AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Unified Mixture-of-Experts Framework for Joint Cardiac and Vascular Ultrasound Analysis and Report Generation

Bin Pu, Jiewen Yang, Xingguo Lv, Kai Xu, Kenli Li

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
joint cardiac and vascular training instead of cardiac only (ablation)ECV · CVU parameter measurementRMSE: 42.30 -> 12.43Improved
joint cardiac and vascular training instead of cardiac only (ablation)ECV · CVU parameter measurementMAE: 6.15 -> 5.72Improved
add cardiac data to vascular-only training (ablation)ECV · CVU parameter measurementMAE: 6.89 -> 5.72Improved
add vascular data to cardiac-only training for vascular reports (ablation)ECV · CVU vascular report generationBertScore: 78.64 -> 81.98Improved
fine-tune vision encoder together with LLM decoder instead of decoder only (ablation)ECV · CVU parameter measurementMAE: 7.48 -> 5.72Improved
fine-tune LLM decoder together with vision encoder instead of encoder only (ablation)ECV · CVU cardiac report generationBertScore: 78.05 -> 87.37Improved
train jointly on measurement and report generation instead of parameter-only (ablation)ECV · CVU cardiac report generationBertScore: 63.67 -> 87.37Improved
train jointly instead of parameter-only (ablation)ECV · CVU parameter measurementMAE: 6.01 -> 5.72Improved
train jointly instead of report-only on cardiac reports (ablation)ECV · CVU cardiac report generationBertScore: 88.43 -> 87.37No clear effect
train jointly instead of report-only on vascular reports (ablation)ECV · CVU vascular report generationBLEU-1: 8.46 -> 24.58Improved
use ECV with MoE vision encoder and measurement module instead of HuaTuo-34BHuaTuo-34B · CVU parameter measurementMAE: 13.25 -> 5.72Improved
use ECV instead of HuaTuo-34B for cardiac report BLEU-4HuaTuo-34B · CVU cardiac report generationBLEU-4: 13.05 -> 5.82Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy