Re-Assessment of Applicability of Greulich and Pyle-Based Bone Age to Korean Children Using Manual and Deep Learning-Based Automated Method
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Purpose: To evaluate the applicability of Greulich-Pyle (GP) standards to bone age (BA) assessment in healthy Korean childrenusing manual and deep learning-based methods. Materials and Methods: We collected 485 hand radiographs of healthy children aged 2–17 years (262 boys) between 2008 and2017. Based on GP method, BA was assessed manually by two radiologists and automatically by two deep learning-based BA as sessment (DLBAA), which estimated GP-assigned (original model) and optimal (modified model) BAs. Estimated BA was com pared to chronological age (CA) using intraclass correlation (ICC), Bland-Altman analysis, linear regression, mean absolute error,and root mean square error. The proportion of children showing a difference >12 months between the estimated BA and CA wascalculated. Results: CA and all estimated BA showed excellent agreement (ICC ≥0.978, p<0.001) and significant positive linear correlations (R2≥0.935, p<0.001). The estimated BA of all methods showed systematic bias and tended to be lower than CA in younger patients, andhigher than CA in older patients (regression slopes ≤-0.11, p<0.001). The mean absolute error of radiologist 1, radiologist 2, origi nal, and modified DLBAA models were 13.09, 13.12, 11.52, and 11.31 months, respectively. The difference between estimatedBA and CA was >12 months in 44.3%, 44.5%, 39.2%, and 36.1% for radiologist 1, radiologist 2, original, and modified DLBAAmodels, respectively. Conclusion: Contemporary healthy Korean children showed different rates of skeletal development than GP standard-BA, andsystemic bias should be considered when determining children’s skeletal maturation.
Abstract
Purpose: To evaluate the applicability of Greulich-Pyle (GP) standards to bone age (BA) assessment in healthy Korean childrenusing manual and deep learning-based methods. Materials and Methods: We collected 485 hand radiographs of healthy children aged 2–17 years (262 boys) between 2008 and2017. Based on GP method, BA was assessed manually by two radiologists and automatically by two deep learning-based BA as sessment (DLBAA), which estimated GP-assigned (original model) and optimal (modified model) BAs. Estimated BA was com pared to chronological age (CA) using intraclass correlation (ICC), Bland-Altman analysis, linear regression, mean absolute error,and root mean square error. The proportion of children showing a difference >12 months between the estimated BA and CA wascalculated. Results: CA and all estimated BA showed excellent agreement (ICC ≥0.978, p<0.001) and significant positive linear correlations (R2≥0.935, p<0.001). The estimated BA of all methods showed systematic bias and tended to be lower than CA in younger patients, andhigher than CA in older patients (regression slopes ≤-0.11, p<0.001). The mean absolute error of radiologist 1, radiologist 2, origi nal, and modified DLBAA models were 13.09, 13.12, 11.52, and 11.31 months, respectively. The difference between estimatedBA and CA was >12 months in 44.3%, 44.5%, 39.2%, and 36.1% for radiologist 1, radiologist 2, original, and modified DLBAAmodels, respectively. Conclusion: Contemporary healthy Korean children showed different rates of skeletal development than GP standard-BA, andsystemic bias should be considered when determining children’s skeletal maturation.
참고문헌 (21)
- Kelly PM, "Lower-limb growth : how predictable are predictions?", J Child Orthop, 2, pp.407~415 (2008)
- Creo AL, "Bone age : a handy tool for pediatric providers", Pediatrics, 140, pp.e20171486~ (2017)
- Greulich WW, "Radiographic atlas of skeletal development of the hand and wrist" (1959), Stanford University Press
- Breen MA, "Bone age assessment practices in infants and older children among Society for Pediatric Radiology members", Pediatr Radiol, 46, pp.1269~1274 (2016)
- Pan I, "Rethinking Greulich and Pyle : a deep learning approach to pediatric bone age assessment using pediatric trauma hand radiographs", Radiol Artif Intell, 2, pp.e190198~ (2020)
- Larson DB, "Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs", Radiology, 287, pp.313~322 (2018)
- Kim JR, "Computerized bone age estimation using deep learning based program : evaluation of the accuracy and efficiency", AJR Am J Roentgenol, 209, pp.1374~1380 (2017)
- 김정례, "Assessment of Bone Age in Prepubertal Healthy Korean Children: Comparison among the Korean Standard Bone Age Chart, Greulich-Pyle Method, and Tanner-Whitehouse Method", Korean Journal of Radiology, 16(1), pp.201~205 (2015), 대한영상의학회[DOI]
- Ontell FK, "Bone age in children of diverse ethnicity", AJR Am J Roentgenol, 167, pp.1395~1398 (1996)
- Alshamrani K, "Is the Greulich and Pyle atlas applicable to all ethnicities? A systematic review and meta-analysis", Eur Radiol, 29, pp.2910~2923 (2019)
- Zhang A, "Racial differences in growth patterns of children assessed on the basis of bone age", Radiology, 250, pp.228~235 (2009)
- Hackman L, "The reliability of the Greulich and Pyle atlas when applied to a modern Scottish population", J Forensic Sci, 58, pp.114~119 (2013)
- Alshamrani K, "Applicability of two commonly used bone age assessment methods to twenty-first century UK children", Eur Radiol, 30, pp.504~513 (2020)
- 김수영, "골연령 측정시 Greulich-Pyle 방법과Tanner-Whitehouse (TW3) 방법의 비교", Annals of Pediatric Endocrinology & Metabolism, 13(1), pp.50~55 (2008), 대한소아내분비학회
- Hallgren KA, "Computing inter-rater reliability for observational data : an overview and tutorial", Tutor Quant Methods Psychol, 8, pp.23~34 (2012)
- Chai T, "Root mean square error(RMSE)or mean absolute error(MAE)?–Arguments against avoiding RMSE in the literature", Geosci Model Dev, 7, pp.1247~1250 (2014)
- Tajmir SH, "Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability", Skeletal Radiol, 48, pp.275~283 (2019)
- Min-Su Oh, "Factors associated with Advanced Bone Age in Overweight and Obese Children", Pediatric Gastroenterology, Hepatology & Nutrition, 23(1), pp.89~97 (2020), 대한소아소화기영양학회[DOI]
- Doosoo Kim, "Diagnosis and constitutional and laboratory features of Korean girls referred for precocious puberty", Clinical and Experimental Pediatrics, 55(12), pp.481~486 (2012), 대한소아청소년과학회
- Martin DD, "The use of bone age in clinical practice-part 1", Horm Res Paediatr, 76, pp.1~9 (2011)
- Gilsanz V, "Hand bone age: a digital atlas of skeletal maturity" (2005), Springer