November 18, 2026 · Abdominal radiology (New York) · DOI: 10.1007/s00261-026-05880-9

Integrated radiomics-deep learning modeling of hepatic vasculature for enhanced noninvasive prediction of portal hypertension and high-risk gastroesophageal varices.

Listen to this summary

This study asks whether CT-derived radiomics and deep learning features extracted from multiple major hepatic vessels can noninvasively improve identification of clinically significant portal hypertension (CSPH) and high-risk gastroesophageal varices (HRVs) in cirrhotic patients. The authors built a dual-path model combining both feature types across several hepatic vessels, which achieved an AUC of 0.892 for CSPH and 0.790 and 0.782 for HRVs in internal and external test sets, outperforming single-path, single-vessel, vascular geometry, and clinical (including APRI-based) models. These results suggest that integrated multi-vessel imaging features may offer a promising noninvasive alternative for risk stratification of portal hypertension complications.

Qixuan Qiu, Rencheng Zheng, Chenyan Wang, He Wang, Jiang Lin

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play