Julia Arribas Anta1,2, Iván Martínez-Ballestero1, Daniel Eiroa1,3, Javier García1, Júlia Rodríguez-Comas4. 1. Scientific and Technical Department, Sycai Technologies S.L., Carrer Roc Boronat 117, MediaTIC Building, 08018, Barcelona, Spain. 2. Department of Gastroenterology, University Hospital, 12 Octubre. Av. de Córdoba, s/n, 28041, Madrid, Spain. 3. Department of Radiology, Institut de Diagnòstic per la Imatge (IDI), Hospital Universitari Vall d'Hebrón, Passeig de la Vall d'Hebron, 119-129, 08035, Barcelona, Spain. 4. Scientific and Technical Department, Sycai Technologies S.L., Carrer Roc Boronat 117, MediaTIC Building, 08018, Barcelona, Spain. jantiart@gmail.com.
Abstract
PURPOSE: Pancreatic cancer is one of the most lethal neoplasms among common cancers worldwide, and PCLs are well-known precursors of this type of cancer. Artificial intelligence (AI) could help to improve and speed up the detection and classification of pancreatic lesions. The aim of this review is to summarize the articles addressing the diagnostic yield of artificial intelligence applied to medical imaging (computed tomography [CT] and/or magnetic resonance [MR]) for the detection of pancreatic cancer and pancreatic cystic lesions. METHODS: We performed a comprehensive literature search using PubMed, EMBASE, and Scopus (from January 2010 to April 2021) to identify full articles evaluating the diagnostic accuracy of AI-based methods processing CT or MR images to detect pancreatic ductal adenocarcinoma (PDAC) or pancreatic cystic lesions (PCLs). RESULTS: We found 20 studies meeting our inclusion criteria. Most of the AI-based systems used were convolutional neural networks. Ten studies addressed the use of AI to detect PDAC, eight studies aimed to detect and classify PCLs, and 4 aimed to predict the presence of high-grade dysplasia or cancer. CONCLUSION: AI techniques have shown to be a promising tool which is expected to be helpful for most radiologists' tasks. However, methodologic concerns must be addressed, and prospective clinical studies should be carried out before implementation in clinical practice.
PURPOSE: Pancreatic cancer is one of the most lethal neoplasms among common cancers worldwide, and PCLs are well-known precursors of this type of cancer. Artificial intelligence (AI) could help to improve and speed up the detection and classification of pancreatic lesions. The aim of this review is to summarize the articles addressing the diagnostic yield of artificial intelligence applied to medical imaging (computed tomography [CT] and/or magnetic resonance [MR]) for the detection of pancreatic cancer and pancreatic cystic lesions. METHODS: We performed a comprehensive literature search using PubMed, EMBASE, and Scopus (from January 2010 to April 2021) to identify full articles evaluating the diagnostic accuracy of AI-based methods processing CT or MR images to detect pancreatic ductal adenocarcinoma (PDAC) or pancreatic cystic lesions (PCLs). RESULTS: We found 20 studies meeting our inclusion criteria. Most of the AI-based systems used were convolutional neural networks. Ten studies addressed the use of AI to detect PDAC, eight studies aimed to detect and classify PCLs, and 4 aimed to predict the presence of high-grade dysplasia or cancer. CONCLUSION: AI techniques have shown to be a promising tool which is expected to be helpful for most radiologists' tasks. However, methodologic concerns must be addressed, and prospective clinical studies should be carried out before implementation in clinical practice.
Authors: Lola Rahib; Benjamin D Smith; Rhonda Aizenberg; Allison B Rosenzweig; Julie M Fleshman; Lynn M Matrisian Journal: Cancer Res Date: 2014-06-01 Impact factor: 12.701
Authors: S Park; L C Chu; R H Hruban; B Vogelstein; K W Kinzler; A L Yuille; D F Fouladi; S Shayesteh; S Ghandili; C L Wolfgang; R Burkhart; J He; E K Fishman; S Kawamoto Journal: Diagn Interv Imaging Date: 2020-04-08 Impact factor: 4.026
Authors: Ahmed Hosny; Chintan Parmar; John Quackenbush; Lawrence H Schwartz; Hugo J W L Aerts Journal: Nat Rev Cancer Date: 2018-08 Impact factor: 60.716