Detection of Cervical Foraminal Stenosis from Oblique Radiograph Using Convolutional Neural Network Algorithm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: This study was conducted to develop a convolutional neural network (CNN) algorithm that can diagnose cervical foraminal stenosis using oblique radiographs and evaluate its accuracy. Materials and Methods: A total of 997 patients who underwent cervical MRI and cervical oblique radiographs within a 3-month interval were included. Oblique radiographs were labeled as “foraminal stenosis” or “no foraminal stenosis” according to whether foraminal stenosis was present in the C2–T1 levels based on MRI evaluation as ground truth. The CNN model involved data augmentation, image preprocessing, and transfer learning using DenseNet161. Visualization of the location of the CNN model was performed using gradient-weight class activation mapping (Grad-CAM). Results: The area under the curve (AUC) of the receiver operating characteristic curve based on DenseNet161 was 0.889 (95% confidence interval, 0.851–0.927). The F1 score, accuracy, precision, and recall were 88.5%, 84.6%, 88.1%, and 88.5%, respectively. The accuracy of the proposed CNN model was significantly higher than that of two orthopedic surgeons (64.0%, p<0.001; 58.0%, p<0.001). Grad-CAM analysis demonstrated that the CNN model most frequently focused on the foramen location for the determination of foraminal stenosis, although disc space was also frequently taken into consideration. Conclusion: A CNN algorithm that can detect neural foraminal stenosis in cervical oblique radiographs was developed. The AUC, F1 score, and accuracy were 0.889, 88.5%, and 84.6%, respectively. With the current CNN model, cervical oblique radiography could be a more effective screening tool for neural foraminal stenosis.
Abstract
Purpose: This study was conducted to develop a convolutional neural network (CNN) algorithm that can diagnose cervical foraminal stenosis using oblique radiographs and evaluate its accuracy. Materials and Methods: A total of 997 patients who underwent cervical MRI and cervical oblique radiographs within a 3-month interval were included. Oblique radiographs were labeled as “foraminal stenosis” or “no foraminal stenosis” according to whether foraminal stenosis was present in the C2–T1 levels based on MRI evaluation as ground truth. The CNN model involved data augmentation, image preprocessing, and transfer learning using DenseNet161. Visualization of the location of the CNN model was performed using gradient-weight class activation mapping (Grad-CAM). Results: The area under the curve (AUC) of the receiver operating characteristic curve based on DenseNet161 was 0.889 (95% confidence interval, 0.851–0.927). The F1 score, accuracy, precision, and recall were 88.5%, 84.6%, 88.1%, and 88.5%, respectively. The accuracy of the proposed CNN model was significantly higher than that of two orthopedic surgeons (64.0%, p<0.001; 58.0%, p<0.001). Grad-CAM analysis demonstrated that the CNN model most frequently focused on the foramen location for the determination of foraminal stenosis, although disc space was also frequently taken into consideration. Conclusion: A CNN algorithm that can detect neural foraminal stenosis in cervical oblique radiographs was developed. The AUC, F1 score, and accuracy were 0.889, 88.5%, and 84.6%, respectively. With the current CNN model, cervical oblique radiography could be a more effective screening tool for neural foraminal stenosis.
참고문헌 (30)
- Enomoto K, "Usefulness of simultaneous magnetic resonance neurography and apparent T2 mapping for the diagnosis of cervical radiculopathy", Asian Spine J, 16, pp.47~55 (2022)
- Meacock J, "Systematic review of radiological cervical foraminal grading systems", Neuroradiology, 63, pp.305~316 (2021)
- Lee DH, "Foraminal restenosis after posterior cervical foraminotomy for the treatment of cervical radiculopathy", Global Spine J, 13, pp.2357~2366 (2023)
- Kim GU, "Diagnostic technology for spine pathology", Asian Spine J, 16, pp.764~775 (2022)
- Schell A, "Assessing foraminal stenosis in the cervical spine : a comparison of three-dimensional computed tomographic surface reconstruction to twodimensional modalities", Global Spine J, 7, pp.266~271 (2017)
- Kim T, "Diagnostic triage in patients with central lumbar spinal stenosis using a deep learning system of radiographs", J Neurosurg Spine, 37, pp.104~111 (2022)
- Saifuddin A, "The imaging of lumbar spinal stenosis", Clin Radiol, 55, pp.581~594 (2000)
- Kang KC, "Cervical radiculopathy focus on characteristics and differential diagnosis", Asian Spine J, 14, pp.921~930 (2020)
- Park S, "Assessment of fusion after anterior cervical discectomy and fusion using convolutional neural network algorithm", Spine(Phila Pa 1976), 47, pp.1645~1650 (2022)
- Miura M, "Automated detection of cervical ossification of the posterior longitudinal ligament in plain lateral radiographs of the cervical spine using a convolutional neural network", Sci Rep, 11, pp.12702~ (2021)
- Lee GW, "Deep learning algorithm to evaluate cervical spondylotic myelopathy using lateral cervical spine radiograph", BMC Neurol, 22, pp.147~ (2022)
- Hallinan JTPD, "Deep learning model for automated detection and classification of central canal, lateral recess, and neural foraminal stenosis at lumbar spine MRI", Radiology, 300, pp.130~138 (2021)
- Ogawa T, "Detecting ossification of the posterior longitudinal ligament on plain radiographs using a deep convolutional neural network : a pilot study", Spine J, 22, pp.934~940 (2022)
- Koo BS, "A pilot study on deep learning-based grading of corners of vertebral bodies for assessment of radiographic progression in patients with ankylosing spondylitis", Ther Adv Musculoskelet Dis, 14, pp.1759720X221114097~ (2022)
- Yamada Y, "Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy : ensemble decision-making with antero-posterior and lateral radiographs", Acta Orthop, 91, pp.699~704 (2020)
- Park J, "Deep learning-based approaches for classifying foraminal stenosis using cervical spine radiographs", Electronics, 12, pp.195~ (2023)
- Lee JE, "Interreader reliability and clinical validity of a magnetic resonance imaging grading system for cervical foraminal stenosis", J Comput Assist Tomogr, 41, pp.926~930 (2017)
- Lee KH, "Inter-observer reliability and clinical validity of the MRI grading system for cervical central stenosis based on sagittal T2-weighted image", Eur J Radiol, 127, pp.108987~ (2020)
- Meng M, "Detection and classification of breast lesions with You Only Look Once version 5", Future Oncol, 18, pp.4361~4370 (2022)
- Mehdizadeh M, "Evaluation of histogram equalization and contrast limited adaptive histogram equalization effect on image quality and fractal dimensions of digital periapical radiographs", Oral Radiol, 39, pp.418~424 (2023)
- Subramani B, "Fuzzy gray level difference histogram equalization for medical image enhancement", J Med Syst, 44, pp.103~ (2020)
- Al-Rasheed A, "An ensemble of transfer learning models for the prediction of skin cancers with conditional generative adversarial networks", Diagnostics(Basel), 12, pp.3145~ (2022)
- Vaiyapuri T, "Design of a honey badger optimization algorithm with a deep transfer learning-based osteosarcoma classification model", Cancers(Basel), 14, pp.6066~ (2022)
- DeLong ER, "Comparing the areas under two or more correlated receiver operating characteristic curves : a nonparametric approach", Biometrics, 44, pp.837~845 (1988)
- Yang C, "Visual explanations from deep 3D convolutional neural networks for Alzheimer’s disease classification", AMIA Annu Symp Proc, 2018, pp.1571~1580 (2018)
- Mandrekar JN, "Receiver operating characteristic curve in diagnostic test assessment", J Thorac Oncol, 5, pp.1315~1316 (2010)
- Lin CH, "The comparison of multiple F-wave variable studies and magnetic resonance imaging examinations in the assessment of cervical radiculopathy", Am J Phys Med Rehabil, 92, pp.737~745 (2013)
- Maduri R, "Transtubular anterior cervical foraminotomy for the treatment of compressive cervical radiculopathy : surgical results and complications in a consecutive series of cases", Asian Spine J, 15, pp.673~681 (2021)
- Kane PM, "Double crush syndrome", J Am Acad Orthop Surg, 23, pp.558~562 (2015)
- Sohn HM, "The relationship between disc degeneration and morphologic changes in the intervertebral foramen of the cervical spine : a cadaveric MRI and CT study", J Korean Med Sci, 19, pp.101~106 (2004)