{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T21:59:01Z","timestamp":1794088741908,"version":"4.8.0"},"reference-count":32,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"11","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":["Invest Radiol"],"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:sec>\n            <jats:title>Objectives<\/jats:title>\n            <jats:p>This study proposes and evaluates a deep learning method to detect pancreatic neoplasms and to identify main pancreatic duct (MPD) dilatation on portal venous computed tomography scans.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Materials and Methods<\/jats:title>\n            <jats:p>A total of 2890 portal venous computed tomography scans from 9 institutions were acquired, among which 2185 had a pancreatic neoplasm and 705 were healthy controls. Each scan was reviewed by one in a group of 9 radiologists. Physicians contoured the pancreas, pancreatic lesions if present, and the MPD if visible. They also assessed tumor type and MPD dilatation. Data were split into a training and independent testing set of 2134 and 756 cases, respectively.<\/jats:p>\n            <jats:p>A method to detect pancreatic lesions and MPD dilatation was built in 3 steps. First, a segmentation network was trained in a 5-fold cross-validation manner. Second, outputs of this network were postprocessed to extract imaging features: a normalized lesion risk, the predicted lesion diameter, and the MPD diameter in the head, body, and tail of the pancreas. Third, 2 logistic regression models were calibrated to predict lesion presence and MPD dilatation, respectively. Performance was assessed on the independent test cohort using receiver operating characteristic analysis. The method was also evaluated on subgroups defined based on lesion types and characteristics.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The area under the curve of the model detecting lesion presence in a patient was 0.98 (95% confidence interval [CI], 0.97\u20130.99). A sensitivity of 0.94 (469 of 493; 95% CI, 0.92\u20130.97) was reported. Similar values were obtained in patients with small (less than 2 cm) and isodense lesions with a sensitivity of 0.94 (115 of 123; 95% CI, 0.87\u20130.98) and 0.95 (53 of 56, 95% CI, 0.87\u20131.0), respectively. The model sensitivity was also comparable across lesion types with values of 0.94 (95% CI, 0.91\u20130.97), 1.0 (95% CI, 0.98\u20131.0), 0.96 (95% CI, 0.97\u20131.0) for pancreatic ductal adenocarcinoma, neuroendocrine tumor, and intraductal papillary neoplasm, respectively. Regarding MPD dilatation detection, the model had an area under the curve of 0.97 (95% CI, 0.96\u20130.98).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>The proposed approach showed high quantitative performance to identify patients with pancreatic neoplasms and to detect MPD dilatation on an independent test cohort. Performance was robust across subgroups of patients with different lesion characteristics and types. Results confirmed the interest to combine a direct lesion detection approach with secondary features such as the MPD diameter, thus indicating a promising avenue for the detection of pancreatic cancer at early stages.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/rli.0000000000000992","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T11:00:12Z","timestamp":1686222012000},"page":"791-798","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":27,"title":["Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning"],"prefix":"10.1097","volume":"58","author":[{"given":"Cl\u00e9ment","family":"Abi Nader","sequence":"first","affiliation":[{"name":"Guerbet Research, Villepinte"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebeca","family":"Vetil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura Kate","family":"Wood","sequence":"additional","affiliation":[{"name":"Guerbet Research, Villepinte"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc-Michel","family":"Rohe","sequence":"additional","affiliation":[{"name":"Guerbet Research, Villepinte"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandre","family":"B\u00f4ne","sequence":"additional","affiliation":[{"name":"Guerbet Research, Villepinte"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hedvig","family":"Karteszi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Pierre","family":"Vullierme","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hospital of Annecy-Genevois, Universit\u00e9 Paris-Cit\u00e9, Paris, France."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"bib1-20250802","doi-asserted-by":"crossref","first-page":"10","DOI":"10.14740\/wjon1166","article-title":"Epidemiology of pancreatic cancer: global trends, etiology and risk factors","volume":"10","year":"2019","journal-title":"World J Oncol"},{"key":"bib2-20250802","first-page":"209","article-title":"Global Cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"bib3-20250802","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1186\/s13244-020-00861-y","article-title":"Imaging diagnosis and staging of pancreatic ductal adenocarcinoma: a comprehensive review","volume":"11","year":"2020","journal-title":"Insights Imaging"},{"key":"bib4-20250802","first-page":"132","article-title":"Which is the best imaging method in pancreatic adenocarcinoma diagnosis and staging\u2014CT, MRI or EUS?","volume":"43","year":"2017","journal-title":"Curr Health Sci J"},{"key":"bib5-20250802","doi-asserted-by":"crossref","first-page":"W37","DOI":"10.2214\/AJR.13.12439","article-title":"Impact of the time interval between MDCT imaging and surgery on the accuracy of identifying metastatic disease in patients with pancreatic cancer","volume":"204","year":"2015","journal-title":"AJR Am J Roentgenol"},{"key":"bib6-20250802","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1001\/jama.2019.9690","article-title":"Screening for pancreatic cancer","volume":"322","year":"2019","journal-title":"JAMA"},{"key":"bib7-20250802","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1093\/jnci\/djaa004","article-title":"Recent trends in the incidence and survival of stage 1A pancreatic cancer: a surveillance, epidemiology, and end results analysis","volume":"112","year":"2020","journal-title":"J Natl Cancer Inst"},{"key":"bib8-20250802","doi-asserted-by":"crossref","first-page":"897","DOI":"10.2214\/ajr.182.4.1820897","article-title":"Time interval between abnormalities seen on CT and the clinical diagnosis of pancreatic cancer: retrospective review of CT scans obtained before diagnosis","volume":"182","year":"2004","journal-title":"AJR Am J Roentgenol"},{"key":"bib9-20250802","doi-asserted-by":"crossref","first-page":"4941","DOI":"10.1007\/s00330-017-4895-8","article-title":"Development of pancreatic cancer is predictable well in advance using contrast-enhanced CT: a case-cohort study","volume":"27","year":"2017","journal-title":"Eur Radiol"},{"key":"bib10-20250802","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.2214\/AJR.21.26014","article-title":"CT abnormalities of the pancreas associated with the subsequent diagnosis of clinical stage I pancreatic ductal adenocarcinoma more than 1 year later: a case-control study","volume":"217","year":"2021","journal-title":"AJR Am J Roentgenol"},{"key":"bib11-20250802","doi-asserted-by":"crossref","first-page":"4160","DOI":"10.1007\/s00261-022-03671-6","article-title":"Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case-control study","volume":"47","year":"2022","journal-title":"Abdom Radiol (NY)"},{"key":"bib12-20250802","first-page":"3","article-title":"Radiomics and deep learning for disease detection in musculoskeletal radiology: an overview of novel MRI- and CT-based approaches","volume":"58","year":"2022","journal-title":"Invest Radiol"},{"key":"bib13-20250802","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1097\/RLI.0000000000000791","article-title":"Fully automatic deep learning in bi-institutional prostate magnetic resonance imaging","volume":"56","year":"2021","journal-title":"Invest Radiol"},{"key":"bib14-20250802","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1097\/RLI.0000000000000842","article-title":"Deep learning algorithm for fully automated detection of small (\u22644 cm) renal cell carcinoma in contrast-enhanced computed tomography using a multicenter database","volume":"57","year":"2022","journal-title":"Invest Radiol"},{"key":"bib15-20250802","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","year":"2020","journal-title":"Nature"},{"key":"bib16-20250802","doi-asserted-by":"crossref","first-page":"106043","DOI":"10.1016\/j.cmpb.2021.106043","article-title":"Recurrent feature fusion learning for multi-modality PET-CT tumor segmentation","volume":"203","year":"2021","journal-title":"Comput Methods Programs Biomed"},{"key":"bib17-20250802","doi-asserted-by":"crossref","first-page":"30","DOI":"10.2967\/jnumed.120.242412","article-title":"Deep-learning 18F-FDG uptake classification enables total metabolic tumor volume estimation in diffuse large B-cell lymphoma","volume":"62","year":"2021","journal-title":"J Nucl Med"},{"key":"bib18-20250802","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1038\/s41597-022-01718-3","article-title":"A whole-body FDG-PET\/CT dataset with manually annotated tumor lesions","volume":"9","year":"2022","journal-title":"Sci Data"},{"key":"bib19-20250802","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1007\/s10278-020-00341-1","article-title":"Tumor segmentation and feature extraction from whole-body FDG-PET\/CT using cascaded 2D and 3D convolutional neural networks","volume":"33","year":"2020","journal-title":"J Digit Imaging"},{"key":"bib20-20250802","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1097\/MPA.0000000000001762","article-title":"Artificial intelligence and early detection of pancreatic cancer: 2020 summative review","volume":"50","year":"2021","journal-title":"Pancreas"},{"key":"bib21-20250802","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1148\/radiol.220152","article-title":"Pancreatic cancer detection on CT scans with deep learning: a nationwide population-based study","volume":"306","year":"2023","journal-title":"Radiology"},{"key":"bib22-20250802","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1148\/radiol.220171","article-title":"Deep learning\u2013based detection of solid and cystic pancreatic neoplasms at contrast-enhanced CT","volume":"306","year":"2023","journal-title":"Radiology"},{"key":"bib23-20250802","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","volume":"abs\/1902.09063","year":"2019","journal-title":"CoRR"},{"key":"bib26-20250802","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D slicer as an image computing platform for the quantitative imaging network","volume":"30","year":"2012","journal-title":"Magn Reson Imaging"},{"key":"bib28-20250802","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning\u2013based biomedical image segmentation","volume":"18","year":"2021","journal-title":"Nat Methods"},{"key":"bib29-20250802","doi-asserted-by":"crossref","first-page":"e453","DOI":"10.7717\/peerj.453","article-title":"scikit-image: image processing in Python","volume":"2","year":"2014","journal-title":"PeerJ"},{"key":"bib30-20250802","doi-asserted-by":"crossref","first-page":"3091","DOI":"10.21105\/joss.03091","article-title":"imea: A Python package for extracting 2D and 3D shape measurements from images","volume":"6","year":"2021","journal-title":"J Open Source Software"},{"key":"bib32-20250802","article-title":"Evaluation of medical image segmentation models for uncertain, small or empty reference annotations","volume":"abs\/2209.13008","year":"2022","journal-title":"ArXiv"},{"key":"bib33-20250802","article-title":"Fully automatic deep learning framework for pancreatic ductal adenocarcinoma detection on computed tomography","volume":"14","year":"2022","journal-title":"Cancer"},{"key":"bib34-20250802","doi-asserted-by":"crossref","first-page":"e303","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","year":"2020","journal-title":"Lancet Digit Health"},{"key":"bib35-20250802","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1148\/radiol.11101133","article-title":"Small (< 20 mm) pancreatic adenocarcinomas: analysis of enhancement patterns and secondary signs with multiphasic multidetector CT","volume":"259","year":"2011","journal-title":"Radiology"},{"key":"bib40-20250802","first-page":"3395","article-title":"Segmentation for classification of screening pancreatic neuroendocrine tumors","year":"2020","journal-title":"2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"}],"container-title":["Investigative Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/RLI.0000000000000992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:06:22Z","timestamp":1754161582000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/RLI.0000000000000992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,8]]},"references-count":32,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1097\/rli.0000000000000992","relation":{},"ISSN":["1536-0210","0020-9996"],"issn-type":[{"value":"1536-0210","type":"electronic"},{"value":"0020-9996","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6,8]]}}}