# Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization

Source: [Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization](<https://www.sota2.com/research/paper/69cca6a70636e5bf4afcbc9d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-02T05:00:12.805Z

Authors: Mst. Fahmida Sultana Naznin, Adnan Ibney Faruq, Mushfiqur Rahman, Niloy Kumar Mondal, Md. Mehedi Hasan Shawon, Md Rakibul Hasan

Published: 2026-03-31T15:47:01.000Z

## Abstract

Automated radiology report summarization aims to distill verbose findings into concise clinical impressions, but existing multimodal models often struggle with visual noise and fail to meaningfully improve over strong text-only baselines in the FINDINGS $\\to$ IMPRESSION transformation. We challenge two prevailing assumptions: (1) that more visual input is always better, and (2) that multimodal models add limited value when findings already contain rich image-derived detail. Through controlled ablations on MIMIC-CXR benchmark, we show that selectively focusing on pathology-relevant visual patches rather than full images yields substantially better performance. We introduce ViTAS, Visual-Text Attention Summarizer, a multi-stage pipeline that combines ensemble-guided MedSAM2 lung segmentation, bidirectional cross-attention for multi-view fusion, Shapley-guided adaptive patch clustering, and hierarchical visual tokenization feeding a ViT. ViTAS achieves SOTA results with 29.25% BLEU-4 and 69.83% ROUGE-L, improved factual alignment in qualitative analysis, and the highest expert-rated human evaluation scores. Our findings demonstrate that less but more relevant visual input is not only sufficient but superior for multimodal radiology summarization.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Medical Report Summarization on MIMIC-CXR (test)](<https://www.sota2.com/research/sota/medical-report-summarization-on-mimic-cxr-test.md>): Medical Report Summarization; MIMIC-CXR (test); ROUGE-L: 69.83.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.29901>)

[PDF](<https://arxiv.org/pdf/2603.29901.pdf>)