EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography

• URL: http://arxiv.org/abs/2606.28164v1
• Date: Fri, 26 Jun 2026 14:58:45 GMT
• Title: EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography
• Abstract summary: We present EchoSonar-R, a multi-view reasoning-enabled vision-enabled model that jointly performs disease classification and report generation.<n>EchoSonar-R is trained in two stages: supervised fine-language encoder (SFT) on reasoning-annotated targets, followed by Group Relative Policy Optimization (O) with task-specific rewards.<n>EchoSonar-R improves macro balanced accuracy by 17.1% on the private set and 6.1% on MIMICQA over the strongest baseline.
• Score: 4.445909648625997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis. Interpreting an echocardiogram requires synthesizing complementary evidence across multiple heart views to identify abnormalities and produce structured clinical reports. While recent efforts focus on improving classification performance, most models lack explicit diagnostic reasoning and spatially grounded anatomical evidence, limiting clinician trust. We present EchoSonar-R, a multi-view reasoning-enabled vision-language model that jointly performs multi-label disease classification and report generation from echocardiography studies. EchoSonar-R combines a spatiotemporal video encoder with a structure-aware cardiac detector that provides spatially grounded anatomical cues to improve interpretability and clinician trust during cross-view reasoning. EchoSonar-R is trained in two stages: supervised fine-tuning (SFT) on reasoning-annotated targets, followed by Group Relative Policy Optimization (GRPO) with task-specific rewards that jointly align classification and report generation within a unified reinforcement-learning framework. Across a private multi-view dataset and two public benchmarks, EchoSonar-R improves macro balanced accuracy by 17.1% on the private set and 6.1% on MIMICEchoQA over the strongest baseline, achieves a GREEN clinical faithfulness score of 0.800, and produces interpretable reasoning traces grounded in multi-view visual evidence.

Related papers

• ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction [27.661246388005384]
  We propose ClinRAG-GRAPH, a framework for pre-treatment pathological complete response (pCR) prediction.<n>ClinRAG-GRAPH constructs an intra-patient clinical-prior graph and applies a prior-guided relation-aware graph convolutional network for structured multimodal representation learning.<n>ClinRAG-GRAPH achieves AUCs of 0.815 on the internal test set and 0.774/0.712 on two external test sets, demonstrating robust pre-treatment pCR prediction across centers.
  arXiv  Detail & Related papers  (2026-07-01T11:28:01Z)
• Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation [76.6507710204181]
  We present Echo-, an agentic multimodal reasoning model for ultrasound interpretation.<n> Echo- is trained to coordinate organ-specific detector outputs, integrate them with global visual context, and convert the resulting evidence into grounded diagnostic decisions.<n>Results suggest that agentic multimodal reasoning can turn specialized detectors into verifiable clinical evidence.
  arXiv  Detail & Related papers  (2026-04-30T15:31:00Z)
• Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents [25.763431177629638]
  Visual language models (VLM) have opened a new avenue for building ultrasound understanding systems for clinical decision support.<n>We propose EchoTrust, an evidence-driven Actor-Verifier framework for trustworthy reasoning in echocardiography VLM-based agents.
  arXiv  Detail & Related papers  (2026-04-07T18:26:46Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• Multi-View Stenosis Classification Leveraging Transformer-Based Multiple-Instance Learning Using Real-World Clinical Data [76.89269238957593]
  Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views.<n>We propose SegmentMIL, a transformer-based multi-view multiple-instance learning framework for patient-level stenosis classification.
  arXiv  Detail & Related papers  (2026-02-02T13:07:52Z)
• Echo-CoPilot: A Multi-View, Multi-Task Agent for Echocardiography Interpretation and Reporting [8.162197738994479]
  We introduce Echo-CoPilot, a multi-view, multi-task agent that uses a large language model to orchestrate specialized echocardiography tools.<n>Within a ReAct-style loop, the agent decomposes clinician queries, invokes tools for view recognition, cardiac structure segmentation, measurement and disease prediction, and report synthesis.<n>We evaluate Echo-CoPilot on the public MIMIC-EchoQA benchmark, where it achieves an accuracy of 50.8%, outperforming both general-purpose and biomedical video vision-language models.
  arXiv  Detail & Related papers  (2025-12-06T23:27:54Z)
• CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection [3.2889108396912974]
  Chagas disease affects nearly 6 million people worldwide, with Chagas cardiomyopathy representing its most severe complication.<n>In regions where serological testing capacity is limited, AI-enhanced electrocardiogram (ECG) screening provides a critical diagnostic alternative.<n>We propose a retrieval-augmented generation framework, CardioRAG, integrating large language models with interpretable ECG-based clinical features.
  arXiv  Detail & Related papers  (2025-10-02T01:02:04Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications [77.3888788549565]
  We present EchoCare, a novel ultrasound foundation model for generalist clinical use.<n>We developed EchoCare via self-supervised learning on our curated, publicly available, large-scale dataset EchoCareData.<n>With minimal training, EchoCare outperforms state-of-the-art comparison models across 10 representative ultrasound benchmarks.
  arXiv  Detail & Related papers  (2025-09-15T10:05:31Z)
• EchoApex: A General-Purpose Vision Foundation Model for Echocardiography [9.202542805578432]
  We introduce EchoApex, the first general-purpose vision foundation model echocardiography with applications on a variety of clinical practice. Leveraging self-supervised learning, EchoApex is pretrained on over 20 million echo images from 11 clinical centres. Compared to state-of-the-art task-specific models, EchoApex attains improved performance with a unified image encoding architecture.
  arXiv  Detail & Related papers  (2024-10-14T21:10:56Z)
• Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation [70.7778938191405]
  We propose a novel factored attention and embedding model (termed FAE-Gen) for the unstructured-view topic-related ultrasound report generation. The proposed FAE-Gen mainly consists of two modules, i.e., view-guided factored attention and topic-oriented factored embedding, which capture the homogeneous and heterogeneous morphological characteristic across different views.
  arXiv  Detail & Related papers  (2022-03-12T15:24:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.