AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

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

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MARE, an end-to-end framework that formulates longitudinal radiology report generation as multimodal analogical reasoning to model disease evolution.

Problem

Radiology report generation from longitudinal medical data needs explicit disease evolution modeling and temporal reasoning, but existing methods mainly rely on multimodal feature fusion.

Approach

Formulates longitudinal report generation as multimodal analogical reasoning so the model explicitly reasons about how disease evolves across time, rather than only fusing features from multiple timepoints.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Adaptive Region Alignment (ARA) (ablation)MARE · Longitudinal-MIMIC testCIDEr: 0.243 -> 0.271Improved
add Adaptive Region Alignment (ARA) (ablation)MARE · Longitudinal-MIMIC testF-1: 0.353 -> 0.375Improved
add Adaptive Region Alignment (ARA) (ablation)MARE · Longitudinal-MIMIC testBLEU-4: 0.129 -> 0.133Improved
add both DEC losses (ablation)MARE · Longitudinal-MIMIC testF-1: 0.330 -> 0.375Improved
add image-evolution consistency loss alone (ablation)MARE · Longitudinal-MIMIC testF-1: 0.330 -> 0.362Improved
add report-evolution consistency loss alone (ablation)MARE · Longitudinal-MIMIC testF-1: 0.330 -> 0.345Improved
add report-evolution loss on top of image-evolution loss (ablation)MARE · Longitudinal-MIMIC testCIDEr: 0.265 -> 0.271Improved
add both DEC losses (ablation)MARE · Longitudinal-MIMIC testCIDEr: 0.251 -> 0.271Improved
increase ARA learnable queries from 16 to 32 (ablation)MARE · Longitudinal-MIMIC testCIDErImproved
increase ARA learnable queries beyond 32 (ablation)MARE · Longitudinal-MIMIC testCIDErHurt
add historical report Yp as inputR2GenGPT · Longitudinal-MIMIC testF-1: 0.247 -> 0.336Improved
add historical image Xp as inputR2GenGPT · Longitudinal-MIMIC testF-1: 0.247 -> 0.250No clear effect

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