Infection and Drug Resistance (Jul 2023)
Accurate Differentiation of Spinal Tuberculosis and Spinal Metastases Using MR-Based Deep Learning Algorithms
Abstract
Shuo Duan,1,* Weijie Dong,2,* Yichun Hua,3 Yali Zheng,4 Zengsuonan Ren,5 Guanmei Cao,6 Fangfang Wu,4 Tianhua Rong,1 Baoge Liu1 1Department of Orthopaedic Surgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, People’s Republic of China; 2Department of Orthopedics, Beijing Chest Hospital, Capital Medical University, Beijing, People’s Republic of China; 3Department of Medical Oncology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People’s Republic of China; 4Department of Respiratory, Critical Care, and Sleep Medicine, Xiang’an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, People’s Republic of China; 5Department of Orthopaedic Surgery, People’s Hospital of Hainan Tibetan Autonomous Prefecture, Hainan Tibetan Autonomous Prefecture, Qinghai Province, People’s Republic of China; 6Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Baoge Liu, Department of Orthopaedic Surgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 South 4th Ring West Road, Fengtai District, Beijing, 100070, People’s Republic of China, Tel +86 13581521066, Fax +010-59978702, Email [email protected]: 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
