Abstract
To evaluate the performance of a deep convolutional neural network (DCNN) in detecting local tumor progression (LTP) after tumor ablation for hepatocellular carcinoma (HCC) on follow-up arterial phase CT images. The DCNN model utilizes three-dimensional (3D) patches extracted from three-channel CT imaging to detect LTP. We built a pipeline to automatically produce a bounding box localization of pathological regions using a 3D-CNN trained for classification. The performance metrics of the 3D-CNN prediction were analyzed in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), area under the receiver operating characteristic curve (AUC), and average precision. We included 34 patients with 49 LTP lesions and randomly selected 40 patients without LTP. A total of 74 patients were randomly divided into three sets: training (n = 48; LTP: no LTP = 21:27), validation (n = 10; 5:5), and test (n = 16; 8:8). When used with the test set (160 LTP positive patches, 640 LTP negative patches), our proposed 3D-CNN classifier demonstrated an accuracy of 97.59%, sensitivity of 96.88%, specificity of 97.65%, and PPV of 91.18%. The AUC and precision–recall curves showed high average precision values of 0.992 and 0.96, respectively. LTP detection on follow-up CT images after tumor ablation for HCC using a DCNN demonstrated high accuracy and incorporated multichannel registration.
Highlights
Hepatocellular carcinoma (HCC) shows arterial enhancement and delayed washout on dynamic contrast-enhancement imaging studies, such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasonography (US)[1]
Among the 184 patients who underwent complete ablation for treatment-naïve single hepatocellular carcinoma (HCC), 26 patients were excluded from the analysis owing to intrasegmental aggressive recurrence, liver transplantation during the follow-up period, and unavailable follow-up CT images
Because the detection and interpretation of enhancing lesions on follow-up imaging studies are essential for diagnosing HCC recurrence, in the current study, we use artificial intelligence (AI) to focus on the detection of arterial enhancing lesions next to an ablation zone and distinguish them from local tumor progression (LTP) and other possible enhancing lesions, including normal vasculatures or arterioportal shunts
Summary
Hepatocellular carcinoma (HCC) shows arterial enhancement and delayed washout on dynamic contrast-enhancement imaging studies, such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasonography (US)[1]. This finding enables non-invasive diagnosis without biopsy and provides reliable and reproducible imaging data to diagnose and detect tumor recurrence during follow-ups after treatment[2]. Deep convolutional neural networks (DCNNs) are deep learning neural networks in which multiple hidden layers are trained to perform particular tasks[5]. They have been used successfully in medical fields including radiology[5,6]. Sex (male:female) Age (years) LTP size (cm) Time interval between ablation and CT (days) Time interval between ablation and last follow up (days) Etiology of liver disease HBV HCV Alcohol Others
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
