An ROI-Guided Imaging Informatics Framework for Image-Language Differentiation of Tuberculous and Pyogenic Spondylitis on MRI.
Authors
Affiliations (5)
Affiliations (5)
- Department of Spine Surgery, University of South China Affiliated Nanhua Hospital, Hengyang, China.
- Department of Infectious Diseases, Hunan University of Medicine General Hospital, Huaihua, China.
- Department of Spine Surgery, University of South China Affiliated Nanhua Hospital, Hengyang, China. [email protected].
- Yue Bei People's Hospital Postdoctoral Innovation Practice Base, Southern Medical University, Guangzhou, Guangdong, China. [email protected].
- Department of Spine Surgery, University of South China Affiliated Nanhua Hospital, Hengyang, China. [email protected].
Abstract
This study aims to develop and validate an MRI-based image-language collaborative framework for differentiating tuberculous spondylitis (TB) from pyogenic spondylitis (PS) at the patient level. This retrospective two-center study included 347 patients with microbiologically or histopathologically confirmed spinal infection (218 TB, 129 PS) who underwent sagittal T2 weighted MRI between June 2021 and June 2025. An enhanced YOLO model was used to localize infection-related regions of interest (ROIs), which were subsequently reviewed by radiologists and used as semi-automated standardized inputs. Patient-level diagnostic performance was evaluated across ROI-guided supervised classifiers (ConvNeXt and Swin Transformer), whole-image large language model (LLM) zero-shot and few-shot inference, and ROI-guided LLM few-shot inference. Multivariable logistic regression was performed to identify independent imaging features. Vertebral collapse (OR, 3.713; p < 0.001) and marked disc involvement (OR, 0.209; p < 0.001) were independent imaging features for differentiating TB from PS. The lesion detector achieved an [email protected] of 0.97. After patient-level probability pooling and validation-set thresholding, ConvNeXt achieved an AUC of 0.762 and an accuracy of 62.9%, whereas Swin Transformer achieved an AUC of 0.804 and an accuracy of 71.4% on the 35-patient independent test set. Whole-image zero-shot LLM inference showed limited diagnostic value, improving with few-shot prompting. On the same 35-patient test set, ROI guided 10-shot LLM achieved 82.9% accuracy, 81.8% sensitivity, 84.6% specificity, 90.0% precision, and 85.7% F1 score, showing numerically more balanced patient-level performance than whole-image inference. Because of the limited test-set size, these performance estimates should be interpreted as exploratory. ROI-guided constrained LLM reasoning provides stable and interpretable patient-level differentiation of spinal infection on MRI. By linking diagnostic output to traceable ROI-level evidence, this framework may serve as a radiologist-supervised second-reader tool for difficult TB/PS cases.