Authors
Ran Wei, Hanyu Jiang, Mengxuan Zuo, Xuelei He, Fei Cao, Bin Song, Shaolong Li, Wang Li, Wendao Liu, Chengzhi Li, Xin Li, Jianjun Han, Yan Fu, Dong Yan, Weiling He, Feng Duan, Xinya Zhao, Chao An
Published in
NPJ precision oncology. Jul 11, 2026. Epub Jul 11, 2026.
Abstract
The macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC) is associated with aggressive biology and poor prognosis. We aimed to develop a CT-based artificial intelligence model (DeepCT-MTM) for the noninvasive prediction of MTM-HCC and investigate its prognostic utilities as well as biological underpinnings. A total of 3118 patients with HCC were included from 20 tertiary-care hospitals. DeepCT-MTM was developed and validated among 832 patients with early-stage HCC undergoing resection (the resection set) and extrapolated to 2286 patients (including 480 prospectively-collected ones) with intermediate/advanced-stage HCC receiving IATs. DeepCT-MTM's predictive performance for MTM-HCC was evaluated using the area under the receiver operating characteristic curve (AUC), and its prognostic values were investigated for progression-free survival (PFS) and overall survival (OS). In the external test cohort of the resection set, DeepCT-MTM predicted MTM-HCC with an AUC of 0.845. The DeepCT-MTM-predicted high-risk group had worse PFS and OS across all IAT sets (all P < 0.05).. DeepCT-MTM is effective for noninvasively predicting MTM-HCC and may help selecting patients who benefit from a combination of IAT with immunotherapy and anti-angiogenic therapy. However, prospective validations are warranted for these hypothesis-generating findings.
PMID:
42436235
Bibliographic data and abstract were imported from PubMed on 12 Jul 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 11
- Comments 0