Automated detection and classification of acute vertebral body fractures using a convolutional neural network on computed tomography

Abstract

BackgroundAcute vertebral fracture is usually caused by low-energy injury with osteoporosis and high-energy trauma. The AOSpine thoracolumbar spine injury classification system (AO classification) plays an important role in the diagnosis and treatment of the disease. The diagnosis and description of vertebral fractures according to the classification scheme requires a great deal of time and energy for radiologists.PurposeTo design and validate a multistage deep learning system (multistage AO system) for the automatic detection, localization and classification of acute thoracolumbar vertebral body fractures according to AO classification on computed tomography.Materials and MethodsThe CT images of 1,217 patients who came to our hospital from January 2015 to December 2019 were collected retrospectively. The fractures were marked and classified by 2 junior radiology residents according to the type A standard in the AO classification. Marked fracture sites included the upper endplate, lower endplate and posterior wall. When there were inconsistent opinions on classification labels, the final result was determined by a director radiologist. We integrated different networks into different stages of the overall framework. U-net and a graph convolutional neural network (U-GCN) are used to realize the location and classification of the thoracolumbar spine. Next, a classification network is used to detect whether the thoracolumbar spine has a fracture. In the third stage, we detect fractures in different parts of the thoracolumbar spine by using a multibranch output network and finally obtain the AO types.ResultsThe mean age of the patients was 61.87 years with a standard deviation of 17.04 years, consisting of 760 female patients and 457 male patients. On vertebrae level, sensitivity for fracture detection was 95.23% in test dataset, with an accuracy of 97.93% and a specificity of 98.35%. For the classification of vertebral body fractures, the balanced accuracy was 79.56%, with an AUC of 0.904 for type A1, 0.945 for type A2, 0.878 for type A3 and 0.942 for type A4.ConclusionThe multistage AO system can automatically detect and classify acute vertebral body fractures in the thoracolumbar spine on CT images according to AO classification with high accuracy.

The Role of Artificial Intelligence in the Identification and Evaluation of Bone Fractures

“…However, there are countless additional applications of AI in musculoskeletal imaging. Numerous studies have investigated the performance of deeplearning methods for fracture detection in other anatomical locations such as the vertebrae [98,99], humerus [15], femur [32,100,101], shoulder [102,103], elbow [104,105], and skull [106]. While not fully covered within the scope of this review, we briefly summarize current AI methodologies for these types of fractures:…”

“…For fracture detection, they achieved a sensitivity of 95.23%, an accuracy of 97.93%, and a specificity of 98.35%. For fracture classification, they achieved AUCs of 0.904, 0.945, 0.878, and 0.942 for the four types of vertebral fractures, respectively [99].…”

Exploring deep learning radiomics for classifying osteoporotic vertebral fractures in X-ray images

“…Zhang et al. ( 18 ) employed U-net and U-Graph Convolution Network for thoracolumbar localization and classification, achieving AO classification through a multi-branch output network. The system’s accuracy was 97.93% for fracture detection and 79.56% for AO classification assessment, indicating its capability to accurately evaluate OVFs based on AO classification.…”

“…However, the MrOS study was limited to male OVFs patients from six clinical centers in the United States, necessitating further testing to determine the model's applicability to females and international populations. Zhang et al (18) employed U-net and U-Graph Convolution Network for thoracolumbar localization and classification, achieving AO classification through a multi-branch output network. The system's accuracy was 97.93% for fracture detection and 79.56% for AO classification assessment, indicating its capability to accurately evaluate OVFs based on AO classification.…”