Khaled Bousabarah1,2,3, Brian Letzen1, Jonathan Tefera1,4, Lynn Savic1,4, Isabel Schobert1,4, Todd Schlachter1, Lawrence H Staib1,5,6, Martin Kocher2, Julius Chapiro7, MingDe Lin1,8. 1. Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 333 Cedar Street, New Haven, CT, 06520, USA. 2. Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Cologne, Germany. 3. Visage Imaging GmbH, Lepsiusstraße 70, Berlin, 12163, Germany. 4. Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität, and Berlin Institute of Health, Institute of Radiology, 10117, Berlin, Germany. 5. Department of Biomedical Engineering, Yale School of Engineering and Applied Science, New Haven, CT, 06520, USA. 6. Department of Electrical Engineering, Yale School of Engineering and Applied Science, New Haven, CT, 06520, USA. 7. Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 333 Cedar Street, New Haven, CT, 06520, USA. j.chapiro@googlemail.com. 8. Visage Imaging, Inc, 12625 High Bluff Dr., Suite 205, San Diego, CA, 92130, USA.
Abstract
PURPOSE: Liver Imaging Reporting and Data System (LI-RADS) uses multiphasic contrast-enhanced imaging for hepatocellular carcinoma (HCC) diagnosis. The goal of this feasibility study was to establish a proof-of-principle concept towards automating the application of LI-RADS, using a deep learning algorithm trained to segment the liver and delineate HCCs on MRI automatically. METHODS: In this retrospective single-center study, multiphasic contrast-enhanced MRIs using T1-weighted breath-hold sequences acquired from 2010 to 2018 were used to train a deep convolutional neural network (DCNN) with a U-Net architecture. The U-Net was trained (using 70% of all data), validated (15%) and tested (15%) on 174 patients with 231 lesions. Manual 3D segmentations of the liver and HCC were ground truth. The dice similarity coefficient (DSC) was measured between manual and DCNN methods. Postprocessing using a random forest (RF) classifier employing radiomic features and thresholding (TR) of the mean neural activation was used to reduce the average false positive rate (AFPR). RESULTS: 73 and 75% of HCCs were detected on validation and test sets, respectively, using > 0.2 DSC criterion between individual lesions and their corresponding segmentations. Validation set AFPRs were 2.81, 0.77, 0.85 for U-Net, U-Net + RF, and U-Net + TR, respectively. Combining both RF and TR with the U-Net improved the AFPR to 0.62 and 0.75 for the validation and test sets, respectively. Mean DSC between automatically detected lesions using the DCNN + RF + TR and corresponding manual segmentations was 0.64/0.68 (validation/test), and 0.91/0.91 for liver segmentations. CONCLUSION: Our DCNN approach can segment the liver and HCCs automatically. This could enable a more workflow efficient and clinically realistic implementation of LI-RADS.
PURPOSE: Liver Imaging Reporting and Data System (LI-RADS) uses multiphasic contrast-enhanced imaging for hepatocellular carcinoma (HCC) diagnosis. The goal of this feasibility study was to establish a proof-of-principle concept towards automating the application of LI-RADS, using a deep learning algorithm trained to segment the liver and delineate HCCs on MRI automatically. METHODS: In this retrospective single-center study, multiphasic contrast-enhanced MRIs using T1-weighted breath-hold sequences acquired from 2010 to 2018 were used to train a deep convolutional neural network (DCNN) with a U-Net architecture. The U-Net was trained (using 70% of all data), validated (15%) and tested (15%) on 174 patients with 231 lesions. Manual 3D segmentations of the liver and HCC were ground truth. The dice similarity coefficient (DSC) was measured between manual and DCNN methods. Postprocessing using a random forest (RF) classifier employing radiomic features and thresholding (TR) of the mean neural activation was used to reduce the average false positive rate (AFPR). RESULTS: 73 and 75% of HCCs were detected on validation and test sets, respectively, using > 0.2 DSC criterion between individual lesions and their corresponding segmentations. Validation set AFPRs were 2.81, 0.77, 0.85 for U-Net, U-Net + RF, and U-Net + TR, respectively. Combining both RF and TR with the U-Net improved the AFPR to 0.62 and 0.75 for the validation and test sets, respectively. Mean DSC between automatically detected lesions using the DCNN + RF + TR and corresponding manual segmentations was 0.64/0.68 (validation/test), and 0.91/0.91 for liver segmentations. CONCLUSION: Our DCNN approach can segment the liver and HCCs automatically. This could enable a more workflow efficient and clinically realistic implementation of LI-RADS.
Authors: Moritz Gross; Michael Spektor; Ariel Jaffe; Ahmet S Kucukkaya; Simon Iseke; Stefan P Haider; Mario Strazzabosco; Julius Chapiro; John A Onofrey Journal: PLoS One Date: 2021-12-01 Impact factor: 3.240
Authors: Carolina Río Bártulos; Karin Senk; Mona Schumacher; Jan Plath; Nico Kaiser; Ragnar Bade; Jan Woetzel; Philipp Wiggermann Journal: Front Med (Lausanne) Date: 2022-04-06