Abstract Background Spinal infections such as pyogenic spondylitis, spinal tuberculosis, and brucellar spondylitis are severe conditions that can lead to significant spinal damage and chronic pain. Whole-slide imaging (WSI) provides valuable visual information in pathological diagnoses. However, owing to the complexity and high dimensionality of WSI data, traditional manual diagnostic methods are often time-consuming and prone to errors. Therefore, developing an automated image analysis method is crucial to enhance the diagnostic accuracy and efficiency of WSI for spinal infections. Methods This study employed a novel framework that combines Graph Convolutional Networks (GCNs) with uncertainty quantification techniques to classify WSI images of spinal infections. A graph was constructed from segmented regions of the WSI, where nodes represented segmented pathological features and edges represented spatial relationships. The model was trained using a dataset of 422 cases from a provincial center for disease control and prevention and annotated for tuberculosis, brucellosis, and purulent spondylitis. The performance metrics were accuracy, precision, recall, and F1 scores. Results The integrated GCN model demonstrated a classification accuracy of 87%, recall of 85%, and F1 score of 0.86. Comparative analyses revealed that the GCN model exhibited a 10% higher performance than that of traditional CNN models. Moreover, the GCN model effectively quantified uncertainty and enhanced confidence in diagnostic decisions. Conclusions Integrating GCNs with model uncertainty enhances the accuracy and reliability of WSI image classification in pathology. This method significantly improves the capture of spatial relationships and identification of pathological features of spinal infections, offering a robust framework for supporting diagnostic and therapeutic decisions in medical practice.
Bone and joint tuberculosis (BJTB) is a distinct variant of tuberculosis in which clinical diagnosis often leads to relative misdiagnosis and missed diagnoses. This study aimed to evaluate the diagnostic accuracy of the targeted nanopore sequencing (TNPseq) assay for BJTB patients in China. The study enrolled a cohort of 163 patients with suspected BJTB. Diagnostic testing was performed using the TNPseq assay on samples including punctured tissue, pus, and blood. The diagnostic accuracy of the TNPseq assay was then compared with that of the T-SPOT and Xpert MTB/RIF assays. TNPseq exhibited superior performance in terms of accuracy, demonstrating a sensitivity of 76.3% (95% CI: 71.0-81.6%) and a specificity of 98.8% (95% CI: 93.5–100%) in clinical diagnosis. When evaluated against a composite reference standard, TNPseq demonstrated a sensitivity of 74.4% (95% CI: 69.3–79.5%) and a specificity of 98.8% (95% CI: 93.7–100%). These results exceed the performance of both the T-SPOT and Xpert MTB/RIF tests. Notably, TNPseq demonstrated high specificity and accuracy in puncture specimens, with a sensitivity of 75.0% (95% CI: 70.2–79.8%) and a specificity of 98.3% (95% CI: 92.7–100%), as well as in pus samples, with a sensitivity of 83.3% (95% CI: 78.6–88.1%) and a specificity of 100% (95% CI: 100–100%). Additionally, TNPseq facilitated the detection of mixed infection scenarios, identifying 20 cases of bacterial-fungal co-infection, 17 cases of bacterial-viral co-infection, and two cases of simultaneous bacterial-fungal-viral co-infection. TNPseq demonstrated great potential in the diagnosis of BJTB due to its high sensitivity and specificity. The ability of TNPseq to diagnose pathogens and detect drug resistance genes can also guide subsequent treatment. Expanding the application scenarios and scope of TNPseq will enable it to benefit more clinical treatments.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)