Deep Learning Prediction of Voxel-Level Liver Stiffness in Patients with Nonalcoholic Fatty Liver Disease.

Autor:	Pollack BL; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Batmanghelich K; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Cai SS; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Gordon E; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Wallace S; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Catania R; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Morillo-Hernandez C; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Furlan A; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.)., Borhani AA; Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.).
Jazyk:	angličtina
Zdroj:	Radiology. Artificial intelligence [Radiol Artif Intell] 2021 Sep 29; Vol. 3 (6), pp. e200274. Date of Electronic Publication: 2021 Sep 29 (Print Publication: 2021).
DOI:	10.1148/ryai.2021200274
Abstrakt:	Purpose: To reconstruct virtual MR elastography (MRE) images based on traditional MRI inputs with a machine learning algorithm. Materials and Methods: In this single-institution, retrospective study, 149 patients (mean age, 58 years ± 12 [standard deviation]; 71 men) with nonalcoholic fatty liver disease who underwent MRI and MRE between January 2016 and January 2019 were evaluated. Nine conventional MRI sequences and clinical data were used to train a convolutional neural network to reconstruct MRE images at the per-voxel level. The architecture was further modified to accept multichannel three-dimensional inputs and to allow inclusion of clinical and demographic information. Liver stiffness and fibrosis category (F0 [no fibrosis] to F4 [significant fibrosis]) of reconstructed images were assessed by using voxel- and patient-level agreement by correlation, sensitivity, and specificity calculations; in addition, classification by receiver operator characteristic analyses was performed, and Dice score was used to evaluate hepatic stiffness locality. Results: The model for predicting liver stiffness incorporated four image sequences (precontrast T1-weighted liver acquisition with volume acquisition [LAVA] water and LAVA fat, 120-second-delay T1-weighted LAVA water, and single-shot fast spin-echo T2 weighted) and clinical data. The model had a patient-level and voxel-level correlation of 0.50 ± 0.05 and 0.34 ± 0.03, respectively. By using a stiffness threshold of 3.54 kPa to make a binary classification into no fibrosis or mild fibrosis (F0-F1) versus clinically significant fibrosis (F2-F4), the model had sensitivity of 80% ± 4, specificity of 75% ± 5, accuracy of 78% ± 3, area under the receiver operating characteristic curve of 84 ± 0.04, and a Dice score of 0.74. Conclusion: The generation of virtual elastography images is feasible by using conventional MRI and clinical data with a machine learning algorithm. Keywords: MR Imaging, Abdomen/GI, Liver, Cirrhosis, Computer Applications/Virtual Imaging, Experimental Investigations, Feature Detection, Classification, Reconstruction Algorithms, Supervised Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2021. Competing Interests: Disclosures of Conflicts of Interest: B.L.P. No relevant relationships. K.B. No relevant relationships. S.S.C. No relevant relationships. E.G. No relevant relationships. S.W. No relevant relationships. R.C. No relevant relationships. C.M.H. No relevant relationships. A.F. Consultancy from Bracco Diagnostics; grant from Endra Life Sciences; royalties from Elsevier/Amirsys. A.A.B. Grant from the Pittsburgh Liver Research Center. (2021 by the Radiological Society of North America, Inc.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu