Accurate Differentiation of Spinal Tuberculosis and Spinal Metastases Using MR-Based Deep Learning Algorithms

Abstract

Purpose

To explore the application of deep learning (DL) methods based on T2 sagittal MR images for discriminating between spinal tuberculosis (STB) and spinal metastases (SM).

Patients and Methods

A total of 121 patients with histologically confirmed STB and SM across four institutions were retrospectively analyzed. Data from two institutions were used for developing deep learning models and internal validation, while the remaining institutions’ data were used for external testing. Utilizing MVITV2, EfficientNet-B3, ResNet101, and ResNet34 as backbone networks, we developed four distinct DL models and evaluated their diagnostic performance based on metrics such as accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score, and confusion matrix. Furthermore, the external test images were blindly evaluated by two spine surgeons with different levels of experience. We also used Gradient-Class Activation Maps to visualize the high-dimensional features of different DL models.

Results

For the internal validation set, MVITV2 outperformed other models with an accuracy of 98.7%, F1 score of 98.6%, and AUC of 0.98. Other models followed in this order: EfficientNet-B3 (ACC: 96.1%, F1 score: 95.9%, AUC: 0.99), ResNet101 (ACC: 85.5%, F1 score: 84.8%, AUC: 0.90), and ResNet34 (ACC: 81.6%, F1 score: 80.7%, AUC: 0.85). For the external test set, MVITV2 again performed excellently with an accuracy of 91.9%, F1 score of 91.5%, and an AUC of 0.95. EfficientNet-B3 came second (ACC: 85.9, F1 score: 91.5%, AUC: 0.91), followed by ResNet101 (ACC:80.8, F1 score: 80.0%, AUC: 0.87) and ResNet34 (ACC: 78.8, F1 score: 77.9%, AUC: 0.86). Additionally, the diagnostic accuracy of the less experienced spine surgeon was 73.7%, while that of the more experienced surgeon was 88.9%.

Conclusion

Deep learning based on T2WI sagittal images can help discriminate between STB and SM, and can achieve a level of diagnostic performance comparable with that produced by experienced spine surgeons.

Keywords:

• artificial intelligence
• deep learning
• spinal tuberculosis
• spinal metastases
• magnetic resonance imaging

Abbreviations

DL, Deep learning; MVITV2, Multiscale Vision Transformers V2; STB, Spinal tuberculosis; SM, Spinal metastases; MRI, Magnetic resonance imaging; ACC, Accuracy; AUC, Area under the receiver operating characteristic curve; PET/CT, Positron Emission Tomography-Computed Tomography; CNN, Convolutional Neural Network; T2WI, T2-weighted imaging; Grad-CAM, Gradient-Class Activation Maps; ROC, Receiver operating characteristic curve; AI, Artificial intelligence.

Ethics Approval

This study was approved (Ethic number, IRB: #KY2020-073-02) by the Human Investigations Committees at Beijing Tiantan Hospital of the Capital Medical University, and the other three participating sites in accordance with the Declaration of Helsinki. All patients signed informed consent for matters regarding participation in the clinical study during hospital admission.

Consent for Publication

All authors have consented to the publication of the manuscript.

Acknowledgments

Some of our experiments were carried out on the OpenMMLab’s Pre-training Toolbox and Benchmark (open source code is released here: https://github.com/open-mmlab/mmpretrain). Thanks to MMPreTrain Contributors.

Author Contributions

All authors made a significant contribution to the work reported, whether that is in the conception, study design, execution, acquisition of data, analysis and interpretation, or in all these areas; took part in drafting, revising or critically reviewing the article; gave final approval of the version to be published; have agreed on the journal to which the article has been submitted; and agree to be accountable for all aspects of the work.

Disclosure

The authors report no conflicts of interest in this work.

Additional information

Funding

This work was supported by the Capital Medical University Education and Teaching Reform Research Project Fund (grant numbers:2023JYY226), National Natural Science Foundation of China (grant numbers:81972084).