Deep Learning-Assisted Quantitative Measurement of Thoracolumbar Fracture Features on Lateral Radiographs

• Published in: Neurospine Vol. 21; no. 1; pp. 30 - 43
• Main Authors: Yuh, Woon Tak, Khil, Eun Kyung, Yoon, Yu Sung, Kim, Burnyoung, Yoon, Hongjun, Lim, Jihe, Lee, Kyoung Yeon, Yoo, Yeong Seo, An, Kyeong Deuk
• Format: Journal Article
• Language: English
• Published: Korea (South) Korean Spinal Neurosurgery Society 01.03.2024; 대한척추신경외과학회
• Subjects: artificial intelligence; deep learning; Original; radiography; spinal curvatures; spinal fractures; spinal injuries; 신경외과학; Deep learning; Radiography; Spinal curvatures; Spinal injuries; Spinal fractures; Artificial intelligence
• ISSN: 2586-6583; 2586-6591
• DOI: 10.14245/ns.2347366.683

This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics-compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)-from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.