Abstract
Radiology report generation models can produce fluent text while still containing finding-level inaccuracies. Diagnosis-driven methods improve generation by conditioning on predicted findings, but these predictions do not directly modify the visual patch features provided to the decoder, and global gating applies the same modulation across spatial locations. We introduce a Position-Aware Gate (PAG) that uses predicted finding representations to modulate visual patches spatially without region supervision. We also propose a Decoder-level Supervised Contrastive Loss (DSCL) that structures decoder representations using shared positive findings rather than instance identity. On MIMIC-CXR, PAG+DSCL improves clinical efficacy (CE) F1 from 0.484 to 0.502 over a matched global-gate reference, while PAG and DSCL individually reach 0.491 and 0.495. Without additional fine-tuning, the combined model achieves 0.226 CE F1 on IU X-Ray, compared with 0.211 reported by PromptMRG.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Rahman, M. M., & Farias, M. C. Q. (2026). Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation. https://omanscience.com/en/articles/diagnosis-conditioned-spatial-gating-and-decoder-level-supervised-contrastive-learning-for-radiology-report-generation
MLA 9
Rahman, Md Mustafizur, and Mylene C. Q. Farias. "Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation." https://omanscience.com/en/articles/diagnosis-conditioned-spatial-gating-and-decoder-level-supervised-contrastive-learning-for-radiology-report-generation.
Chicago (author–date)
Rahman, Md Mustafizur, and Mylene C. Q. Farias. 2026. "Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation." https://omanscience.com/en/articles/diagnosis-conditioned-spatial-gating-and-decoder-level-supervised-contrastive-learning-for-radiology-report-generation.
Harvard
Rahman, M. M. and Farias, M. C. Q. (2026) 'Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation', Available at: https://omanscience.com/en/articles/diagnosis-conditioned-spatial-gating-and-decoder-level-supervised-contrastive-learning-for-radiology-report-generation.
Vancouver
Rahman MM, Farias MCQ. Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation. https://omanscience.com/en/articles/diagnosis-conditioned-spatial-gating-and-decoder-level-supervised-contrastive-learning-for-radiology-report-generation
IEEE
M. M. Rahman, and M. C. Q. Farias, "Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation," https://omanscience.com/en/articles/diagnosis-conditioned-spatial-gating-and-decoder-level-supervised-contrastive-learning-for-radiology-report-generation.