Sep 2026· International Conference on Artificial Intelligence, Machine, Vision and Control· Vol 14345, pp. 143451R - 143451R-12· 0 citations· 41 references
Engineering
TL;DR
Experimental results demonstrate the model's efficacy in enhancing critical region representation and semantic consistency, thereby improving clinical trust in computer-aided diagnosis, and highlights the model's efficacy in enhancing critical region representation and semantic consistency.
Abstract
Radiologists typically adopt a coarse-to-fine, dynamic focusing cognitive strategy when interpreting medical images, focusing on potential abnormal regions while integrating semantic context to compose reports. However, most existing medical report generation methods rely on fixed-resolution image encoding, which struggle to accommodate the radiologist's spatial interaction intent, resulting in insufficient fine-grained lesion descriptions. To address this, we propose a controllable medical report generation framework centered on physician interaction. The framework introduces the mechanism of "Select bbox-to-Explain", utilizing physician-specified spatial regions as instruction signals. The model constructs high-resolution local views and global contextual representations through a bounding-box-guided multi-scale dynamic focusing mechanism. During the report generation phase, regional visual features are parsed into structured medical semantics, which are then modeled alongside spatial instructions and natural language task prompts as a unified Multimodal Prompt. This architecture drives a Large Language Model (LLM) to generate controllable and clinically consistent medical reports. Experimental results demonstrate that the proposed model achieves a ROUGE-L score of 0.402 on region-level reports—an approximate 40% improvement over the baseline while maintaining the contextual integrity of the full report. This highlights the model's efficacy in enhancing critical region representation and semantic consistency, thereby improving clinical trust in computer-aided diagnosis.
A unified framework for automatic report generation from SPECT bone scintigrams that integrates domain-adaptive representation learning, fine-grained image–text alignment, and anatomy-guided supervision is proposed, offering a valuable pathway to achieving trustworthy and intelligent diagnostic support within nuclear m...
Tao Song, Qiang Lin, Tong-Tong Li et al.· Applied intelligence (Boston...· 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
ClinAlign—a memory-based retrieval framework aligned with clinical workflow, drawing inspiration from clinical diagnostic workflows is proposed, which constructs a disease-aware visual memory bank and introduces Classification-Guided Prompt Augmentation (CGPA), where disease state predictions are converted into structu...
Lihong Qiao, Shi-Yi Gao, Yu-Cheng Shu et al.· Proceedings of the Thirty-Fi...· 0 citations
Through hierarchical gated co-attention, this approach dynamically aligns image and text representations, addressing the limitations of static fusion and providing a foundation for interpretable, real-time retrieval systems that can accelerate and improve clinical decision support.
A training-time report-guided framework that leverages structured radiology reports as privileged concept supervision while enabling image-only diagnosis at test time, and refines image-derived concepts through a teacher-guided editing mechanism within a malignancy-aware ordered concept space.
Wen-Tao Yue, Tian-You Lai, Jia-Yu Luo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.