad: removing noise by adding noise. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1706.03825 (2017).","DOI":"10.48550\/arXiv.1706.03825"},{"key":"69295_CR74","doi-asserted-by":"publisher","unstructured":"Gotkowski, K. et al. Embarrassingly simple scribble supervision for 3D medical segmentation. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2403.12834 (2024).","DOI":"10.48550\/arXiv.2403.12834"},{"key":"69295_CR75","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"69295_CR76","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1145\/279232.279236","volume":"23","author":"C Zhu","year":"1997","unstructured":"Zhu, C., Byrd, R. H., Lu, P. & Nocedal, J. Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization. ACM Trans. Math. Softw. 23, 550\u2013560 (1997).","journal-title":"ACM Trans. Math. Softw."}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69295-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69295-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69295-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:04:50Z","timestamp":1770815090000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69295-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":76,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["69295"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-69295-2","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]},"assertion":[{"value":"22 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The Authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1558"}}