YOLOv8-Seg: A Deep Learning Approach for Accurate Classification of Osteoporotic Vertebral Fractures

Abstract

The abstract of the article presents a study focused on the application of deep learning for the classification of osteoporotic vertebral fractures (OVF), a growing health concern among the elderly. The research aimed to explore the potential of deep learning to assist in diagnosing OVF, evaluate the clinical viability of this method, and enhance recovery rates. A dataset comprising 643 CT images of OVF from patients admitted between March 2013 and May 2023 was collected and classified according to the European Vertebral Osteoporosis Study Group (EVOSG) spine classification system. Of these, 613 images were utilized for training and validating a deep learning model, while 30 images served as a test set to assess the model's performance against clinician diagnoses. The deep learning system achieved an impressive 85.9% accuracy rate in classifying fractures according to the EVOSG criteria. The study concludes that deep learning offers a high degree of accuracy in identifying OVF from CT images, which could streamline and improve the current manual diagnostic process that is often complex and challenging. The study also introduces the YOLOv8-Seg model, a novel classification method designed to enhance the diagnostic capabilities for OVF. The use of deep learning in this context is positioned as a significant advancement with the potential to support medical professionals in making early and precise diagnoses, thereby improving patient outcomes. Key terms highlighted in the abstract include deep learning, osteoporotic vertebral fracture, and YOLOv8, indicating the integration of advanced technology in medical diagnosis.