Automatic Segmentation and Radiologic Measurement of Distal Radius Fractures Using Deep Learning
Clinics in Orthopedic Surgery · 2024
DOI: 10.4055/cios23130 ↗At a glance
Journal article in Clinics in Orthopedic Surgery, 2024. Written by Sanglim Lee and 6 co-authors. Institution: Department of Orthopedic Surgery, Inje University Sanggye Paik Hospital, Seoul, Korea. Major MEDLINE topics: Radius Fractures, Wrist Fractures, Deep Learning. Cited 10 times so far (Crossref); 19 references. The full text is freely available (open access, CC BY-NC 4.0).
Abstract (original language)
Background
Recently, deep learning techniques have been used in medical imaging studies. We present an algorithm that measures radiologic parameters of distal radius fractures using a deep learning technique and compares the predicted parameters with those measured by an orthopedic hand surgeon.
Methods
We collected anteroposterior (AP) and lateral X-ray images of 634 wrists in 624 patients with distal radius fractures treated conservatively with a follow-up of at least 2 months. We allocated 507 AP and 507 lateral images to the training set (80% of the images were used to train the model, and 20% were utilized for validation) and 127 AP and 127 lateral images to the test set. The margins of the radius and ulna were annotated for ground truth, and the scaphoid in the lateral views was annotated in the box configuration to determine the volar side of the images. Radius segmentation was performed using attention U-Net, and the volar/dorsal side was identified using a detection and classification model based on RetinaNet. The proposed algorithm measures the radial inclination, dorsal or volar tilt, and radial height by index axes and points from the segmented radius and ulna.
Results
The segmentation model for the radius exhibited an accuracy of 99.98% and a Dice similarity coefficient (DSC) of 98.07% for AP images, and an accuracy of 99.75% and a DSC of 94.84% for lateral images. The segmentation model for the ulna showed an accuracy of 99.84% and a DSC of 96.48%. Based on the comparison of the radial inclinations measured by the algorithm and the manual method, the Pearson correlation coefficient was 0.952, and the intraclass correlation coefficient was 0.975. For dorsal/volar tilt, the correlation coefficient was 0.940, and the intraclass correlation coefficient was 0.968. For radial height, it was 0.768 and 0.868, respectively.
Conclusions
The deep learning-based algorithm demonstrated excellent segmentation of the distal radius and ulna in AP and lateral radiographs of the wrist with distal radius fractures and afforded automatic measurements of radiologic parameters.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Orthopedic Surgery, Inje University Sanggye Paik Hospital, Seoul, Korea.
- Department of Biomedical Engineering, Gachon University College of Medicine, Incheon, Korea.
- Department of Orthopaedic Surgery, National Medical Center, Seoul, Korea.
ORCID profiles: Sanglim Lee, Kwang Gi Kim, Young Jae Kim, Ji Soo Jeon, Gi Pyo Lee, Kyung-Chan Kim, Suk Ha Jeon
Cite
APA
Lee, S., Kim, K. G., Kim, Y. J., Jeon, J. S., Lee, G. P., Kim, K. C., & Jeon, S. H. (2024). Automatic Segmentation and Radiologic Measurement of Distal Radius Fractures Using Deep Learning. Clinics in Orthopedic Surgery. https://doi.org/10.4055/cios23130
Vancouver
Lee S, Kim KG, Kim YJ, Jeon JS, Lee GP, Kim KC, et al. Automatic Segmentation and Radiologic Measurement of Distal Radius Fractures Using Deep Learning. Clinics in Orthopedic Surgery. 2024. doi:10.4055/cios23130
BibTeX
@article{Lee2024,
author = {Lee, Sanglim and Kim, Kwang Gi and Kim, Young Jae and Jeon, Ji Soo and Lee, Gi Pyo and Kim, Kyung-Chan and Jeon, Suk Ha},
title = {Automatic Segmentation and Radiologic Measurement of Distal Radius Fractures Using Deep Learning},
journal = {Clinics in Orthopedic Surgery},
year = {2024},
doi = {10.4055/cios23130}
}
EUVIMED