{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T15:08:31Z","timestamp":1789398511154,"version":"build-2803163510"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T00:00:00Z","timestamp":1724889600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007278","name":"Henry Ford Health System","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007278","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"\n Introduction<\/jats:title>\n Early detection of pancreatic cancer continues to be a challenge due to the difficulty in accurately identifying specific signs or symptoms that might correlate with the onset of pancreatic cancer. Unlike breast or colon or prostate cancer where screening tests are often useful in identifying cancerous development, there are no tests to diagnose pancreatic cancers. As a result, most pancreatic cancers are diagnosed at an advanced stage, where treatment options, whether systemic therapy, radiation, or surgical interventions, offer limited efficacy.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A two-stage weakly supervised deep learning-based model has been proposed to identify pancreatic tumors using computed tomography (CT) images from Henry Ford Health (HFH) and publicly available Memorial Sloan Kettering Cancer Center (MSKCC) data sets. In the first stage, the nnU-Net supervised segmentation model was used to crop an area in the location of the pancreas, which was trained on the MSKCC repository of 281 patient image sets with established pancreatic tumors. In the second stage, a multi-instance learning-based weakly supervised classification model was applied on the cropped pancreas region to segregate pancreatic tumors from normal appearing pancreas. The model was trained, tested, and validated on images obtained from an HFH repository with 463 cases and 2,882 controls.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The proposed deep learning model, the two-stage architecture, offers an accuracy of 0.907\n \n \n \n \u00a0<\/mml:mo>\n \u00b1<\/mml:mo>\n \u00a0<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.01, sensitivity of 0.905\n \n \n \n \u00a0<\/mml:mo>\n \u00b1<\/mml:mo>\n \u00a0<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.01, specificity of 0.908\n \n \n \n \u00a0<\/mml:mo>\n \u00b1<\/mml:mo>\n \u00a0<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.02, and AUC (ROC) 0.903\n \n \n \n \u00a0<\/mml:mo>\n \u00b1<\/mml:mo>\n \u00a0<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.01. The two-stage framework can automatically differentiate pancreatic tumor from non-tumor pancreas with improved accuracy on the HFH dataset.\n <\/jats:p>\n <\/jats:sec>\n \n Discussion<\/jats:title>\n The proposed two-stage deep learning architecture shows significantly enhanced performance for predicting the presence of a tumor in the pancreas using CT images compared with other reported studies in the literature.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fonc.2024.1362850","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T00:54:06Z","timestamp":1724892846000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Weakly supervised large-scale pancreatic cancer detection using multi-instance learning"],"prefix":"10.3389","volume":"14","author":[{"given":"Shyamapada","family":"Mandal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keerthiveena","family":"Balraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hariprasad","family":"Kodamana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chetan","family":"Arora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julie M.","family":"Clark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David S.","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag S.","family":"Rathore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,8,29]]},"reference":[{"key":"B1","unstructured":"Pancreatic cancer prognosis, Aug. 08, 2021"},{"key":"B2","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1097\/MPA.0000000000001762","article-title":"Artificial intelligence and early detection of pancreatic cancer: 2020 summative review","volume":"50","author":"Kenner","year":"2021","journal-title":"Pancreas"},{"key":"B3","unstructured":"IsenseeF\n 10.11588\/HEIDOK.00029345Heidelberg, GermanyUniversity of HeidelbergFrom manual to automated design of biomedical semantic segmentation methods2020"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1274803","article-title":"Lesion segmentation on 18 F-fluciclovine (18 F-FACBC) PET\/CT images using deep learning","volume":"13","author":"Wang","year":"2023","journal-title":"Front Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1285924","article-title":"Deep learning application for abdominal organs segmentation on 0.35 T MR-Linac images","volume":"13","author":"Zhou","year":"2024","journal-title":"Front Oncol"},{"key":"B6","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.03999","article-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv preprint arXiv:1804.03999"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00864","article-title":"Recurrent saliency transformation network: Incorporating multi-stage visual cues for small organ segmentation","author":"Yu","year":"2018"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30267-3","article-title":"Diagnosis and risk stratification in hypertrophic cardiomyopathy using machine learning wall thickness measurement: a comparison with human test-retest performance","volume":"3","author":"Augusto","year":"2021","journal-title":"Lancet Digital Health"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07454-9","article-title":"Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images","volume":"31","author":"Zhou","year":"2021","journal-title":"Eur Radiol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-39310-2","article-title":"The benefit of secondary prevention with oat fiber in reducing future cardiovascular event among CAD patients after coronary intervention","volume":"9","author":"Wu","year":"2019","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2015.7298965","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1225170","article-title":"Prediction of adenocarcinoma and squamous carcinoma based on CT perfusion parameters of brain metastases from lung cancer: a pilot study","volume":"13","author":"Jiang","year":"2023","journal-title":"Front Oncol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06214-8","article-title":"Deep learning for liver tumor diagnosis part II: convolutional neural network interpretation using radiologic imaging features","volume":"29","author":"Wang","year":"2019","journal-title":"Eur Radiol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-08128-1","article-title":"The prognostic value of tumor-infiltrating lymphocytes in hepatocellular carcinoma: a systematic review and meta-analysis","volume":"7","author":"Yao","year":"2017","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","first-page":"114562","DOI":"10.1016\/j.eswa.2021.114562","article-title":"Automated detection and counting of Artemia using U-shaped fully convolutional networks and deep convolutional networks","volume":"171","author":"Wang","year":"2021","journal-title":"Expert Syst Appl"},{"key":"B17","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/B978-0-12-818438-7.00002-2","article-title":"The rise of artificial intelligence in healthcare applications","author":"Bohr","year":"2020","journal-title":"Artif Intell healthcare"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30078-9","article-title":"Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation","volume":"2","author":"Liu","year":"2020","journal-title":"Lancet Digital Health"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7419-5","article-title":"Deep learning convolutional neural network (CNN) With Gaussian mixture model for predicting pancreatic cancer","volume":"79","author":"Sekaran","year":"2020","journal-title":"Multimedia Tools Appl"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.04.037","article-title":"Detection and diagnosis of pancreatic tumor using deep learning-based hierarchical convolutional neural network on the internet of medical things platform","volume":"111","author":"Xuan","year":"2020","journal-title":"Future Generation Comput Syst"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.42","article-title":"Lung and pancreatic tumor characterization in the deep learning era: novel supervised and unsupervised learning approaches","volume":"38","author":"Hussein","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"B22","doi-asserted-by":"publisher","first-page":"116444","DOI":"10.1016\/j.eswa.2021.116444","article-title":"Pancreas Co-segmentation based on dynamic ROI extraction and VGGU-Net","volume":"192","author":"Liu","year":"2022","journal-title":"Expert Syst Appl"},{"key":"B23","doi-asserted-by":"publisher","first-page":"102774","DOI":"10.1016\/j.media.2023.102774","article-title":"Generalized pancreatic cancer diagnosis via multiple instance learning and anatomically-guided shape normalization","volume":"86","author":"Qu","year":"2023","journal-title":"Med Image Anal"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3236162","article-title":"Causality-driven graph neural network for early diagnosis of pancreatic cancer in non-contrast computerized tomography","volume":"42","author":"Li","year":"2023","journal-title":"IEEE Trans Med Imaging"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1159\/000503291","article-title":"Preoperative prediction of pancreatic neuroendocrine neoplasms grading based on enhanced computed tomography imaging: validation of deep learning with a convolutional neural network","volume":"110","author":"Luo","year":"2020","journal-title":"Neuroendocrinology"},{"key":"B26","doi-asserted-by":"publisher","first-page":"833","DOI":"10.21037\/atm","article-title":"Predicting the recurrence risk of pancreatic neuroendocrine neoplasms after radical resection using deep learning radiomics with preoperative computed tomography images","volume":"9","author":"Song","year":"2021","journal-title":"Ann Trans Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1186\/s12918-018-0572-z","article-title":"Hierarchical combinatorial deep learning architecture for pancreas segmentation of medical computed tomography cancer images","volume":"12","author":"Fu","year":"2018","journal-title":"BMC Syst Biol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-022-00685-w","article-title":"RAD-UNet: a residual, attention-based, dense UNet for CT sparse reconstruction","volume":"35","author":"Qiao","year":"2022","journal-title":"J Digital Imaging"},{"key":"B29","doi-asserted-by":"publisher","first-page":"102232","DOI":"10.1016\/j.media.2021.102232","article-title":"M3Net: A multi-scale multi-view framework for multi-phase pancreas segmentation based on cross-phase non-local attention","volume":"75","author":"Qu","year":"2022","journal-title":"Med Image Anal"},{"key":"B30","doi-asserted-by":"publisher","first-page":"101829","DOI":"10.1016\/j.media.2020.101829","article-title":"Statistical deformation reconstruction using multi-organ shape features for pancreatic cancer localization","volume":"67","author":"Nakao","year":"2021","journal-title":"Med image Anal"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09063","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","author":"Simpson","year":"2019","journal-title":"arXiv preprint arXiv:1902.09063"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository","volume":"26","author":"Clark","year":"2013","journal-title":"J digital Imaging"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on whole slide images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"118016","DOI":"10.1016\/j.eswa.2022.118016","article-title":"An unsupervised domain adaptation brain CT segmentation method across image modalities and diseases","volume":"207","author":"Dong","year":"2022","journal-title":"Expert Syst Appl"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.06382","article-title":"Hierarchical 3D fully convolutional networks for multi-organ segmentation","author":"Roth","year":"2017","journal-title":"arXiv preprint arXiv:1704.06382"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.34","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.660","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"},{"key":"B39","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.549","article-title":"Refinenet: Multi-path refinement networks for high-resolution semantic segmentation","author":"Lin","year":"2017"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1279750","article-title":"A deep learning model to generate synthetic CT for prostate MR-only radiotherapy dose planning: a multicenter study","volume":"13","author":"Tahri","year":"2023","journal-title":"Front Oncol"},{"key":"B41","article-title":"Deepprognosis: Preoperative prediction of pancreatic cancer survival and surgical margin via contrast-enhanced CT imaging","author":"Yao","year":"2019"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.42","article-title":"Classification of volumetric images using multi-instance learning and extreme value theorem","volume":"39","author":"Tennakoon","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"B43","first-page":"1","article-title":"Learning and interpreting multi-multi-instance learning networks","volume":"21","author":"Tibo","year":"2020","journal-title":"J Mach Learn Res"},{"key":"B44","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B45","doi-asserted-by":"publisher","first-page":"119113","DOI":"10.1016\/j.eswa.2022.119113","article-title":"Robust bag classification approach for multi-instance learning via subspace fuzzy clustering","volume":"214","author":"Waqas","year":"2023","journal-title":"Expert Syst Appl"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.phpro.2012.03.206","article-title":"A clustering method based on K-means algorithm","volume":"25","author":"Li","year":"2012","journal-title":"Phys Proc"},{"key":"B47","doi-asserted-by":"publisher","first-page":"107762","DOI":"10.1016\/j.patcog.2020.107762","article-title":"Automatic pancreas segmentation based on lightweight DCNN modules and spatial prior propagation","volume":"114","author":"Zhang","year":"2021","journal-title":"Pattern Recognition"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.11.112","article-title":"Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation","volume":"392","author":"Ibragimov","year":"2020","journal-title":"Neurocomputing"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1159\/000503291","article-title":"Preoperative prediction of pancreatic neuroendocrine neoplasms grading based on enhanced computed tomography imaging: validation of deep learning with a convolutional neural network","volume":"110","author":"Luo","year":"2020","journal-title":"Neuroendocrinology"},{"key":"B51","doi-asserted-by":"publisher","first-page":"5156","DOI":"10.3748\/wjg.v26.i34.5156","article-title":"Construction of a convolutional neural network classifier developed by computed tomography images for pancreatic cancer diagnosis","volume":"26","author":"Ma","year":"2020","journal-title":"World J Gastroenterol"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.10601","article-title":"Efficient context-aware network for abdominal multi-organ segmentation","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv:2109.10601"},{"key":"B53","first-page":"80","article-title":"Global and local multi-scale feature fusion enhancement for brain tumor segmentation and pancreas segmentation","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes. Lecture Notes in Computer Science, Shenzhen, China, October 17, 2019","author":"Wang","year":"2020"},{"key":"B54","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/s00530-022-00963-1","article-title":"FPF-Net: feature propagation and fusion based on attention mechanism for pancreas segmentation","volume":"29","author":"Chen","year":"2022","journal-title":"Multimedia Syst"},{"key":"B55","first-page":"220","article-title":"Scalable neural architecture search for 3d medical image segmentation","volume-title":"In International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Kim","year":"2019"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2024.1362850\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T00:54:14Z","timestamp":1724892854000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2024.1362850\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,29]]},"references-count":55,"alternative-id":["10.3389\/fonc.2024.1362850"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2024.1362850","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,29]]},"article-number":"1362850"}}