Diagnostic performance of convolutional neural network-based Tanner-Whitehouse 3 bone age assessment system

Zhou, Xuelian; Wang, Ergang; Lin, Qiang; Dong, Guanping; Wu, Wei; Lai, Can; Yu, Gang; Zhou, Haichun; Ma, Xiaomeng; Jia, Xiuzhi; Shi, Lei; Zheng, Yongsheng; Liu, Lan-Xuan; Ha, Da; Ni, Hao; Yang, Jun; Fu, Junfen

doi:10.21037/qims.2020.02.20

Cited by 28 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another key finding was that AI assistance decreased MAE for specific bones, the first and fifth proximal phalanges, among bone age assessments performed by physicians of all levels of experience including senior, mid-level, and junior physicians. Similar results were reported by Xue-Lian Zhou and colleagues ( 25 ): human interpretations of particular bones, male capitate, hamate, the first distal and fifth middle phalanx and female capitate, the trapezoid, and the third and fifth middle phalanx, were the most inconsistent. This is likely because the China 05 RUS-CHN method is subjective—there is no standard regarding which bone should be weighted or relied upon more during the assessment ( 8 ).…”

Section: Ai-assisted Bone Age Assessmentsupporting

confidence: 87%

Artificial Intelligence–Assisted Bone Age Assessment to Improve the Accuracy and Consistency of Physicians With Different Levels of Experience

Zhou

Gong³

et al. 2022

Front. Pediatr.

View full text Add to dashboard Cite

BackgroundThe accuracy and consistency of bone age assessments (BAA) using standard methods can vary with physicians' level of experience.MethodsTo assess the impact of information from an artificial intelligence (AI) deep learning convolutional neural network (CNN) model on BAA, specialists with different levels of experience (junior, mid-level, and senior) assessed radiographs from 316 children aged 4–18 years that had been randomly divided into two equal sets-group A and group B. Bone age (BA) was assessed independently by each specialist without additional information (group A) and with information from the model (group B). With the mean assessment of four experts as the reference standard, mean absolute error (MAE), and intraclass correlation coefficient (ICC) were calculated to evaluate accuracy and consistency. Individual assessments of 13 bones (radius, ulna, and short bones) were also compared between group A and group B with the rank-sum test.ResultsThe accuracies of senior, mid-level, and junior physicians were significantly better (all P < 0.001) with AI assistance (MAEs 0.325, 0.344, and 0.370, respectively) than without AI assistance (MAEs 0.403, 0.469, and 0.755, respectively). Moreover, for senior, mid-level, and junior physicians, consistency was significantly higher (all P < 0.001) with AI assistance (ICCs 0.996, 0.996, and 0.992, respectively) than without AI assistance (ICCs 0.987, 0.989, and 0.941, respectively). For all levels of experience, accuracy with AI assistance was significantly better than accuracy without AI assistance for assessments of the first and fifth proximal phalanges.ConclusionsInformation from an AI model improves both the accuracy and the consistency of bone age assessments for physicians of all levels of experience. The first and fifth proximal phalanges are difficult to assess, and they should be paid more attention.

show abstract

Section: Ai-assisted Bone Age Assessmentsupporting

confidence: 87%

Artificial Intelligence–Assisted Bone Age Assessment to Improve the Accuracy and Consistency of Physicians With Different Levels of Experience

Zhou

Gong³

et al. 2022

Front. Pediatr.

View full text Add to dashboard Cite

show abstract

“…At present, several studies have addressed this issue, but none of them have conducted reliability tests on reviewers who labeled radiographs. 16,23 Herein, this study organized the relevant reliability tests on bone age assessments, and radiologists' performance, including interobserver and intraobserver agreement, fell within that range referring to international reliability studies on the TW method, indicating that our reviewers performed similarly to other international manual raters.…”

Section: Resultsmentioning

confidence: 79%

“…Recently, Larson et al 12 developed an automated bone age system based on the G-P atlas, which was similar to that of an expert radiologist, reaching an RMS of 0.63 years. Zhou et al 16 proposed a carpal bone age system using deep learning with 0.5 years of RMS, compared with 0.32 years for our model. However, the differences in test sets and bone age evaluation methods made it difficult to compare the accuracy of our model with that of these models.…”

Section: Resultsmentioning

confidence: 99%

Construction of artificial intelligence system of carpal bone age for Chinese children based on China‐05 standard

et al. 2022

View full text Add to dashboard Cite

The purpose of this study is to construct an automatic carpal bone age evaluation system for Chinese children based on TW3-C Carpal method by deep learning and to evaluate the accuracies in test set and clinical test set. Methods: A total of 8184 radiographs of Chinese Han healthy children (2-14 years old) were collected from the 2005 China Skeletal Development Survey data and from the accumulated radiographs in bone age studies over the years. Three experienced radiologists and the China-05 standard maker jointly evaluated each bone development stage, and the consensual stage was decided as the reference standard. According to each epiphysis development stage, 10% of them were derived by stratified random sampling as test sets, and the remaining radiographs were used as training sets and validation sets. Furthermore, the overall performance of the model was estimated by comparing the mean difference, 95% limits of agreement, mean absolute difference (MAD) and root mean square (RMS) between the model predictions and the reference standard. Results:The percentage agreement of ratings in each epiphysis in the test set ranged from 82.82% to 90.06%, with an average of 86.94%. Compared with the reference standard, the automated bone age system has a mean difference of 0.01 years old, ± 0.45 years old in 95% confidence interval by single reading, an 85.93% percentage agreement of ratings, a 90.5% bone age accuracy rate, 0.20 years old of MAD, and 0.32 years old of RMS in the clinical test set. Conclusions: The automatic bone age system for Chinese children has a comparable accuracy and stable determination compared with experienced radiologists.

show abstract

“…The information of the bone age and gender of each individual in the Jishuitan database was also included in the annotation file. Moreover, as skeletal maturity scores can be converted into a bone age using a bone age table, the official model of BoNet (33), SIMBA (34), and Yitu-AICARE (35) were trained and tested on the Jishuitan database. The best performing models on the validation set were selected to conduct the comparative experiments.…”

Section: Smanet Compared With Other Networkmentioning

confidence: 99%

SMANet: multi-region ensemble of convolutional neural network model for skeletal maturity assessment

Zhang

Zhu

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Bone age assessment (BAA) is a crucial research topic in pediatric radiology. Interest in the development of automated methods for BAA is increasing. The current BAA algorithms based on deep learning have displayed the following deficiencies: (I) most methods involve end-to-end prediction, lacking integration with clinically interpretable methods; (II) BAA methods exhibit racial and geographical differences.Methods: A novel, automatic skeletal maturity assessment (SMA) method with clinically interpretable methods was proposed based on a multi-region ensemble of convolutional neural networks (CNNs). This method predicted skeletal maturity scores and thus assessed bone age by utilizing left-hand radiographs and key regional patches of clinical concern.Results: Experiments included 4,861 left-hand radiographs from the database of Beijing Jishuitan Hospital and revealed that the mean absolute error (MAE) was 31.4±0.19 points (skeletal maturity scores) and 0.45±0.13 years (bone age) for the carpal bones-series and 29.9±0.21 points and 0.43±0.17 years, respectively, for the radius, ulna, and short (RUS) bones series based on the Tanner-Whitehouse 3 (TW3) method. Conclusions:The proposed automatic SMA method, which was without racial and geographical influence, is a novel, automatic method for assessing childhood bone development by utilizing skeletal maturity.Furthermore, it provides a comparable performance to endocrinologists, with greater stability and efficiency.

show abstract

Diagnostic performance of convolutional neural network-based Tanner-Whitehouse 3 bone age assessment system

Cited by 28 publications

References 19 publications

Artificial Intelligence–Assisted Bone Age Assessment to Improve the Accuracy and Consistency of Physicians With Different Levels of Experience

Artificial Intelligence–Assisted Bone Age Assessment to Improve the Accuracy and Consistency of Physicians With Different Levels of Experience

Construction of artificial intelligence system of carpal bone age for Chinese children based on China‐05 standard

SMANet: multi-region ensemble of convolutional neural network model for skeletal maturity assessment

Contact Info

Product

Resources

About