• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.187-201
• /
• 2024

Osteoporosis is a major health issue globally, often remaining undetected until a fracture occurs. To facilitate early detection, deep learning (DL) models were developed to classify osteoporosis using abdominal computed tomography (CT) scans. This study was conducted using retrospectively collected data from 3,012 contrast-enhanced abdominal CT scans. The DL models developed in this study were constructed for using image data, demographic/clinical information, and multi-modality data, respectively. Patients were categorized into the normal, osteopenia, and osteoporosis groups based on their T-scores, obtained from dual-energy X-ray absorptiometry, into normal, osteopenia, and osteoporosis groups. The models showed high accuracy and effectiveness, with the combined data model performing the best, achieving an area under the receiver operating characteristic curve of 0.94 and an accuracy of 0.80. The image-based model also performed well, while the demographic data model had lower accuracy and effectiveness. In addition, the DL model was interpreted by gradient-weighted class activation mapping (Grad-CAM) to highlight clinically relevant features in the images, revealing the femoral neck as a common site for fractures. The study shows that DL can accurately identify osteoporosis stages from clinical data, indicating the potential of abdominal CT scans in early osteoporosis detection and reducing fracture risks with prompt treatment.

• Journal of Korean Orthopaedic Sports Medicine
• /
• v.10 no.2
• /
• pp.86-93
• /
• 2011

Purpose: The purpose of this study was to analyze the characteristics of the injuries of the national elite Taekwondo players with the best performance in the international championship competition. Materials and Methods: Fifty-two athletes who got the injury in the 2011 Gyeongju World Taekwondo Championship competition were included in this sturdy. 950 members of national team of 146 countries participated in this game, 1,063 matches were performed. We analyzed the characteristics of the injuries such as injury rate by gender, age, weight class, injured region and injury type. Results: Fifty-two athletes of 950 athletes in 1,063 matches got injured and injury rate was 5.47 per 100 participants and 24.47/1,000 athlete-exposures. Injury rate of female athletes was higher than mail, but there was no significant statistical difference (p=0.512). Injury rate of over 30 years old was 17.39 per 100 participants, and injury rate of over 87 kg in male weight class and 68 to 73kg in female weight class were highest than other groups, but there was no significant statistical difference (p=0.838). Overall injury rate of the lower extremity was 13.17/1,000 A-E, higher than upper extremity or head and neck or trunk, but injury rate of the hand was 5.17/1,000 A-E, highest as a specific injured region, followed by the knee, 4.70/1,000 A-E (p=0.714). Injury rate of the sprain was 10.81/1,000 A-E, highest as an injury type, the second most common injury type was the fracture, 5.40/1,000 A-E in men, and was the contusion, 9.63/1,000 A-E in women (p=0.033). As one of the most serious injury, 4 of 8 fractures were occurred in hand. Conclusion: Overall injury rate of the elite Taekwondo players in 2011 Gyeongju World Taekwondo Championship was 5.47 per 100 participants and 24.46 per 1,000 athlete exposures. Although the most common type of injury was the sprain of the knee and ankle, the fractures were more commonly occurred in hand.