Improving risk stratification and detection of early HCC using ultrasound-based deep learning models

作者：Jérémy Dana, Adrien Meyer, Anita Paisant, Agnès Rode, Riccardo Sartoris, Olivier Séror, Christophe Cassinotto, Laurent Milot, Jules Grégory, Jules Cœur, J. Lebigot, Valentina Schembri, François Villeret, Armelle-Natsuo Takeda, Maxime Ronot, Valérie Vilgrain, Thomas F. Baumert, B. Gallix, Nicolas Padoy, Pierre Nahon · 发表于：JHEP Reports · 年份：2025 · DOI：10.1016/j.jhepr.2025.101510 · 被引用次数：3 · 研究领域：Hepatocellular Carcinoma Treatment and Prognosis、Liver Disease Diagnosis and Treatment、Organ Transplantation Techniques and Outcomes

Background & Aims: Hepatocellular carcinoma (HCC) surveillance programs are suboptimal. We aimed to design an ultrasound-based deep learning model for HCC risk stratification (STARHE-RISK) and early-stage HCC detection (STARHE-DETECT) in patients with compensated advanced chronic liver disease (cACLD). Methods: This prospective multicentric study included 403 adult patients with cACLD of all causes enrolled in a surveillance program for at least 6 months without prior history of HCC. STARHE-RISK was trained on ultrasound cine clips of the non-tumoral liver parenchyma using two classes: cases (n = 152 patients with early-stage HCC; 137/152 [82%] male; median age 63 years) and controls (n = 170 patients without HCC at inclusion and during a subsequent 1-year follow-up; 120/170 [71%] male; median age 69 years). STARHE-DETECT was trained on tumour ultrasound cine clips. The training/validation and testing sets were stratified according to potential confounders, and 50 patients who were balanced in both groups were allocated to the independent testing set based on sample size calculation. Statistical analysis included classification and detection metrics. Results: = 0.004]) for predicting a patient at high risk of HCC development. STARHE-DETECT achieved a 0.67 mAP10, a 0.68 sensitivity (95% CI 0.47-0.85), and a 0.82 specificity (95% CI 0.69-0.91) for detecting early-stage HCC. Conclusions: STARHE-RISK and STARHE-DETECT achieved robust performances for HCC risk stratification and e...