Stefanie J Hectors1,2,3, Paul Kennedy1,2, Kuang-Han Huang1,4, Daniel Stocker1,2,5, Guillermo Carbonell1,2,6, Hayit Greenspan7, Scott Friedman8, Bachir Taouli9,10. 1. BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA. 2. Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY, 10029, USA. 3. Department of Radiology, Weill Cornell Medicine, New York, NY, USA. 4. Prealize Health, Palo Alto, CA, USA. 5. Institute of Interventional and Diagnostic Radiology, University Hospital Zurich and University of Zurich, Zurich, Switzerland. 6. Department of Radiology, Virgen de la Arrixaca University Clinical Hospital, University of Murcia, Murcia, Spain. 7. Medical Imaging Processing Lab, Faculty of Engineering, Department of Biomedical Engineering, Tel Aviv University, Tel Aviv, Israel. 8. Division of Liver Diseases, Icahn School of Medicine at Mount Sinai, New York, NY, USA. 9. BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA. bachir.taouli@mountsinai.org. 10. Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY, 10029, USA. bachir.taouli@mountsinai.org.
Abstract
OBJECTIVES: To (1) develop a fully automated deep learning (DL) algorithm based on gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and (2) compare the diagnostic performance of DL vs. MR elastography (MRE) for noninvasive staging of liver fibrosis. METHODS: This single-center retrospective study included 355 patients (M/F 238/117, mean age 60 years; training, n = 178; validation, n = 123; test, n = 54) who underwent gadoxetic acid-enhanced abdominal MRI, including HBP and MRE, and pathological evaluation of the liver within 1 year of MRI. Cropped liver HBP images from a custom-written fully automated liver segmentation were used as input for DL. A transfer learning approach based on the ImageNet VGG16 model was used. Different DL models were built for the prediction of fibrosis stages F1-4, F2-4, F3-4, and F4. ROC analysis was performed to evaluate the performance of DL in training, validation, and test sets and of MRE liver stiffness in the test set. RESULTS: AUC values of DL were 0.99/0.70/0.77 (F1-4), 0.92/0.71/0.91 (F2-4), 0.91/0.78/0.90 (F3-4), and 0.98/0.83/0.85 (F4) for training/validation/test sets, respectively. The AUCs of MRE liver stiffness in the test set were 0.86 (F1-4), 0.87 (F2-4), 0.92 (F3-4), and 0.86 (F4). AUCs of MRE and DL were not significantly different for any of the fibrosis stages (p > 0.134). CONCLUSIONS: The fully automated DL models based on HBP gadoxetic acid MRI showed good-to-excellent diagnostic performance for staging of liver fibrosis, with similar diagnostic performance to MRE. After validation in independent sets, the DL algorithm may allow for noninvasive liver fibrosis assessment without the need for additional MRI hardware. KEY POINTS: • The developed deep learning algorithm, based on routine standard-of-care gadoxetic acid-enhanced MRI data, showed good-to-excellent diagnostic performance for noninvasive staging of liver fibrosis. • The diagnostic performance of the deep learning algorithm was equivalent to that of MR elastography in a separate test set.
OBJECTIVES: To (1) develop a fully automated deep learning (DL) algorithm based on gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and (2) compare the diagnostic performance of DL vs. MR elastography (MRE) for noninvasive staging of liver fibrosis. METHODS: This single-center retrospective study included 355 patients (M/F 238/117, mean age 60 years; training, n = 178; validation, n = 123; test, n = 54) who underwent gadoxetic acid-enhanced abdominal MRI, including HBP and MRE, and pathological evaluation of the liver within 1 year of MRI. Cropped liver HBP images from a custom-written fully automated liver segmentation were used as input for DL. A transfer learning approach based on the ImageNet VGG16 model was used. Different DL models were built for the prediction of fibrosis stages F1-4, F2-4, F3-4, and F4. ROC analysis was performed to evaluate the performance of DL in training, validation, and test sets and of MRE liver stiffness in the test set. RESULTS: AUC values of DL were 0.99/0.70/0.77 (F1-4), 0.92/0.71/0.91 (F2-4), 0.91/0.78/0.90 (F3-4), and 0.98/0.83/0.85 (F4) for training/validation/test sets, respectively. The AUCs of MRE liver stiffness in the test set were 0.86 (F1-4), 0.87 (F2-4), 0.92 (F3-4), and 0.86 (F4). AUCs of MRE and DL were not significantly different for any of the fibrosis stages (p > 0.134). CONCLUSIONS: The fully automated DL models based on HBP gadoxetic acid MRI showed good-to-excellent diagnostic performance for staging of liver fibrosis, with similar diagnostic performance to MRE. After validation in independent sets, the DL algorithm may allow for noninvasive liver fibrosis assessment without the need for additional MRI hardware. KEY POINTS: • The developed deep learning algorithm, based on routine standard-of-care gadoxetic acid-enhanced MRI data, showed good-to-excellent diagnostic performance for noninvasive staging of liver fibrosis. • The diagnostic performance of the deep learning algorithm was equivalent to that of MR elastography in a separate test set.
Entities:
Keywords:
Artificial intelligence; Deep learning; Liver cirrhosis; Liver diseases; Magnetic resonance imaging
Authors: Jérémy Dana; Aïna Venkatasamy; Antonio Saviano; Joachim Lupberger; Yujin Hoshida; Valérie Vilgrain; Pierre Nahon; Caroline Reinhold; Benoit Gallix; Thomas F Baumert Journal: Hepatol Int Date: 2022-02-09 Impact factor: 9.029