Aug 2026· 2026 International Conference on Modern Sustainable Systems (CMSS)· pp. 238-242· 0 citations· 16 references
Abstract
Automatic radiology report generation has become an active research area due to its potential to reduce radiologist workload and standardize reporting quality. However, state-of- the-art systems still suffer from hallucinated findings, limited clinical reasoning, and a lack of calibrated uncertainty estimates, all of which undermine trust in realworld deployments. This paper presents a clinically-aware multimodal radiology assis- tant that combines graph-enhanced cross-modal reasoning with uncertainty-guided report generation. The assistant integrates a convolutional or vision transformer backbone with a structured clinical knowledge graph, coupled through a graph-enhanced cross-attention module to align visual features with anatomical and pathological entities. A clinical consistency loss penalizes mismatches between image-based abnormality predictions and findings expressed in the generated text, directly targeting hallucinations. Uncertainty is quantified using Monte Carlo dropout and temperature scaling, enabling confidence-aware outputs and uncertainty-guided triage. Experiments on two public chest X- ray benchmarks and cross-dataset evaluation demonstrate im- proved factual consistency, reduced hallucination rate, and better calibration, including in rare-disease subsets, compared with transformer-only baselines. These results suggest that structured reasoning and uncertainty modeling are key ingredients for trustworthy radiology report generation.
This work proposes integrating Clinically-Aligned Chain-of-Thought reasoning pathways into the report generation process, and establishes a hierarchical diagnostic schema organized by imaging projections and anatomical structures, thereby ensuring a structured, interpretable workflow.
Yan Yang, Jia-Mei Sun, Zhou Yu et al.· IEEE journal of biomedical a...· 0 citations
Chest X-ray report generation systems are valuable for assisting disease diagnosis and improving healthcare efficiency. However, existing methods still face two key challenges. First, multiple diseases often co-occur, leading to a combinatorial explosion of label combinations and sparse supervision for learning a gener...
Hong-Ze Zhu, Hong Liu, Ya-Wen Huang et al.· IEEE Transactions on Medical...· 0 citations
Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes.
Xin-Yue Xu, Hong-Bin Lin, Juan-Gui Xu et al.· 0 citations
The proposed AG-VLM framework provides a scalable foundation for computer-assisted radiology reporting while retaining the need for radiologist verification before clinical use and indicates that explicit attention-guided visual reasoning combined with cross-modal semantic alignment can generate more accurate, clinical...
P. Dayaker, M. Vignesh, I. Z. et al.· International journal of com...· 0 citations
Results demonstrate that carefully designed prompting strategies can compete with substantially more complex image-grounded architectures, while multimodal methods continue to provide complementary clinical context for discrepancy understanding.
Asma Ben Abacha, Zhao-Yi Sun, Wen-wai Yim et al.· Conference and Labs of the E...· 3 citations
This work reformulate report generation as an anatomically grounded, multi-label, structured reporting task, predicting localized tumor involvement across a hierarchical clinical schema, and introduces SGRNet (Spatially Guided Radiology Network), incorporating two low-cost spatial priors: automated organ segmentations...
Ayush Gupta, V. Srivastav, Prateek Upadhya et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.