Development of a deep learning-based auto-segmentation algorithm for hepatocellular carcinoma (HCC) and application to predict microvascular invasion of HCC using CT texture analysis: preliminary results

Abstract

Background Automatic segmentation has recently been developed to yield objective data. Prediction of microvascular invasion (MVI) of hepatocellular carcinoma (HCC) using radiomics has been reported. Purpose To develop a deep learning-based auto-segmentation algorithm (DL-AS) for the detection of HCC and to predict MVI using computed tomography (CT) texture analysis. Material and Methods We retrospectively collected training data from 249 patients with HCC and validation set from 35 patients. Lesions of the training set were manually drawn by radiologist, in the delayed phase. 2D U-Net was selected as the DL architecture. Using the validation set, one radiologist manually drew 2D and 3D regions of interest twice, and the developed DL-AS was performed twice with a one-month time interval. The reproducibility was calculated using intraclass correlation coefficients (ICC). Logistic regression was performed to predict MVI. Results ICC was in the range of 0.190–0.998/0.341–0.997 in the manual 3D/2D segmentation. In contrast, it was perfect in 3D/2D using DL-AS, with a success rate of 88.6% for the detection of HCC. For predicting MVI, sphericity was a significant parameter (odds ratio <0.001; 95% confidence interval <0.001–0.206; P = 0.020) for predicting MVI using 2D DL-AS. However, 3D DL-AS segmentation did not yield a predictive parameter. Conclusion The auto-segmentation of HCC using DL-AS provides perfect reproducibility, although it failed to detect 11.4% (4/35). However, the extracted parameters yielded different important predictors of MVI in HCC. Sphericity was a significant predictor in 2D DL-AS and 3D manual segmentation, while discrete compactness was a significant predictor in 2D manual segmentation.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

“…Common automatic segmentation algorithms include fully convolutional network, U-Net, Seg-Net, DeepLab, and their variations [ 40 – 44 ]. Previous studies have shown that such algorithms could generate a satisfactory performance with a Dice coefficient larger than 0.9 for organ segmentation [ 45 , 46 ], while their performance should be further improved for segmenting tumor regions, especially for DSNs [ 47 , 48 ]. In contrast, deep learning analysis of medical images only needs a coarse segmentation of tumor region, such as a bounding box including the whole tumor region, which is easy to achieve and feasible to use in clinical practice.…”