EUVIMEDEUVIMED entdecken
Crossref

MARE: Multimodal Analogical Reasoning for Disease Evolution-Aware Radiology Report Generation

Qingqing Gao, Tengfei Liu, Xiaoyan Li, Xiaodan Zhang, Zhongfan Sun, Boyue Wang, Baocai Yin, Zhaohui Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 21180-21188

DOI: 10.1609/aaai.v40i25.39262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Qingqing Gao und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radiology report generation from longitudinal medical data is critical for assessing disease progression and automating diagnostic workflows. While recent methods incorporate longitudinal information, they primarily rely on multimodal feature fusion, with limited capacity for explicit disease evolution modeling and temporal reasoning. To address this, we propose MARE, an end-to-end framework that formulates longitudinal radiology report generation as a multimodal analogical reasoning task. Inspired by the Abduction–Mapping–Induction paradigm, MARE models latent relational structures underlying disease evolution by aligning lesion-level visual features across time and mapping them to the textual domain for temporally coherent and clinically meaningful report generation. To mitigate the spatial misalignment caused by patient positioning or imaging variation, we introduce an Adaptive Region Alignment (ARA) module for robust temporal correspondence. Additionally, we design Dual Evolution Consistency (DEC) losses to regularize analogical reasoning by enforcing temporal coherence in both visual and textual evolution paths. Extensive experiments on the Longitudinal-MIMIC dataset demonstrate that MARE significantly outperforms state-of-the-art baselines across both natural language generation and clinical effectiveness metrics, highlighting the value of structured analogical reasoning for disease evolution-aware report generation.

Zitieren

APA

Gao, Q., Liu, T., Li, X., Zhang, X., Sun, Z., Wang, B., Yin, B., & Liu, Z. (2026). MARE: Multimodal Analogical Reasoning for Disease Evolution-Aware Radiology Report Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 21180-21188. https://doi.org/10.1609/aaai.v40i25.39262

Vancouver

Gao Q, Liu T, Li X, Zhang X, Sun Z, Wang B, et al. MARE: Multimodal Analogical Reasoning for Disease Evolution-Aware Radiology Report Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):21180-21188. doi:10.1609/aaai.v40i25.39262

BibTeX
@article{Gao2026,
  author = {Gao, Qingqing and Liu, Tengfei and Li, Xiaoyan and Zhang, Xiaodan and Sun, Zhongfan and Wang, Boyue and Yin, Baocai and Liu, Zhaohui},
  title = {MARE: Multimodal Analogical Reasoning for Disease Evolution-Aware Radiology Report Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {25},
  pages = {21180--21188},
  doi = {10.1609/aaai.v40i25.39262}
}
Kostenlos starten →