Computer-aided hepatocellular carcinoma detection on the hepatobiliary phase of gadoxetic acid-enhanced magnetic resonance imaging using a convolutional neural network: Feasibility evaluation with multi-sequence data. (October 2022)

• Record Type: Journal Article
• Authors: Cho, Yongwon; Han, Yeo Eun; Kim, Min Ju; Park, Beom Jin; Sim, Ki Choon; Sung, Deuk Jae; Han, Na Yeon; Park, Yang Shin
• Is Part Of: Computer methods and programs in biomedicine. Volume 225(2022)
• Publication Date: 2022-10
• Subjects: Abdominal Image Analysis -- Computer-Aided Diagnosis -- Deep Learning -- Hepatocellular Carcinoma -- Magnetic Resonance Imaging; HCC hepatocellular carcinoma -- CT computed tomography -- MRI magnetic resonance imaging -- T2WI T2-weighted imaging -- T1WI T1-weighted imaging -- HBP hepatobiliary phase -- PVP portal venous phase -- CAD computer-aided detection -- CNN convolutional neural network -- ROI region of interest -- FROC free-response receiver operating characteristic -- FP false-positive -- FOM figure of merit -- JAFROC jackknife alternative free-response receiver operating characteristic -- KUAH Korea University Anam Hospital -- KUGH Korea University Guro Hospital -- DSC dice similarity coefficient -- DLS dice loss -- BLS boundary loss; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107032
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We developed computer-aided detection (CAD) for hepatocellular carcinoma (HCC) on the hepatobiliary phase (HBP) of gadoxetic acid-enhanced magnetic resonance imaging (MRI) using a convolutional neural network. We evaluated its feasibility on multi-sequence, multi-unit, and multi-center data. Internal and external validation of the CAD was performed with HBP, T1-weighted imaging, T2-weighted imaging, and portal venous phase. The CAD developed using single MRI sequence (HBP) may be applied to other similar sequences. This results will reduce labor and time for CAD development in multi-sequence MRI. ABSTRACT: Background and Objectives: Diagnosis of hepatocellular carcinoma (HCC) on liver MRI needs analysis of multi-sequence images. However, developing computer-aided detection (CAD) for every single sequence requires considerable time and labor for image segmentation. Therefore, we developed CAD for HCC on the hepatobiliary phase (HBP) of gadoxetic acid-enhanced magnetic resonance imaging (MRI) using a convolutional neural network (CNN) and evaluated its feasibility on multi-sequence, multi-unit, and multi-center data. Methods: Patients who underwent gadoxetic acid-enhanced MRI and surgery for HCC in Korea University Anam Hospital (KUAH) and Korea University Guro Hospital (KUGH) were reviewed. Finally, 170 nodules from 155 consecutive patients from KUAH and 28 nodules from 28 patients randomly selected from KUGH were included. Regions of interests were drawn on the whole HCC volume on HBP, T1-weighted (T1WI), T2-weighted (T2WI), and portal venous phase (PVP) images. The CAD was developed from the HBP images of KUAH using customized-nnUNet and post-processed for false-positive reduction. Internal and external validation of the CAD was performed with HBP, T1WI, T2WI, and PVP of KUAH and KUGH. Results: The figure of merit and recall of the jackknife alternative free-response receiver operating characteristic of the CAD for HBP, T1WI, T2WI, and PVP at false-positive rate 0.5 were (0.87 and 87.0), (0.73 and 73.3), (0.13 and 13.3), and (0.67 and 66.7) in KUAH and (0.86 and 86.0), (0.61 and 53.6), (0.07 and 0.07), and (0.57 and 53.6) in KUGH, respectively. Conclusions: The CAD for HCC on gadoxetic acid-enhanced MRI developed by CNN from HBP detected HCCs feasibly on HBP, T1WI, and PVP of gadoxetic acid-enhanced MRI obtained from multiple units and centers. This result imply that the CAD developed using single MRI sequence may be applied to other similar sequences and this will reduce labor and time for CAD development in multi-sequence MRI.