R2Gen-Mamba: A Selective State Space Model for Radiology Report Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Yongheng, Lee, Yueh Z., Woodard, Genevieve A., Zhu, Hongtu, Lian, Chunfeng, Liu, Mingxia
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916450386575360
author Sun, Yongheng
Lee, Yueh Z.
Woodard, Genevieve A.
Zhu, Hongtu
Lian, Chunfeng
Liu, Mingxia
author_facet Sun, Yongheng
Lee, Yueh Z.
Woodard, Genevieve A.
Zhu, Hongtu
Lian, Chunfeng
Liu, Mingxia
contents Radiology report generation is crucial in medical imaging,but the manual annotation process by physicians is time-consuming and labor-intensive, necessitating the develop-ment of automatic report generation methods. Existingresearch predominantly utilizes Transformers to generateradiology reports, which can be computationally intensive,limiting their use in real applications. In this work, we presentR2Gen-Mamba, a novel automatic radiology report genera-tion method that leverages the efficient sequence processingof the Mamba with the contextual benefits of Transformerarchitectures. Due to lower computational complexity ofMamba, R2Gen-Mamba not only enhances training and in-ference efficiency but also produces high-quality reports.Experimental results on two benchmark datasets with morethan 210,000 X-ray image-report pairs demonstrate the ef-fectiveness of R2Gen-Mamba regarding report quality andcomputational efficiency compared with several state-of-the-art methods. The source code can be accessed online.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18135
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle R2Gen-Mamba: A Selective State Space Model for Radiology Report Generation
Sun, Yongheng
Lee, Yueh Z.
Woodard, Genevieve A.
Zhu, Hongtu
Lian, Chunfeng
Liu, Mingxia
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Radiology report generation is crucial in medical imaging,but the manual annotation process by physicians is time-consuming and labor-intensive, necessitating the develop-ment of automatic report generation methods. Existingresearch predominantly utilizes Transformers to generateradiology reports, which can be computationally intensive,limiting their use in real applications. In this work, we presentR2Gen-Mamba, a novel automatic radiology report genera-tion method that leverages the efficient sequence processingof the Mamba with the contextual benefits of Transformerarchitectures. Due to lower computational complexity ofMamba, R2Gen-Mamba not only enhances training and in-ference efficiency but also produces high-quality reports.Experimental results on two benchmark datasets with morethan 210,000 X-ray image-report pairs demonstrate the ef-fectiveness of R2Gen-Mamba regarding report quality andcomputational efficiency compared with several state-of-the-art methods. The source code can be accessed online.
title R2Gen-Mamba: A Selective State Space Model for Radiology Report Generation
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2410.18135