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

TL;DR

R2Gen-Mamba introduces an efficient radiology report generation model combining Mamba's sequence processing with Transformer benefits, achieving high-quality reports with reduced computational costs on benchmark datasets.

Contribution

It presents a novel model that improves efficiency and report quality in radiology report generation by integrating Mamba with Transformer architectures.

Findings

Outperforms state-of-the-art methods in report quality.

Reduces training and inference time significantly.

Effective on large benchmark datasets.

Abstract

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.