TRACE Model: Predicting Treatment Response to Transarterial Chemoembolization in Unresectable Hepatocellular Carcinoma.

PURPOSE

To develop and validate a predictive model for predicting six-month outcome by integrating pretreatment MRI features and one-month treatment response after TACE.

METHODS

A total of 108 patients with 160 hCCs from a single-arm, multicenter clinical trial (NCT03113955) were analyzed and served as the training cohort. An external multicenter dataset (ChiCTR2100046020) consisting of 63 patients with 99 hCCs served as the test dataset. Radiomics model was constructed based on the selected features from pretreatment MR images. Univariate and multivariate logistic regression analysis of clinical and radiological factors were used to identify the independent predictors for the 6-month treatment response. A combined model was further constructed by incorporating one-month treatment response, selected clinical and radiological factors and radiomics signature.

RESULTS

Among all the clinical and radiological features, only corona enhancement and one-month treatment response were selected. The combined model, named TRACE model (Treatment response at 1 month, RAdiomics and Corona Enhancement), with AUCs of 0.91 (training cohort) and 0.84 (test cohort). The TRACE model demonstrated a significantly higher AUC than the radiomics model ( = 0.001). High-risk and low-risk groups stratified by using the TRACE model also exhibited significant differences in overall survival (OS) ( < 0.001). In contrast, none of the published scoring systems, including ART, SNACOR or ABCR score, demonstrated significant differences between the risk groups in OS prediction.

CONCLUSION

The TRACE model exhibited favorable predictive capability for six-month TACE response, and holds potential as a marker for long-term survival outcomes.