Abstract

Clinical diagnosis relies on consistent multimodal data collected from the same patient throughout the disease course, yet such data are difficult to acquire at scale because of collection costs, missing modalities, fragmented systems, and privacy risks. Existing synthetic-data approaches largely focus on individual modalities or vision-language report-level outputs and cannot readily construct virtual cases with consistent patient backgrounds, coherent trajectories, and interrelated modality-specific evidence. We introduce CaseWeaver, a multi-agent framework built around a timeline-anchored Latent Clinical Case Graph (LCCG). The LCCG organizes patient context, latent disease states, clinical events, and expected observations in a shared patient-level representation. Modality agents use scoped observation subgraphs and clinical protocols to generate evidence including clinical records, laboratory results, physiological signals, and medical images. We evaluate clinical inferability using a calibrated AgentClinic protocol and case diversity using Virtual Case Diversity (VCD) score. CaseWeaver outperformed general-model and agentic-workflow baselines on both evaluations, with more diverse and coherent multimodal virtual cases.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MedAgent_032.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: https://openreview.net/forum?id=zybXTf8wkU

BibTex

@InProceedings{QuJie_CaseWeaver_MICCAISAT2026,
        author = { Qu, Jierui AND Peng, Jiachuan AND Li, Lin AND Lam, Kyle AND Qiu, Jianing},
        title = { { CaseWeaver: A Multi-Agent Framework for Multimodal Virtual Clinical Case Generation } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17263},
        month = {pending},
        page = {pending}
}


back to top