Skip to content
NewA calmer, faster ZeroHour

VCRE-Fib: View-Conditioned Regional Evidence for Fine-Grained Ultrasound Grading of Schistosoma japonicum-Associated Liver Fibrosis

arXiv cs.AI / cs.LG / cs.CLby Ziyang Xu ()1 min read
AI summary · grok-4.7Summaries by Vani AI

VCRE-Fib improves ultrasound grading of schistosomiasis liver fibrosis using view-conditioned regional evidence.

VCRE-Fib is a view-conditioned regional evidence model for fine-grained ultrasound grading of Schistosoma japonicum-associated liver fibrosis. It builds local grading evidence before spatial pooling, uses weak localization to aggregate it, and combines that with a global prediction, also returning view and a candidate abnormal-region map. On 108,709 images from 6,373 patients across 35 centers, a four-center test of 4,107 images from 240 patients showed a 7.115% lower composite grading risk than SFibAI and MAE of 0.378 versus 0.391.

Key facts
  • Cohort of 108,709 ultrasound images from 6,373 patients at 35 centers
  • Patient-disjoint test: 4,107 images from 240 patients at four centers
  • Composite grading risk fell 7.115% versus SFibAI on the same split
  • Image-level MAE improved from 0.391 to 0.378
  • View conditioning and weak localization both reduced grading risk
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Accurate assessment of Schistosoma japonicum-associated liver fibrosis is essential for disease management and long-term follow-up in endemic regions. Ultrasound provides non-invasive imaging, but complex local echogenic patterns and anatomical structures make fine-grained grading challenging.

arXiv cs.AI / cs.LG / cs.CL

By Ziyang Xu · arxiv.org

Read the full article at arXiv cs.AI / cs.LG / cs.CL

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.