A deep learning model for personalized intra-arterial therapy planning in unresectable hepatocellular carcinoma: a multicenter retrospective study

Background Unresectable Hepatocellular Carcinoma (uHCC) poses a substantial global health challenge, demanding innovative prognostic and therapeutic planning tools for improved patient management. The predominant treatment strategies include Transarterial chemoembolization (TACE) and hepatic arterial infusion chemotherapy (HAIC). Methods Between January 2014 and November 2021, a total of 1725 uHCC patients [mean age, 52.8 +/- 11.5 years; 1529 males] received preoperative CECT scans and were eligible for TACE or HAIC. Patients were assigned to one of the four cohorts according to their treatment, four transformer models (SELECTION) were trained and validated on each cohort; AUC was used to determine the prognostic performance of the trained models. Patients were stratified fi ed into high and low-risk groups based on the survival scores computed by SELECTION. The proposed AI-based treatment decision model (ATOM) utilizes survival scores to further inform fi nal therapeutic recommendation. Findings In this study, the training and validation sets included 1448 patients, with an additional 277 patients allocated to the external validation sets. The SELECTION model outperformed both clinical models and the ResNet approach in terms of AUC. Specifically, fi cally, SELECTION-TACE and SELECTION-HAIC achieved AUCs of 0.761 (95% CI, 0.693-0.820) - 0.820) and 0.805 (95% CI, 0.707-0.881) - 0.881) respectively, in predicting ORR in their external validation cohorts. In predicting OS, SELECTION-TC and SELECTION-HC demonstrated AUCs of 0.736 (95% CI, 0.608-0.841) - 0.841) and 0.748 (95% CI, 0.599-0.865) - 0.865) respectively, in their external validation sets. SELECTION-derived survival scores effectively stratified fi ed patients into high and low-risk groups, showing significant fi cant differences in survival probabilities (P < 0.05 across all four cohorts). Additionally, the concordance between ATOM and clinician recommendations was associated with significantly fi cantly higher response/survival rates in cases of agreement, particularly within the TACE, HAIC, and TC cohorts in the external validation sets (P < 0.05). Interpretation ATOM was proposed based on SELECTION-derived survival scores, emerges as a promising tool to inform the selection among different intra-arterial interventional therapy techniques.