arXiv cs.AI· Yuchen Yang, Xin Wang, Lufan Wang, Yinghong Pan, Yujuan Feng, Yuqing Yang·· 9 天前AI 评分22
CAMEO：面向超声报告生成的临床感知多图像证据框架
Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence
AI 导读
CAMEO 是一个临床感知的多图像证据编排框架，用于从超声图像生成报告，通过三阶段流程学习视觉语言基元、跨视图证据接地和临床感知偏好对齐。
正文 · 原文
Abstract:Generating ultrasound reports from multiple images requires aggregating clinical evidence across views, yet archived key frames capture only part of the dynamic examination. Raw-report imitation is therefore misaligned with visual supervision: content that is clinically valid for the full examination may be unverifiable from the images available to a model. This gap creates a clinical behavior alignment problem. A model must preserve visible findings, avoid diagnostic reversals and unsupported completion, and not collapse into conservative templates. We propose CAMEO, a Clinically Aware Multi-image Evidence-grounded Orchestration framework for ultrasound report generation. Stage I learns ultrasound visual-language primitives; Stage II performs Cross-View Evidence Grounding by distilling trusted visible report points into multi-image QA and report-style supervision; and Stage III performs Clinically Aware Preference Alignment using clinical-error-oriented preference pairs. From USReport, we construct USReport-Distilled with 17,670 evidence-grounded paired-image training instances and USReport-Pref with 21,869 preference pairs; we additionally use 25,631 PubMedVision-US ultrasound instruction samples for domain adaptation and multi-image instruction tuning. On the primary USReport-Distilled benchmark, CAMEO improves over EchoVLM from 0.25 to 0.40 BLEU-1, 0.28 to 0.45 ROUGE-1, and 0.27 to 0.43 METEOR, while raising ClinicalScore from 55.02 to 74.20. These results underscore the value of evidence-grounded supervision, clinically aware alignment, and clinically structured evaluation for reliable ultrasound report generation.
| Comments: | Accepted to BMVC 2026. Code: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.10; I.2.7 |
| Cite as: | arXiv:2610.11610 [cs.CV] |
| (or arXiv:2610.11610v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11610 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yang Yuchen [view email]
[v1]
Thu, 8 Oct 2026 09:53:46 UTC (5,391 KB)
来源：arXiv cs.AI · arxiv.org