Hind Dadoun1, Anne-Laure Rousseau1, Eric de Kerviler1, Jean-Michel Correas1, Anne-Marie Tissier1, Fanny Joujou1, Sylvain Bodard1, Kemel Khezzane1, Constance de Margerie-Mellon1, Hervé Delingette1, Nicholas Ayache1. 1. Université Côte d'Azur, Inria, Epione Team, Sophia Antipolis, 2004 Route des Lucioles, 06902 Valbonne, France (H. Dadoun, H. Delingette, N.A.); Department of Vascular Surgery, Georges Pompidou European Hospital APHP, Université de Paris, Paris, France (A.L.R.); NHance.ngo, Saint Germain en Laye, France (A.L.R.); Department of Radiology, Hôpital Saint Louis APHP, Université de Paris, Paris, France (E.d.K., F.J., K.K., C.d.M.M.); and Department of Adult Radiology, Université de Paris and Université de l'Hôpital Necker, Paris, France (J.M.C., A.M.T., S.B.).
Abstract
Purpose: To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images. Materials and Methods: In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based convolutional neural network (Faster R-CNN) and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018). Performance of the networks was analyzed on a test set of 48 additional patients (n = 155 B-mode abdominal US images obtained in 2019) and compared with the performance of three caregivers (one nonexpert and two experts) blinded to the clinical history. The sign test was used to compare accuracy, specificity, sensitivity, and positive predictive value among all raters. Results: DETR achieved a specificity of 90% (95% CI: 75, 100) and a sensitivity of 97% (95% CI: 97, 97) for the detection of FLLs. The performance of DETR met or exceeded that of the three caregivers for this task. DETR correctly localized 80% of the lesions, and it achieved a specificity of 81% (95% CI: 67, 91) and a sensitivity of 82% (95% CI: 62, 100) for FLL characterization (benign vs malignant) among lesions localized by all raters. The performance of DETR met or exceeded that of two experts and Faster R-CNN for these tasks. Conclusion: DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images. Supplemental material is available for this article. RSNA, 2022Keywords: Computer-aided Diagnosis (CAD), Ultrasound, Abdomen/GI, Liver, Tissue Characterization, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN). 2022 by the Radiological Society of North America, Inc.
Purpose: To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images. Materials and Methods: In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based convolutional neural network (Faster R-CNN) and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018). Performance of the networks was analyzed on a test set of 48 additional patients (n = 155 B-mode abdominal US images obtained in 2019) and compared with the performance of three caregivers (one nonexpert and two experts) blinded to the clinical history. The sign test was used to compare accuracy, specificity, sensitivity, and positive predictive value among all raters. Results: DETR achieved a specificity of 90% (95% CI: 75, 100) and a sensitivity of 97% (95% CI: 97, 97) for the detection of FLLs. The performance of DETR met or exceeded that of the three caregivers for this task. DETR correctly localized 80% of the lesions, and it achieved a specificity of 81% (95% CI: 67, 91) and a sensitivity of 82% (95% CI: 62, 100) for FLL characterization (benign vs malignant) among lesions localized by all raters. The performance of DETR met or exceeded that of two experts and Faster R-CNN for these tasks. Conclusion: DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images. Supplemental material is available for this article. RSNA, 2022Keywords: Computer-aided Diagnosis (CAD), Ultrasound, Abdomen/GI, Liver, Tissue Characterization, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN). 2022 by the Radiological Society of North America, Inc.
Authors: Robert F Hanna; Vesselin Z Miloushev; An Tang; Lee A Finklestone; Sidney Z Brejt; Ranjit S Sandhu; Cynthia S Santillan; Tanya Wolfson; Anthony Gamst; Claude B Sirlin Journal: Abdom Radiol (NY) Date: 2016-01
Authors: B Schmauch; P Herent; P Jehanno; O Dehaene; C Saillard; C Aubé; A Luciani; N Lassau; S Jégou Journal: Diagn Interv Imaging Date: 2019-03-27 Impact factor: 4.026
Authors: Hana Park; Jun Yong Park; Do Young Kim; Sang Hoon Ahn; Chae Yoon Chon; Kwang-Hyub Han; Seung Up Kim Journal: World J Gastroenterol Date: 2013-01-14 Impact factor: 5.742