Automated prediction of the Thoracolumbar Injury Classification and Severity Score from CT using a novel deep learning algorithm

Abstract

OBJECTIVE Damage to the thoracolumbar spine can confer significant morbidity and mortality. The Thoracolumbar Injury Classification and Severity Score (TLICS) is used to categorize injuries and determine patients at risk of spinal instability for whom surgical intervention is warranted. However, calculating this score can constitute a bottleneck in triaging and treating patients, as it relies on multiple imaging studies and a neurological examination. Therefore, the authors sought to develop and validate a deep learning model that can automatically categorize vertebral morphology and determine posterior ligamentous complex (PLC) integrity, two critical features of TLICS, using only CT scans. METHODS All patients who underwent neurosurgical consultation for traumatic spine injury or degenerative pathology resulting in spine injury at a single tertiary center from January 2018 to December 2019 were retrospectively evaluated for inclusion. The morphology of injury and integrity of the PLC were categorized on CT scans. A state-of-the-art object detection region-based convolutional neural network (R-CNN), Faster R-CNN, was leveraged to predict both vertebral locations and the corresponding TLICS. The network was trained with patient CT scans, manually labeled vertebral bounding boxes, TLICS morphology, and PLC annotations, thus allowing the model to output the location of vertebrae, categorize their morphology, and determine the status of PLC integrity. RESULTS A total of 111 patients were included (mean ± SD age 62 ± 20 years) with a total of 129 separate injury classifications. Vertebral localization and PLC integrity classification achieved Dice scores of 0.92 and 0.88, respectively. Binary classification between noninjured and injured morphological scores demonstrated 95.1% accuracy. TLICS morphology accuracy, the true positive rate, and positive injury mismatch classification rate were 86.3%, 76.2%, and 22.7%, respectively. Classification accuracy between no injury and suspected PLC injury was 86.8%, while true positive, false negative, and false positive rates were 90.0%, 10.0%, and 21.8%, respectively. CONCLUSIONS In this study, the authors demonstrate a novel deep learning method to automatically predict injury morphology and PLC disruption with high accuracy. This model may streamline and improve diagnostic decision support for patients with thoracolumbar spinal trauma.

Machine Learning and Deep Learning in Spinal Injury: A Narrative Review of Algorithms in Diagnosis and Prognosis

“…For example, Chen et al used deep learning for high-accuracy AO (Arbeitsgemeinschaft für Osteosynthesefragen) classification of thoracolumbar fractures [14]. On the other hand, Doerr et al developed a model to categorize vertebral morphology and determine posterior ligamentous complex integrity for the purpose of assigning Thoracolumbar Injury Classification and Severity Score (TLICS), both using CT scans [46]. Zhang et al developed a multistage system using CNNs (U-net, GCN, 3D-ResNet) that can automatically detect and classify acute thoracolumbar vertebral body fractures on CT images with high-accuracy AO classification-achieving a sensitivity of 95.23%, an overall accuracy of 97.93%, a specificity of 98.35%, and balanced accuracy rates ranging from 79.56% to 94.5% for different fracture types according to AO classification [34].…”

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

“… 29 In a retrospective examination, the computed tomography (CT) scans of 111 individuals with thoracolumbar spinal injuries were merged into a DL model, which was able to classify non-injured and suspected injury with an accuracy of 86.8% ( Table 1 ). 8

Fig. 2 Algorithms/Models of Artificial Intelligence for Neurosurgery Diagnostics and Treatment Approach.

…”

Machine Learning in Spine Surgery: A Narrative Review

“…Faster R-CNN classifies between noninjured and injured patients at an accuracy of 95.1%. 21 Anatomic landmarks and Cobb angle measurements are also identified from CT images of the spine by determining the vertebral body shape, intervertebral disk height, thoracic kyphosis, and lumbar lordosis. 22 ML uses CT attenuation of vertebrae to identify osteoporotic patients by transforming Hounsfield units into estimations of bone mineral densities and eventually T-scores.…”