Abstract
BACKGROUND: To develop and validate an overall survival (OS) prediction model for transarterial chemoembolization (TACE). METHODS: In this retrospective study, 301 patients with hepatocellular carcinoma (HCC) who received TACE from 2012 to 2015 were collected. The residual network was used to extract prognostic information from CT images, which was then combined with the clinical factors adjusted by COX regression to predict survival using a modified deep learning model (DLOP(Combin)). The DLOP(Combin) model was compared with the residual network model (DLOP(CTR)), multiple COX regression model (DLOP(Cox)), Radiomic model (Radiomic), and clinical model. RESULTS: In the validation cohort, DLOP(Combin) shows the highest TD AUC of all cohorts, which compared with Radiomic (TD AUC: 0.96vs 0.63) and clinical model (TD AUC: 0.96 vs 0.62) model. DLOP(Combin) showed significant difference in C index compared with DLOP(CTR) and DLOP(Cox) models (P < 0.05). Moreover, the DLOP(Combin) showed good calibration and overall net benefit. Patients with DLOP(Combin) model score ≤ 0.902 had better OS (33 months vs 15.5 months, P < 0.0001). CONCLUSION: The deep learning model can effectively predict the patients' overall survival of TACE.