What question did this study set out to answer?

To develop a non-invasive imaging biomarker for predicting progression-free survival in hepatocellular carcinoma patients treated with immunotherapy and targeted therapy.

February 22, 2026Academic Radiology

Multiparametric MRI-Based Deep Learning and Radiomics for Predicting Progression-Free Survival Benefit in Patients with Hepatocellular Carcinoma Treated with Immunotherapy and Targeted Therapy Plus Transarterial Chemoembolization: A Bicentric Study

View Full Paper

Ask AI

Bookmark

Authors

WKWendi KangCentral South University YLYingen LuoChinese Academy of Medical Sciences & Peking Union Medical College XZXuan ZhouCentral South University

Discussion

Member takes

Implication

This bicentric study demonstrates improved progression-free survival prediction in hepatocellular carcinoma patients using deep learning and immunotherapy.

Key Points

To develop a non-invasive imaging biomarker for predicting progression-free survival in hepatocellular carcinoma patients treated with immunotherapy and targeted therapy.
Included 180 patients with hepatocellular carcinoma treated with immunotherapy and targeted therapy plus transarterial chemoembolization at two centers.
Extracted radiomic features from six multiparametric MRI sequences using deep learning based on the ResNet50 algorithm.
Developed a Cox regression combined model integrating clinical, radiomic, and deep learning features.
The CRAFITY score was identified as an independent predictor of progression-free survival (P < 0.05).
C-index values for the deep learning model were 0.757, 0.751, and 0.744 across cohorts.
Combined model C-index values were 0.803, 0.746, and 0.744 respectively, achieving AUC values of up to 0.934.

Cite This Study

Kang et al. (2026) studied this question.

synapsesocial.com/papers/699a534bfdaf4e3c1268ef0d https://doi.org/10.1016/j.acra.2026.01.059

View Full Paper

Ask AI

Bookmark

Implication

This bicentric study demonstrates improved progression-free survival prediction in hepatocellular carcinoma patients using deep learning and immunotherapy.

Multiparametric MRI-Based Deep Learning and Radiomics for Predicting Progression-Free Survival Benefit in Patients with Hepatocellular Carcinoma Treated with Immunotherapy and Targeted Therapy Plus Transarterial Chemoembolization: A Bicentric Study

Discussion

Member takes

Implication

Key Points

Cite This Study

Multiparametric MRI-Based Deep Learning and Radiomics for Predicting Progression-Free Survival Benefit in Patients with Hepatocellular Carcinoma Treated with Immunotherapy and Targeted Therapy Plus Transarterial Chemoembolization: A Bicentric Study

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider