Spinal tuberculosis: proposed spinal infection multidisciplinary management project (SIMP) flow chart revision

Computer-Aided Diagnosis of Spinal Tuberculosis From CT Images Based on Deep Learning With Multimodal Feature Fusion

Background

Spinal tuberculosis (TB) has the highest incidence in remote plateau areas, particularly in Tibet, China, due to inadequate local healthcare services, which not only facilitates the transmission of TB bacteria but also increases the burden on grassroots hospitals. Computer-aided diagnosis (CAD) is urgently required to improve the efficiency of clinical diagnosis of TB using computed tomography (CT) images. However, classical machine learning with handcrafted features generally has low accuracy, and deep learning with self-extracting features relies heavily on the size of medical datasets. Therefore, CAD, which effectively fuses multimodal features, is an alternative solution for spinal TB detection.

Methods

A new deep learning method is proposed that fuses four elaborate image features, specifically three handcrafted features and one convolutional neural network (CNN) feature. Spinal TB CT images were collected from 197 patients with spinal TB, from 2013 to 2020, in the People’s Hospital of Tibet Autonomous Region, China; 3,000 effective lumbar spine CT images were randomly screened to our dataset, from which two sets of 1,500 images each were classified as tuberculosis (positive) and health (negative). In addition, virtual data augmentation is proposed to enlarge the handcrafted features of the TB dataset. Essentially, the proposed multimodal feature fusion CNN consists of four main sections: matching network, backbone (ResNet-18/50, VGG-11/16, DenseNet-121/161), fallen network, and gated information fusion network. Detailed performance analyses were conducted based on the multimodal features, proposed augmentation, model stability, and model-focused heatmap.

Results

Experimental results showed that the proposed model with VGG-11 and virtual data augmentation exhibited optimal performance in terms of accuracy, specificity, sensitivity, and area under curve. In addition, an inverse relationship existed between the model size and test accuracy. The model-focused heatmap also shifted from the irrelevant region to the bone destruction caused by TB.

Conclusion

The proposed augmentation effectively simulated the real data distribution in the feature space. More importantly, all the evaluation metrics and analyses demonstrated that the proposed deep learning model exhibits efficient feature fusion for multimodal features. Our study provides a profound insight into the preliminary auxiliary diagnosis of spinal TB from CT images applicable to the Tibetan area.

Selection of the fusion and fixation range in the intervertebral surgery to correct thoracolumbar and lumbar tuberculosis: a retrospective clinical study

Background

To compare the diseased verses the non-diseased intervertebral surgery used in the treatment of thoracolumbar and lumbar spinal tuberculosis and to explore the best choice of fusion of fixation range.

Methods

Two hundred twenty-one patients with thoracolumbar and lumbar tuberculosis were categorized into two groups. One hundred eighteen patients underwent the diseased intervertebral surgery (lesion vertebral pedicle fixation, Group A) and 103 patients underwent the non-diseased intervertebral surgery (1 or 2 vertebral fixation above and below the affected vertebra, group B). Spinal tuberculosis diagnosis was confirmed in both groups of patients before lesion removal, bone graft fusion, and internal fixation. Clinical data and efficacy of the two surgical methods were then evaluated.

Results

The mean follow-up duration for both procedures was 65 months (50–68 months range). There were no significant differences in laboratory examinations, VAS scores, and the Cobb angle correction rate and the angle loss. However, significant differences existed in the operation time, blood loss, serosanguineous drainage volume, and blood transfusion requirement between the two groups. The diseased intervertebral surgery group performed significantly better than the non-diseased intervertebral surgery group in all of these areas. In both cases, the bone graft fused completely with the normal bone by the last follow-up, occuring at 50–86 months post surgery.

Conclusion

The diseased intervertebral surgery is a safe and feasible option for the treatment of thoracolumbar and lumbar tuberculosis. It effectively restores the physiological curvature of the spine and reduces the degeneration of adjacent vertebral bodies in the spinal column.