Clinical Validation of a Deep Learning-Based Hybrid (Greulich-Pyle and Modified Tanner-Whitehouse) Method for Bone Age Assessment

Abstract

Objective To evaluate the accuracy and clinical efficacy of a hybrid Greulich-Pyle (GP) and modified Tanner-Whitehouse (TW) artificial intelligence (AI) model for bone age assessment. Materials and Methods A deep learning-based model was trained on an open dataset of multiple ethnicities. A total of 102 hand radiographs (51 male and 51 female; mean age ± standard deviation = 10.95 ± 2.37 years) from a single institution were selected for external validation. Three human experts performed bone age assessments based on the GP atlas to develop a reference standard. Two study radiologists performed bone age assessments with and without AI model assistance in two separate sessions, for which the reading time was recorded. The performance of the AI software was assessed by comparing the mean absolute difference between the AI-calculated bone age and the reference standard. The reading time was compared between reading with and without AI using a paired t test. Furthermore, the reliability between the two study radiologists' bone age assessments was assessed using intraclass correlation coefficients (ICCs), and the results were compared between reading with and without AI. Results The bone ages assessed by the experts and the AI model were not significantly different (11.39 ± 2.74 years and 11.35 ± 2.76 years, respectively, p = 0.31). The mean absolute difference was 0.39 years (95% confidence interval, 0.33–0.45 years) between the automated AI assessment and the reference standard. The mean reading time of the two study radiologists was reduced from 54.29 to 35.37 seconds with AI model assistance ( p < 0.001). The ICC of the two study radiologists slightly increased with AI model assistance (from 0.945 to 0.990). Conclusion The proposed AI model was accurate for assessing bone age. Furthermore, this model appeared to enhance the clinical efficacy by reducing the reading time and improving the inter-observer reliability.

An overview of deep learning applications in precocious puberty and thyroid dysfunction

“…Recently, Lee et al. ( 43 ) suggested a hybrid GP- and TW-based DL system. Two public datasets were used to train a CNN model: (1) 14,236 radiographs from RSNA ( 54 ) and (2) 1,375 radiographs from Digital ( 57 ).…”

Bone Age Assessment Based on Deep Convolutional Features and Fast Extreme Learning Machine Algorithm

“…Then, it is realized by recognizing the maturity of the bones through the changes of radiographic appearance. There exist two most typical methods for BAA, namely the Greulich-Pyle (GP) method and the Tanner-Whitehouse (TW) method (Lee et al, 2021;Shah et al, 2021). The former one is based on the hand atlas, and its reference dataset consists of a series of left-hand X-ray images derived from the middle socioeconomic class of Caucasian children from the Midwest region of the US from 1931 to 1942.…”

Effect of AI-assisted software on inter- and intra-observer variability for the X-ray bone age assessment of preschool children

“…With the rapid development of deep learning algorithms and the rapid improvement of computer hardware in the past few years, artificial intelligence AI-assisted diagnosis software has begun to be applied in hospitals, among which bone age AI-assisted software is one of the earliest [7][8][9][10][11][12]. AI-assisted diagnosis software for bone age has achieved good diagnostic performance [12][13][14][15][16][17]. Some studies have proven that the results of AI-assisted diagnosis software for bone age are as accurate as those of experts [13,15,18].…”

“…AI-assisted diagnosis software for bone age has achieved good diagnostic performance [12][13][14][15][16][17]. Some studies have proven that the results of AI-assisted diagnosis software for bone age are as accurate as those of experts [13,15,18]. While some shown that AI assistance improves the diagnostic accuracy rate of radiologists [12,15,17,19].…”