Next Article in Journal
Line Defects in One-Dimensional Hexagonal Quasicrystals
Previous Article in Journal
Finite-Time Stability of a Class of Nonstationary Nonlinear Fractional Order Time Delay Systems: New Gronwall–Bellman Inequality Approach
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

RMPT: Reinforced Memory-Driven Pure Transformer for Automatic Chest X-Ray Report Generation

1
Institute of Information Engineering, Sanming University, Sanming 365004, China
2
Qingdao Nuocheng Chemicals Safty Technology Co., Ltd., Qingdao 266071, China
*
Author to whom correspondence should be addressed.
Mathematics 2025, 13(9), 1492; https://doi.org/10.3390/math13091492
Submission received: 21 March 2025 / Revised: 27 April 2025 / Accepted: 29 April 2025 / Published: 30 April 2025

Abstract

Automatic generation of chest X-ray reports, designed to produce clinically precise descriptions from chest X-ray images, is gaining significant research attention because of its vast potential in clinical applications. Recently, despite considerable progress, current models typically adhere to a CNN–Transformer-based framework, which still fails to enhance the perceptual field during image feature extraction. To solve this problem, we propose the Reinforced Memory-driven Pure Transformer (RMPT), which is a novel Transformer–Transformer-based model. In implementation, our RMPT employs the Swin Transformer to extract visual features from given X-ray images, which has a larger perceptual field to better model the relationships between different regions. Furthermore, we adopt a memory-driven Transformer (MemTrans) to effectively model similar patterns in different reports, which is able to facilitate the model to generate long reports. Finally, we present an innovative training approach leveraging Reinforcement Learning (RL) that efficiently steers the model to focus on challenging samples, consequently improving its comprehensive performance across both straightforward and complex situations. Experimental results on the IU X-ray dataset show that our proposed RMPT achieves superior performance on various Natural Language Generation (NLG) evaluation metrics. Further ablation study results demonstrate that our RMPT model achieves 10.5% overall performance compared to the base mode.
Keywords: chest X-ray report generation; transformer; image-to-text; reinforcement learning; MSC: 68T50 chest X-ray report generation; transformer; image-to-text; reinforcement learning; MSC: 68T50

Share and Cite

MDPI and ACS Style

Qin, C.; Xiong, Y.; Chen, W.; Li, Y. RMPT: Reinforced Memory-Driven Pure Transformer for Automatic Chest X-Ray Report Generation. Mathematics 2025, 13, 1492. https://doi.org/10.3390/math13091492

AMA Style

Qin C, Xiong Y, Chen W, Li Y. RMPT: Reinforced Memory-Driven Pure Transformer for Automatic Chest X-Ray Report Generation. Mathematics. 2025; 13(9):1492. https://doi.org/10.3390/math13091492

Chicago/Turabian Style

Qin, Caijie, Yize Xiong, Weibin Chen, and Yong Li. 2025. "RMPT: Reinforced Memory-Driven Pure Transformer for Automatic Chest X-Ray Report Generation" Mathematics 13, no. 9: 1492. https://doi.org/10.3390/math13091492

APA Style

Qin, C., Xiong, Y., Chen, W., & Li, Y. (2025). RMPT: Reinforced Memory-Driven Pure Transformer for Automatic Chest X-Ray Report Generation. Mathematics, 13(9), 1492. https://doi.org/10.3390/math13091492

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop