한빛사 논문
Seok Won CHUNG1, Seung Seog HAN2, Ji Whan LEE1, Kyung-Soo OH1, Na Ra KIM3, Jong Pil YOON4, Joon Yub KIM5, Sung Hoon MOON6, Jieun KWON7, Hyo-Jin LEE8, Young-Min NOH9, and Youngjun KIM10,*
1Department of Orthopaedic Surgery and 3Department of Radiology, Konkuk University School of Medicine, Seoul; 2Department of Dermatology, I-dermatology clinic, Seoul ; 4Department of Orthopaedic Surgery, Kyungpook National University College of Medicine, Daegu, Korea; 5Department of Orthopaedic Surgery, Myungji Hospital, Goyang; 6Department of Orthopaedic Surgery, Kangwon National University College of Medicine, Chuncheon, Korea; 7Department of Othopaedic Surgery, National Police Hospital, Seoul; 8Department of Orthopaedic Surgery, Catholic University College of Medicine, Seoul, St Mary’s Hospital, Seoul, Korea; 9Department of Orthopaedic Surgery, Dong-A University College of Medicine, Pusan; 10Center for Bionics, Korea Institute of Science and Technology, Seoul, Korea
*Corresponding author
Abstract
Background and purpose — We aimed to evaluate the ability of artificial intelligence (a deep learning algorithm) to detect and classify proximal humerus fractures using plain anteroposterior shoulder radiographs.
Patients and methods — 1,891 images (1 image per person) of normal shoulders (n = 515) and 4 proximal humerus fracture types (greater tuberosity, 346; surgical neck, 514; 3-part, 269; 4-part, 247) classified by 3 specialists were evaluated. We trained a deep convolutional neural network (CNN) after augmentation of a training dataset. The ability of the CNN, as measured by top-1 accuracy, area under receiver operating characteristics curve (AUC), sensitivity/specificity, and Youden index, in comparison with humans (28 general physicians, 11 general orthopedists, and 19 orthopedists specialized in the shoulder) to detect and classify proximal humerus fractures was evaluated.
Results — The CNN showed a high performance of 96% top-1 accuracy, 1.00 AUC, 0.99/0.97 sensitivity/specificity, and 0.97 Youden index for distinguishing normal shoulders from proximal humerus fractures. In addition, the CNN showed promising results with 65–86% top-1 accuracy, 0.90–0.98 AUC, 0.88/0.83–0.97/0.94 sensitivity/specificity, and 0.71–0.90 Youden index for classifying fracture type. When compared with the human groups, the CNN showed superior performance to that of general physicians and orthopedists, similar performance to orthopedists specialized in the shoulder, and the superior performance of the CNN was more marked in complex 3- and 4-part fractures.
Interpretation — The use of artificial intelligence can accurately detect and classify proximal humerus fractures on plain shoulder AP radiographs. Further studies are necessary to determine the feasibility of applying artificial intelligence in the clinic and whether its use could improve care and outcomes compared with current orthopedic assessments.
논문정보
관련 링크
연구자 키워드
연구자 ID
관련분야 연구자보기
소속기관 논문보기
관련분야 논문보기
해당논문 저자보기