1
|
Ryu SM, Lee S, Jang M, Koh JM, Bae SJ, Jegal SG, Shin K, Kim N. Diagnosis of osteoporotic vertebral compression fractures and fracture level detection using multitask learning with U-Net in lumbar spine lateral radiographs. Comput Struct Biotechnol J 2023; 21:3452-3458. [PMID: 37457807 PMCID: PMC10345217 DOI: 10.1016/j.csbj.2023.06.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Revised: 06/18/2023] [Accepted: 06/24/2023] [Indexed: 07/18/2023] Open
Abstract
Recent studies of automatic diagnosis of vertebral compression fractures (VCFs) using deep learning mainly focus on segmentation and vertebral level detection in lumbar spine lateral radiographs (LSLRs). Herein, we developed a model for simultaneous VCF diagnosis and vertebral level detection without using adjacent vertebral bodies. In total, 1102 patients with VCF, 1171 controls were enrolled. The 1865, 208, and 198 LSLRS were divided into training, validation, and test dataset. A ground truth label with a 4-point trapezoidal shape was made based on radiological reports showing normal or VCF at some vertebral level. We applied a modified U-Net architecture, in which decoders were trained to detect VCF and vertebral levels, sharing the same encoder. The multi-task model was significantly better than the single-task model in sensitivity and area under the receiver operating characteristic curve. In the internal dataset, the accuracy, sensitivity, and specificity of fracture detection per patient or vertebral body were 0.929, 0.944, and 0.917 or 0.947, 0.628, and 0.977, respectively. In external validation, those of fracture detection per patient or vertebral body were 0.713, 0.979, and 0.447 or 0.828, 0.936, and 0.820, respectively. The success rates were 96 % and 94 % for vertebral level detection in internal and external validation, respectively. The multi-task-shared encoder was significantly better than the single-task encoder. Furthermore, both fracture and vertebral level detection was good in internal and external validation. Our deep learning model may help radiologists perform real-life medical examinations.
Collapse
Affiliation(s)
- Seung Min Ryu
- Department of Orthopedic Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Soyoung Lee
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Miso Jang
- Department of Convergence Medicine, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Jung-Min Koh
- Division of Endocrinology and Metabolism, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Sung Jin Bae
- Department of Health Screening and Promotion Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Seong Gyu Jegal
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Keewon Shin
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Namkug Kim
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- Department of Convergence Medicine, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| |
Collapse
|
2
|
Lee JS, Shin K, Ryu SM, Jegal SG, Lee W, Yoon MA, Hong GS, Paik S, Kim N. Screening of adolescent idiopathic scoliosis using generative adversarial network (GAN) inversion method in chest radiographs. PLoS One 2023; 18:e0285489. [PMID: 37216382 DOI: 10.1371/journal.pone.0285489] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Accepted: 04/25/2023] [Indexed: 05/24/2023] Open
Abstract
OBJECTIVE Conventional computer-aided diagnosis using convolutional neural networks (CNN) has limitations in detecting sensitive changes and determining accurate decision boundaries in spectral and structural diseases such as scoliosis. We devised a new method to detect and diagnose adolescent idiopathic scoliosis in chest X-rays (CXRs) employing the latent space's discriminative ability in the generative adversarial network (GAN) and a simple multi-layer perceptron (MLP) to screen adolescent idiopathic scoliosis CXRs. MATERIALS AND METHODS Our model was trained and validated in a two-step manner. First, we trained a GAN using CXRs with various scoliosis severities and utilized the trained network as a feature extractor using the GAN inversion method. Second, we classified each vector from the latent space using a simple MLP. RESULTS The 2-layer MLP exhibited the best classification in the ablation study. With this model, the area under the receiver operating characteristic (AUROC) curves were 0.850 in the internal and 0.847 in the external datasets. Furthermore, when the sensitivity was fixed at 0.9, the model's specificity was 0.697 in the internal and 0.646 in the external datasets. CONCLUSION We developed a classifier for Adolescent idiopathic scoliosis (AIS) through generative representation learning. Our model shows good AUROC under screening chest radiographs in both the internal and external datasets. Our model has learned the spectral severity of AIS, enabling it to generate normal images even when trained solely on scoliosis radiographs.
Collapse
Affiliation(s)
- Jun Soo Lee
- Department of Industrial Engineering, Seoul National University, Seoul, Korea
| | - Keewon Shin
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Seung Min Ryu
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- Department of Orthopedic Surgery, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Seong Gyu Jegal
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Woojin Lee
- Department of Radiology, Hanyang University Hospital, Seoul, Korea
| | - Min A Yoon
- Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Gil-Sun Hong
- Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Sanghyun Paik
- Department of Radiology, Hanyang University Hospital, Seoul, Korea
| | - Namkug Kim
- Department of Convergence Medicine, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| |
Collapse
|