Clinical application differences between TW3-Carpal and TW3-RUS based artificial intelligence-assisted bone age assessment system: a real-world pilot study / 中华放射学杂志

Objective:To investigate the differences between Tanner-Whitehouse (TW)3-Carpal and TW3-RUS(radius, ulna and short bone)-based artificial intelligence (AI)-assisted bone age assessment system using real world data.Methods:The image data of 262 children who received X-ray examination of left wrist in the Affiliated Children′s Hospital, Capital Institute of Pediatrics from July to September 2021 were retrospectively collected. The AI bone age assistant methods based on TW3-RUS and TW3-Carpal criteria were used to obtain the bone age results, respectively. Two senior pediatric radiologists evaluated the bone age on the basis of TW3-RUS and TW3-Carpal criteria, and the averaged values of two reviewers was calculated and taken as the gold standard reference. The cases were stratified into six age groups at 3-year intervals according to the gold standard reference, including 1-3 ( n=10), 4-6 ( n=35), 7-9 ( n=70), 10-12 ( n=118), 13-15 ( n=27) and 16-18 ( n=2) years old groups. Intraclass correlation coefficient (ICC) was used to evaluate the consistency between AI results and the gold standard bone age results. Pearson correlation method was used to measure the reliability between AI results and the gold standard results. The difference of bone age results between using TW3-RUS and TW3-Carpal criteria in different age groups was compared using paired t-test. Results:As for the whole sample, the results based on TW3-RUS criteria were 8.9±3.1 years old for AI assessment and 8.7±2.9 years old for the golden standard reference, with the ICC of 0.983; and the results based on TW3-Carpal criteria were 8.7±3.0 years old for AI and 8.8±2.8 years old for the golden standard reference, with the ICC of 0.976. Positive correlation were found in both TW3-RUS ( r=0.985, P<0.001) and TW3-Carpal criteria groups ( r=0.978, P<0.001). There were significant differences between TW3-RUS and TW3-Carpal at age groups of 7-9( t=-3.36, P=0.001), 10-12( t=-1.77, P=0.046), and 13-15 years old ( t=1.84, P=0.040). The bone age assessment using TW3-RUS and TW3-Carpal criteria were both in good agreement with the gold standard reference in age group of 4-6 years old (ICC=0.929 and 0.940), as well as in age group of 7-9 years old (ICC=0.882 and 0.927, respectively), with the results using TW3-Carpal criteria were slightly higher. As for the age groups of 10-12 and 13-15 years old, the method using TW3-RUS criteria showed excellent agreement with the gold standard reference (ICC=0.962 and 0.963, respectively), which were better than the performance of method using TW3-Carpal criteria (ICC=0.744 and 0.605, respectively). Conclusions:AI-assisted bone age system based TW3-Carpal and TW3-RUS criteria both show good reliability and accuracy in the bone age measurements. The AI method based TW3-Carpal criteria shows better performance in age group of 4-9 years old, while the method based on TW3-RUS criteria may be better for children of age 10-15 years old.

Assessment of Bone Age in Prepubertal Healthy Korean Children: Comparison among the Korean Standard Bone Age Chart, Greulich-Pyle Method, and Tanner-Whitehouse Method

OBJECTIVE: To compare the reliability of the Greulich-Pyle (GP) method, Tanner-Whitehouse 3 (TW3) method and Korean standard bone age chart (KS) in the evaluation of bone age of prepubertal healthy Korean children. MATERIALS AND METHODS: Left hand-wrist radiographs of 212 prepubertal healthy Korean children aged 7 to 12 years, obtained for the evaluation of the traumatic injury in emergency department, were analyzed by two observers. Bone age was estimated using the GP method, TW3 method and KS, and was calculated in months. The correlation between bone age measured by each method and chronological age of each child was analyzed using Pearson correlation coefficient, scatterplot. The three methods were compared using one-way analysis of variance. RESULTS: Significant correlations were found between chronological age and bone age estimated by all three methods in whole group and in each gender (R2 ranged from 0.87 to 0.9, p 0.01). CONCLUSION: The KS, GP, and TW3 methods show good reliability in the evaluation of bone age of prepubertal healthy Korean children without significant difference between them. Any are useful for evaluation of bone age in prepubertal healthy Korean children.

Comparison of the Greulich-Pyle and Tanner Whitehouse (TW3) Methods in Bone Age Assessment / 대한소아내분비학회지

PURPOSE: The determination of skeletal age is important for the analysis of growth and growth disorders in children. The aim of this study is to investigate the difference of bone age comparing Greulich-Pyle (GP) and Tanner Whitehouse (TW3) methods. We also evaluated the reproducibility of results of each method by different observers (interobserver variation) and by same observer (intraobserver variation). METHODS: Bone ages were assessed from left hand-wrist radiographs of 200 children (108 males and 92 females) aged 7 to 15 years by GP and TW3 methods. To evaluate the reproducibility of each method, 102 radiographs were assessed independently by three observers and 100 radiographs were reassessed by one same observer using both methods. RESULTS: The average bone age by GP and TW3 were 10.65+/-2.24 years and 10.48+/-2.18 years, respectively (P<0.01). There is significant correlation between GP and TW3 methods (R(2)=0.94, P<0.01). The interobserver variation of GP and TW3 was not different significantly (0.51+/-0.44 years by GP vs 0.54+/-0.42 years by TW3). The intraobserver variation also was not different significantly (0.48+/-0.44 years by GP vs 0.45+/-0.37 years by TW3). CONCLUSION: Our data indicate that bone age by TW3 method was slightly younger than that by GP method but similar, and the reproducibility of both methods were not different. Therefore, both GP and TW3 methods are useful for estimation of bone age in Korea children.

Assessment of Bone Age: A comparison of the Greulich Pyle Method to the Tanner Whitehouse Method / 대한내분비학회지

BACKGROUND: Bone age measurements have clinical significance in estimation of growth status and prediction of final adult height. Mostly used methods of bone age measurements are Tanner Whitehouse method(TW2) and Greulich-Pyle method(OP). TW2 is known to be more accurate method in determining the bone age, compared to GP. But GP is being used more widely despite some shortcomings, because TW2 is time consuming and need special training. In this study, we observed the correlation between GP and TW2 to evaluate which bone age among three portions of hand and wrist[metacarpals and phalanges(GP1), carpal bones(GP2), distai radius and ulna (GP3)], measured by GP, was more correlated with the bone age, measured by TW2. METHODS: Left hand/wrist radiographs were taken from 100 prepubertal children with normal growth. These radiogrphs were reviewed by two pediatric endocrinologists independently. Bone ages using TW2 were measured at first, and then GP1, GP2, and GP3 were measured. These bone ages had been compared with TW2, using SAS computer program. RESULTS: The mean chronological age of 100 children was 10.0+/-2.5 years(5 years to 14.7 years range, 63 males and 37 females). The bone age by TW2 was 9.0+/- 2.6 years(2.3 to 13.6 years). The bone age by GP1, GP2, and GP3 were 8.8+/-2.5 years, 8.7+/-2.9 years, and 8.3+/-2.8 years, respectively. Bone ages by TW2 were significantly closer to the chronological age than those by GP. The Pea~rson correlation coefficients of GP1, GP2, and GP3 in eomparison to TW2 were 0,87(p=0.0001), 0.94(p=0.0001), and 0.91(p=0.0001), respectively, There are significant correlatkm between bone ages by TW2 and GP. Bone ages by GP2 and GP3 were statistically significantly different from those by TW2(P<0.01). Bone ages by GP1 has no statistical difference with that by TW2(P=0.64). CONCLUSION: TW2 method is more accurate than GP method in determining the bone age, but it needs time-consuming and laborious efforts. We suggest that the use of GP method for the metacarpals and phalanges can result in a considerable saving of time with no significant loss of accuracy and reproducibility.