Cross-Center Validation of Deep Learning Model for Musculoskeletal Fracture Detection in Radiographic Imaging: A Feasibility Study

HRUBÝ, Robert, Daniel KVAK, Jakub DANDÁR, Anora ATAKHANOVA, Matěj MISAŘ a Daniel DUFEK. Cross-Center Validation of Deep Learning Model for Musculoskeletal Fracture Detection in Radiographic Imaging: A Feasibility Study. MedRxiv - The Preprint Server for Health Sciences. Cold Spring Harbor Laboratory: Yale, BMJ, and Cold Spring Harbor Lab., 2024, s. 1-9. Dostupné z: https://dx.doi.org/10.1101/2024.01.17.24301244.

Základní údaje

• Originální název: Cross-Center Validation of Deep Learning Model for Musculoskeletal Fracture Detection in Radiographic Imaging: A Feasibility Study
• Autoři: HRUBÝ, Robert, Daniel KVAK, Jakub DANDÁR, Anora ATAKHANOVA, Matěj MISAŘ a Daniel DUFEK.
• Vydání: MedRxiv - The Preprint Server for Health Sciences, Cold Spring Harbor Laboratory, Yale, BMJ, and Cold Spring Harbor Lab. 2024.

Další údaje

• Typ výsledku: Článek v odborném periodiku (nerecenzovaný)
• Utajení: není předmětem státního či obchodního tajemství
• WWW: URL
• Doi: http://dx.doi.org/10.1101/2024.01.17.24301244
• Klíčová slova anglicky: Bone Fracture, Computer-Aided Detection, Deep Learning, Musculoskeletal X-ray, YOLO

Anotace

Fractures, often resulting from trauma, overuse, or osteoporosis, pose diagnostic challenges due to their variable clinical manifestations. To address this, we propose a deep learning-based decision support system to enhance the efficacy of fracture detection in radiographic imaging. For the purpose of our study, we utilized 720 annotated musculoskeletal (MSK) X-rays from the MURA dataset, augmented by bounding box-level annotation, for training the YOLO (You Only Look Once) model. The model's performance was subsequently tested on two datasets, sampled FracAtlas dataset (Dataset 1, 840 images, n_NORMAL=696, n_FRACTURE=144) and our own internal dataset (Dataset 2, 124 images, n_NORMAL=50, n_FRACTURE=74), encompassing a diverse range of MSK radiographs. The results showed a Sensitivity (Se) of 0.910 (95% CI: 0.852-0.946) and Specificity (Sp) of 0.557 (95% CI: 0.520-0.594) on Dataset 1, and a Se of 0.622 (95% CI: 0.508-0.724) and Sp of 0.740 (95% CI: 0.604-0.841) on Dataset 2. This study underscores the promising role of AI in medical imaging, providing a solid foundation for future research and advancements in the field of radiographic diagnostics.