CT images-based 3D convolutional neural network to predict early recurrence of solitary hepatocellular carcinoma after radical hepatectomy

Abstract

PURPOSE The high rate of recurrence of hepatocellular carcinoma (HCC) after radical hepatectomy is an important factor that affects the long-term survival of patients. This study aimed to develop a computed tomography (CT) images-based 3-dimensional (3D) convolutional neural network (CNN) for the preoperative prediction of early recurrence (ER) (≤2 years) after radical hepatectomy in patients with solitary HCC and to compare the effects of segmentation sampling (SS) and non-segmentation sampling (NSS) on the prediction performance of 3D-CNN. METHODS Contrast-enhanced CT images of 220 HCC patients were used in this study (training group = 178 and test group = 42). We used SS and NSS to select the volume-of-interest to train SS-3D-CNN and NSS-3D-CNN separately. The prediction accuracy was evaluated using the test group. Finally, gradient-weighted class activation mappings (Grad-CAMs) were plotted to analyze the difference of prediction logic between the SS-3D-CNN and NSS-3D-CNN. RESULTS The areas under the receiver operating characteristic curves (AUCs) of the SS-3D-CNN and NSS-3D-CNN in the training group were 0.824 (95% CI: 0.764-0.885) and 0.868 (95% CI: 0.815-0.921). The AUC of the SS-3D-CNN and NSS-3D-CNN in the test group were 0.789 (95% CI: 0.637-0.941) and 0.560 (95% CI: 0.378-0.742). The SS-3D-CNN could stratify patients into low- and high-risk groups, with significant differences in recurrence-free survival (RFS) ( P < .001). But NSS-3D-CNN could not effectively stratify them in the test group. According to the Grad-CAMs, compared with SS-3D-CNN, NSS-3D-CNN was obviously interfered by the nearby tissues. CONCLUSION SS-3D-CNN may be of clinical use for identifying high-risk patients and formulating individualized treatment and follow-up strategies. SS is better than NSS in improving the performance of 3D-CNN in our study.

Real-Time Recognition Method for Key Signals of Rock Fracture Acoustic Emissions Based on Deep Learning

“…CNN has exhibited exceptional accuracy in image classification tasks and has achieved significant success in diverse application domains [33][34][35][36][37]. Consequently, the thorough investigation of employing efficient CNN models for the classification and recognition of 2D feature maps, such as Mel power spectrograms, STFT spectrograms, and wavelet spectrograms of acoustic emission signals, holds considerable research value.…”