Development of a YOLOv3-Based Model for Automated Detection of Thoracic Ossification of the Posterior Longitudinal Ligament and the Ligamentum Flavum on Plain Radiographs
Authors:
- Sadayuki ItoSISadayuki Ito
- Hiroaki NakashimaHNHiroaki Nakashima
- Naoki SegiNSNaoki Segi
- Jun OuchidaJOJun Ouchida
- Ippei YamauchiIYIppei Yamauchi
- Takashi HiraiTHTakashi Hirai
- Masahiro OdaMOMasahiro Oda
- Kensaku MoriKMKensaku Mori
- Masashi YamazakiMasashi Yamazaki
- Toshitaka YoshiiTYToshitaka Yoshii
- Shiro ImagamaSIShiro Imagama
Open Access
- 31 March 2025
- journal article
- research article
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (7) , 2389
Abstract
Background/Objectives: This study aims to develop and validate a YOLOv3-based deep learning model for detecting ossification of the posterior longitudinal ligament (OPLL) and ossification of the ligamentum flavum (OLF) on lateral thoracic radiographs, improving early diagnosis and screening accessibility. Methods: A retrospective dataset of 356 lateral thoracic radiographs, including 176 with OPLL or OLF and 180 controls, was annotated by spine surgeons. The YOLOv3 model was trained using data augmentation and evaluated via five-fold cross-validation, with accuracy, precision, recall, and F1-score compared to two spine surgeons. Results: The model achieved 80.6% accuracy, 70.3% precision, 92.6% recall, and 79.9% F1-score, surpassing spine surgeons in accuracy and recall, especially for combined OPLL and OLF cases. Detection accuracy was 81.1% for OPLL, 53.3% for OLF, and 86.3% for combined cases. Conclusions: The YOLOv3-based model provides high accuracy and robust detection of OPLL and OLF on plain radiographs, offering an efficient and accessible screening tool.Keywords
Funding Information
- Japan Agency for Medical Research and Development (JP21ek0109541h0001, 40)
- Health and Labor Science Research Grants (JP21ek0109541h0001, 40)
This publication has 24 references indexed in Scilit:
- The Da Vinci Robot, a promising yet underused minimally invasive tool for spine surgery: A scoping review of its current role and limitsNeurochirurgie, 2024
- A systematic review of deep learning data augmentation in medical imaging: Recent advances and future research directionsHealthcare Analytics, 2024
- A deep learning algorithm to identify cervical ossification of posterior longitudinal ligaments on radiographyScientific Reports, 2022
- The impact of training sample size on deep learning-based organ auto-segmentation for head-and-neck patientsPhysics in Medicine & Biology, 2021
- Surgical outcomes in patients with mild symptoms, but severely compressed spinal cord from cervical ossification of the posterior longitudinal ligamentJournal of Clinical Neuroscience, 2016
- Ossification of the Posterior Longitudinal Ligament of the Cervical Spine in 3161 PatientsSpine, 2015
- Management of thoracic myelopathy caused by ossification of the posterior longitudinal ligament combined with ossification of the ligamentum flavum—a retrospective studyThe Spine Journal, 2012
- Two-staged decompression for thoracic paraparesis due to the combined ossification of the posterior longitudinal ligament and the ligamentum flavum: a case reportArchives of orthopaedic and trauma surgery, 2007
- Case report 779Skeletal Radiology, 1993
- Total decompression of the spinal cord for combined ossification of posterior longitudinal ligament and yellow ligament in the thoracic spineArchives of orthopaedic and trauma surgery, 1990