Multi-algorithms analysis for pre-treatment prediction of response to transarterial chemoembolization in hepatocellular carcinoma on multiphase MRI

• Published in: Insights into imaging Vol. 14; no. 1; pp. 38 - 12
• Main Authors: Chen, Mingzhen, Kong, Chunli, Qiao, Enqi, Chen, Yaning, Chen, Weiyue, Jiang, Xiaole, Fang, Shiji, Zhang, Dengke, Chen, Minjiang, Chen, Weiqian, Ji, Jiansong
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 28.02.2023; Springer Nature B.V; SpringerOpen
• Subjects: Algorithms; Artificial neural networks; Chemoembolization; Classifiers; Deep learning; Diagnostic Radiology; Hepatocellular carcinoma; Imaging; Internal Medicine; Interventional Radiology; Liver cancer; Machine learning; Medicine; Medicine & Public Health; Neuroradiology; Original; Original Article; Performance prediction; Pretreatment; Radiology; Radiomics; Support vector machines; Test sets; Training; Transarterial chemoembolization; Ultrasound; Deep learning; Hepatocellular carcinoma; Transarterial chemoembolization; Radiomics
• ISSN: 1869-4101; 1869-4101
• DOI: 10.1186/s13244-023-01380-2

Objectives This study compared the accuracy of predicting transarterial chemoembolization (TACE) outcomes for hepatocellular carcinoma (HCC) patients in the four different classifiers, and comprehensive models were constructed to improve predictive performance. Methods The subjects recruited for this study were HCC patients who had received TACE treatment from April 2016 to June 2021. All participants underwent enhanced MRI scans before and after intervention, and pertinent clinical information was collected. Registry data for the 144 patients were randomly assigned to training and test datasets. The robustness of the trained models was verified by another independent external validation set of 28 HCC patients. The following classifiers were employed in the radiomics experiment: machine learning classifiers k-nearest neighbor (KNN), support vector machine (SVM), the least absolute shrinkage and selection operator (Lasso), and deep learning classifier deep neural network (DNN). Results DNN and Lasso models were comparable in the training set, while DNN performed better in the test set and the external validation set. The CD model (Clinical & DNN merged model) achieved an AUC of 0.974 (95% CI: 0.951–0.998) in the training set, superior to other models whose AUCs varied from 0.637 to 0.943 ( p  < 0.05). The CD model generalized well on the test set (AUC = 0.831) and external validation set (AUC = 0.735). Conclusions DNN model performs better than other classifiers in predicting TACE response. Integrating with clinically significant factors, the CD model may be valuable in pre-treatment counseling of HCC patients who may benefit the most from TACE intervention. Key points DNN and LASSO models performed better than other classifiers in TACE response prediction. CD model achieved an AUC of 0.974 in the training set, superior to other comprehensive models. CD model may serve as a potential tool for the selection of suitable TACE candidates.