R2Gen-Mamba: A Selective State Space Model for Radiology Report Generation
This work addresses the time-consuming manual annotation process in medical imaging for physicians, offering an incremental improvement in automatic report generation.
The paper tackles the problem of automatic radiology report generation by proposing R2Gen-Mamba, a method that combines Mamba and Transformer architectures to improve efficiency and quality. Experimental results on over 210,000 X-ray image-report pairs show it outperforms state-of-the-art methods in report quality and computational efficiency.
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.