Development and Evaluation of Ultrasound Image Learning Pipelines for MASLD Risk Stratification

SummaryAI generated

On September 7, 2026, arXiv cs.CV published a study on the development and evaluation of an ultrasound image learning pipeline for the stratification of risk in metabolic-related fatty liver disease (MASLD). This work aims to utilize deep learning techniques to process ultrasound image data, thereby enabling more accurate stratification and assessment of MASLD risk.

Related eventsRELATED EVENTS

2026-09-09 05:29OpenAI claims huge maths breakthrough on a famed ‘Millennium Problem’
2026-09-09 06:11OpenAI claims to have solved the Navier-Stokes equation problem, but its originality is questioned by the academic community
2026-09-08 22:00Google DeepMind Maps 9 Billion Possible DNA Variants

Key entitiesKEY ENTITIES

arXiv

SignalsSIGNALS

Keyword heat

arXiv1

All reports (1)SOURCES

↗

A arXiv cs.CV en 2026-09-07 12:00

本研究开发了用于代谢功能障碍相关脂肪性肝病（MASLD）风险分层的超声图像学习流程，并评估了其在纤维化分期及高危代谢功能障碍相关脂肪性肝炎（MASH）患者识别中的应用。研究纳入 250 例超声检查数据，采用三折交叉验证评估模型性能。结果显示，端到端的剪切波弹性成像（SWE）图像学习在纤维化分期中的表现与人工引导的 SWE 相当；总体而言，基于 SWE 的学习优于 B 模图像学习，其在 F≥2、F≥3 及 F4 阶段的 AUROC 分别提升至 0.72、0.78 和 0.80。