Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xi, Meng, Zaiqiao, Lever, Jake, Ho, Edmond S. L.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.19378
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911087641755648
author Zhang, Xi
Meng, Zaiqiao
Lever, Jake
Ho, Edmond S. L.
author_facet Zhang, Xi
Meng, Zaiqiao
Lever, Jake
Ho, Edmond S. L.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19378
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Libra: Leveraging Temporal Images for Biomedical Radiology Analysis
Zhang, Xi
Meng, Zaiqiao
Lever, Jake
Ho, Edmond S. L.
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
I.2.10; J.3; I.5.4
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.
title Libra: Leveraging Temporal Images for Biomedical Radiology Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
I.2.10; J.3; I.5.4
url https://arxiv.org/abs/2411.19378