Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT
- 21 December 2024
- journal article
- research article
- Published by Springer Nature in European Spine Journal
- p. 1-10
Abstract
Purpose To develop a deep learning system for automatic segmentation of compression fracture vertebral bodies on thoracolumbar CT and differentiate between fresh and old fractures. Methods We included patients with thoracolumbar fractures treated at our Hospital South Campus from January 2020 to December 2023, with prospective validation from January to June 2024, and used data from the North Campus from January to December 2023 for external validation. Fresh fractures were defined as back pain lasting less than 4 weeks, with MRI showing bone marrow edema (BME). We utilized a 3D V-Net for image segmentation and several ResNet and DenseNet models for classification, evaluating performance with ROC curves, accuracy, sensitivity, specificity, precision, F1 score, and AUC. The optimal model was selected to construct deep learning system and its diagnostic efficacy was compared with that of two clinicians. Results The training dataset included 238 vertebras (man/women: 55/183; age: 72.11 ± 11.55), with 59 in internal validation (man/women: 13/46; age: 74.76 ± 8.96), 34 in external validation, and 48 in prospective validation. The 3D V-Net model achieved a DSC of 0.90 on the validation dataset. ResNet18 performed best among classification models, with an AUC of 0.96 in validation, 0.89 in external dataset, and 0.87 in prospective validation, surpassing the two clinicians in both external and prospective validations. Conclusion The deep learning model can automatically and accurately segment the vertebral bodies with compression fractures and classify them as fresh or old fractures, thereby assisting clinicians in making clinical decisions.Keywords
Funding Information
- Guangdong Medical Research Foundation (A2021280)
- Science and Technology Program of Guangzhou (202201020365)
- Sun Yat-sen Scientific Research Project (YXQH202213)
- National Natural Science Foundation of China (No.82202653)
This publication has 35 references indexed in Scilit:
- Brain Tumour Segmentation on 3D MRI Using Attention V-Net2022
- Prediction of acute versus chronic osteoporotic vertebral fracture using radiomics-clinical model on CTEuropean Journal of Radiology, 2022
- Prediction of the Acuity of Vertebral Compression Fractures on CT Using Radiologic and Radiomic FeaturesAcademic Radiology, 2022
- Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CTEuropean Radiology, 2021
- The impact of magnetic resonance imaging in the diagnostic and classification process of osteoporotic vertebral fracturesInjury, 2018
- Brain tumor segmentation with Deep Neural NetworksMedical Image Analysis, 2017
- Shape, texture and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance imagesComputers in Biology and Medicine, 2016
- A multi-center milestone study of clinical vertebral CT segmentationComputerized Medical Imaging and Graphics, 2016
- Dual-energy CT in vertebral compression fractures: performance of visual and quantitative analysis for bone marrow edema demonstration with comparison to MRISkeletal Radiology, 2014
- The prognosis for pain, disability, activities of daily living and quality of life after an acute osteoporotic vertebral body fracture: its relation to fracture level, type of fracture and grade of fracture deformationEuropean Spine Journal, 2008