Libra: Leveraging Temporal Images for Biomedical Radiology Analysis

TL;DR

Libra is a novel multimodal large language model designed for chest X-ray report generation that effectively captures temporal differences between current and prior images, improving report accuracy.

Contribution

Libra introduces a temporal-aware architecture with a specialized Temporal Alignment Connector for enhanced medical image analysis.

Findings

Achieves state-of-the-art performance on MIMIC-CXR dataset.

Effectively captures temporal differences in chest X-ray images.

Improves clinical relevance and lexical accuracy in reports.

Abstract

Radiology report generation (RRG) requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. While multimodal large language models (MLLMs) align with pre-trained vision encoders to enhance visual-language understanding, most existing methods rely on single-image analysis or rule-based heuristics to process multiple images, failing to fully leverage temporal information in multi-modal medical datasets. In this paper, we introduce Libra, a temporal-aware MLLM tailored for chest X-ray report generation. Libra combines a radiology-specific image encoder with a novel Temporal Alignment Connector (TAC), designed to accurately capture and integrate temporal differences between paired current and prior images. Extensive experiments on the MIMIC-CXR dataset demonstrate that Libra establishes a new state-of-the-art benchmark among similarly scaled MLLMs, setting new standards in both clinical relevance and lexical accuracy.