Kyung-Sik Ahn1, Byeonguk Bae2, Woo Young Jang3, Jin Hyuck Lee4, Saelin Oh1, Baek Hyun Kim5, Si Wook Lee6, Hae Woon Jung7, Jae Won Lee2, Jinkyeong Sung2, Kyu-Hwan Jung2, Chang Ho Kang1, Soon Hyuck Lee8. 1. Department of Radiology, Korea University Anam Hospital, Seoul, Republic of Korea. 2. VUNO, Inc., Seoul, Republic of Korea. 3. Department of Orthopedic Surgery, Korea University Anam Hospital, 73, Goryeodae-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea. opmanse@gmail.com. 4. Department of Sports Medicine, Anam Hospital, Korea University College of Medicine, Seoul, Republic of Korea. 5. Department of Radiology, Korea University Ansan Hospital, Gyeonggi-do, Republic of Korea. 6. Department of Orthopedic Surgery, Keimyung University, School of Medicine, Dongsan Medical Center, Daegu, Republic of Korea. 7. Department of Pediatrics, Kyung Hee University Hospital, Seoul, Republic of Korea. 8. Department of Orthopedic Surgery, Korea University Anam Hospital, 73, Goryeodae-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea.
Abstract
OBJECTIVES: Bone age is considered an indicator for the diagnosis of precocious or delayed puberty and a predictor of adult height. We aimed to evaluate the performance of a deep neural network model in assessing rapidly advancing bone age during puberty using elbow radiographs. METHODS: In all, 4437 anteroposterior and lateral pairs of elbow radiographs were obtained from pubertal individuals from two institutions to implement and validate a deep neural network model. The reference standard bone age was established by five trained researchers using the Sauvegrain method, a scoring system based on the shapes of the lateral condyle, trochlea, olecranon apophysis, and proximal radial epiphysis. A test set (n = 141) was obtained from an external institution. The differences between the assessment of the model and that of reviewers were compared. RESULTS: The mean absolute difference (MAD) in bone age estimation between the model and reviewers was 0.15 years on internal validation. In the test set, the MAD between the model and the five experts ranged from 0.19 to 0.30 years. Compared with the reference standard, the MAD was 0.22 years. Interobserver agreement was excellent among reviewers (ICC: 0.99) and between the model and the reviewers (ICC: 0.98). In the subpart analysis, the olecranon apophysis exhibited the highest accuracy (74.5%), followed by the trochlea (73.7%), lateral condyle (73.7%), and radial epiphysis (63.1%). CONCLUSIONS: Assessment of rapidly advancing bone age during puberty on elbow radiographs using our deep neural network model was similar to that of experts. KEY POINTS: • Bone age during puberty is particularly important for patients with scoliosis or limb-length discrepancy to determine the phase of the disease, which influences the timing and method of surgery. • The commonly used hand radiographs-based methods have limitations in assessing bone age during puberty due to the less prominent morphological changes of the hand and wrist bones in this period. • A deep neural network model trained with elbow radiographs exhibited similar performance to human experts on estimating rapidly advancing bone age during puberty.
OBJECTIVES: Bone age is considered an indicator for the diagnosis of precocious or delayed puberty and a predictor of adult height. We aimed to evaluate the performance of a deep neural network model in assessing rapidly advancing bone age during puberty using elbow radiographs. METHODS: In all, 4437 anteroposterior and lateral pairs of elbow radiographs were obtained from pubertal individuals from two institutions to implement and validate a deep neural network model. The reference standard bone age was established by five trained researchers using the Sauvegrain method, a scoring system based on the shapes of the lateral condyle, trochlea, olecranon apophysis, and proximal radial epiphysis. A test set (n = 141) was obtained from an external institution. The differences between the assessment of the model and that of reviewers were compared. RESULTS: The mean absolute difference (MAD) in bone age estimation between the model and reviewers was 0.15 years on internal validation. In the test set, the MAD between the model and the five experts ranged from 0.19 to 0.30 years. Compared with the reference standard, the MAD was 0.22 years. Interobserver agreement was excellent among reviewers (ICC: 0.99) and between the model and the reviewers (ICC: 0.98). In the subpart analysis, the olecranon apophysis exhibited the highest accuracy (74.5%), followed by the trochlea (73.7%), lateral condyle (73.7%), and radial epiphysis (63.1%). CONCLUSIONS: Assessment of rapidly advancing bone age during puberty on elbow radiographs using our deep neural network model was similar to that of experts. KEY POINTS: • Bone age during puberty is particularly important for patients with scoliosis or limb-length discrepancy to determine the phase of the disease, which influences the timing and method of surgery. • The commonly used hand radiographs-based methods have limitations in assessing bone age during puberty due to the less prominent morphological changes of the hand and wrist bones in this period. • A deep neural network model trained with elbow radiographs exhibited similar performance to human experts on estimating rapidly advancing bone age during puberty.
Authors: Nakul E Reddy; Jesse C Rayan; Ananth V Annapragada; Nadia F Mahmood; Alan E Scheslinger; Wei Zhang; J Herman Kan Journal: Pediatr Radiol Date: 2019-12-20
Authors: David B Larson; Matthew C Chen; Matthew P Lungren; Safwan S Halabi; Nicholas V Stence; Curtis P Langlotz Journal: Radiology Date: 2017-11-02 Impact factor: 11.105
Authors: Ana Luiza Dallora; Peter Anderberg; Ola Kvist; Emilia Mendes; Sandra Diaz Ruiz; Johan Sanmartin Berglund Journal: PLoS One Date: 2019-07-25 Impact factor: 3.240