Ultrasound report generation improves by aligning with visible clinical evidence
Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Making accurate ultrasound reports from several images is tricky because the images only show part of the full exam. The authors identify a problem where reports copied from raw data don’t always match what the images prove. They created a new method called CAMEO that learns key clinical details, cross-checks information across images, and prefers medically correct phrasing. Their approach improved multiple accuracy scores for ultrasound report generation, showing it can produce more reliable and clinically sensible reports.
What this means in practice
- •For medical ai developers: Create ultrasound report tools that generate more clinically accurate and evidence-based summaries from multiple ultrasound images.
- •For radiology workflow teams: Integrate automated report generation that aligns better with visible ultrasound findings to support radiologists and reduce misreporting.
Authors
Yuchen Yang, Xin Wang, Lufan Wang, Yinghong Pan, Yujuan Feng, Yuqing Yang
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.