1
|
Kim KD, Kyung S, Jang M, Ji S, Lee DH, Yoon HM, Kim N. Enhancement of Non-Linear Deep Learning Model by Adjusting Confounding Variables for Bone Age Estimation in Pediatric Hand X-rays. J Digit Imaging 2023; 36:2003-2014. [PMID: 37268839 PMCID: PMC10501988 DOI: 10.1007/s10278-023-00849-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Revised: 05/08/2023] [Accepted: 05/10/2023] [Indexed: 06/04/2023] Open
Abstract
In medicine, confounding variables in a generalized linear model are often adjusted; however, these variables have not yet been exploited in a non-linear deep learning model. Sex plays important role in bone age estimation, and non-linear deep learning model reported their performances comparable to human experts. Therefore, we investigate the properties of using confounding variables in a non-linear deep learning model for bone age estimation in pediatric hand X-rays. The RSNA Pediatric Bone Age Challenge (2017) dataset is used to train deep learning models. The RSNA test dataset is used for internal validation, and 227 pediatric hand X-ray images with bone age, chronological age, and sex information from Asan Medical Center (AMC) for external validation. U-Net based autoencoder, U-Net multi-task learning (MTL), and auxiliary-accelerated MTL (AA-MTL) models are chosen. Bone age estimations adjusted by input, output prediction, and without adjusting the confounding variables are compared. Additionally, ablation studies for model size, auxiliary task hierarchy, and multiple tasks are conducted. Correlation and Bland-Altman plots between ground truth and model-predicted bone ages are evaluated. Averaged saliency maps based on image registration are superimposed on representative images according to puberty stage. In the RSNA test dataset, adjusting by input shows the best performances regardless of model size, with mean average errors (MAEs) of 5.740, 5.478, and 5.434 months for the U-Net backbone, U-Net MTL, and AA-MTL models, respectively. However, in the AMC dataset, the AA-MTL model that adjusts the confounding variable by prediction shows the best performance with an MAE of 8.190 months, whereas the other models show the best performances by adjusting the confounding variables by input. Ablation studies of task hierarchy reveal no significant differences in the results of the RSNA dataset. However, predicting the confounding variable in the second encoder layer and estimating bone age in the bottleneck layer shows the best performance in the AMC dataset. Ablations studies of multiple tasks reveal that leveraging confounding variables plays an important role regardless of multiple tasks. To estimate bone age in pediatric X-rays, the clinical setting and balance between model size, task hierarchy, and confounding adjustment method play important roles in performance and generalizability; therefore, proper adjusting methods of confounding variables to train deep learning-based models are required for improved models.
Collapse
Affiliation(s)
- Ki Duk Kim
- Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-Ro 43-Gil, Songpa-Gu, Seoul, 05505, Republic of Korea
| | - Sunggu Kyung
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, 05505, Republic of Korea
| | - Miso Jang
- Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-Ro 43-Gil, Songpa-Gu, Seoul, 05505, Republic of Korea
| | - Sunghwan Ji
- Department of Internal Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, 05505, Republic of Korea
- Department of Translational Medicine, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of Medicine, Seoul, 05505, Republic of Korea
| | - Dong Hee Lee
- College of Medicine, The Catholic University of Korea, Seoul, 06591, Republic of Korea
| | - Hee Mang Yoon
- Department of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, 05505, Republic of Korea.
| | - Namkug Kim
- Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-Ro 43-Gil, Songpa-Gu, Seoul, 05505, Republic of Korea.
- Department of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, 05505, Republic of Korea.
| |
Collapse
|
2
|
Seo H, Hwang J, Jung YH, Lee E, Nam OH, Shin J. Deep focus approach for accurate bone age estimation from lateral cephalogram. J Dent Sci 2023; 18:34-43. [PMID: 36643224 PMCID: PMC9831852 DOI: 10.1016/j.jds.2022.07.018] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2022] [Revised: 07/22/2022] [Accepted: 07/22/2022] [Indexed: 01/18/2023] Open
Abstract
Background/purpose Bone age is a useful indicator of children's growth and development. Recently, the rapid development of deep-learning technique has shown promising results in estimating bone age. This study aimed to devise a deep-learning approach for accurate bone-age estimation by focusing on the cervical vertebrae on lateral cephalograms of growing children using image segmentation. Materials and methods We included 900 participants, aged 4-18 years, who underwent lateral cephalogram and hand-wrist radiograph on the same day. First, cervical vertebrae segmentation was performed from the lateral cephalogram using DeepLabv3+ architecture. Second, after extracting the region of interest from the segmented image for preprocessing, bone age was estimated through transfer learning using a regression model based on Inception-ResNet-v2 architecture. The dataset was divided into train:test sets in a ratio of 4:1; five-fold cross-validation was performed at each step. Results The segmentation model possessed average accuracy, intersection over union, and mean boundary F1 scores of 0.956, 0.913, and 0.895, respectively, for the segmentation of cervical vertebrae from lateral cephalogram. The regression model for estimating bone age from segmented cervical vertebrae images yielded average mean absolute error and root mean squared error values of 0.300 and 0.390 years, respectively. The coefficient of determination of the proposed method for the actual and estimated bone age was 0.983. Our method visualized important regions on cervical vertebral images to make a prediction using the gradient-weighted regression activation map technique. Conclusion Results showed that our proposed method can estimate bone age by lateral cephalogram with sufficiently high accuracy.
Collapse
Affiliation(s)
- Hyejun Seo
- Department of Pediatric Dentistry, School of Dentistry, Pusan National University, Yangsan, South Korea,Department of Dentistry, Ulsan University Hospital, Ulsan, South Korea
| | - JaeJoon Hwang
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Pusan National University, Yangsan, South Korea,Dental and Life Science Institute & Dental Research Institute, School of Dentistry, Pusan National University, Yangsan, South Korea
| | - Yun-Hoa Jung
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Pusan National University, Yangsan, South Korea,Dental and Life Science Institute & Dental Research Institute, School of Dentistry, Pusan National University, Yangsan, South Korea
| | - Eungyung Lee
- Department of Pediatric Dentistry, School of Dentistry, Pusan National University, Yangsan, South Korea,Dental and Life Science Institute & Dental Research Institute, School of Dentistry, Pusan National University, Yangsan, South Korea
| | - Ok Hyung Nam
- Department of Pediatric Dentistry, School of Dentistry, Kyung Hee University, Seoul, South Korea,Corresponding author. Department of Pediatric Dentistry, Kyung Hee University School of Dentistry, 26 Kyungheedae-ro, Dongdaemun-gu, Seoul 02447, South Korea.
| | - Jonghyun Shin
- Department of Pediatric Dentistry, School of Dentistry, Pusan National University, Yangsan, South Korea,Dental and Life Science Institute & Dental Research Institute, School of Dentistry, Pusan National University, Yangsan, South Korea,Corresponding author. Department of Pediatric Dentistry, School of Dentistry, Pusan National University, Geumo-ro 20, Mulgeum-eup, Yangsan-si, 50612, South Korea.
| |
Collapse
|
3
|
Peng LQ, Guo YC, Wan L, Liu TA, Wang P, Zhao H, Wang YH. Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network. Int J Legal Med 2022. [PMID: 35039894 DOI: 10.1007/s00414-021-02746-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2021] [Accepted: 11/10/2021] [Indexed: 12/20/2022]
Abstract
In the forensic estimation of bone age, the pelvis is important for identifying the bone age of teenagers. However, studies on this topic remain insufficient as a result of lower accuracy due to the overlapping of pelvic organs in X-ray images. Segmentation networks have been used to automate the location of key pelvic areas and minimize restrictions like doubling images of pelvic organs to increase the accuracy of estimation. This study conducted a retrospective analysis of 2164 pelvis X-ray images of Chinese Han teenagers ranging from 11 to 21 years old. Key areas of the pelvis were detected with a U-Net segmentation network, and the findings were combined with the original X-ray image for regional augmentation. Bone age estimation was conducted with the enhanced and not enhanced pelvis X-ray images by separately using three convolutional neural networks (CNNs). The root mean square errors (RMSE) of the Inception-V3, Inception-ResNet-V2, and VGG19 convolutional neural networks were 0.93 years, 1.12 years, and 1.14 years, respectively, and the mean absolute errors (MAE) of these networks were 0.67 years, 0.77 years, and 0.88 years, respectively. For comparison, a network without segmentation was employed to conduct the estimation, and it was found that the RMSE of the three CNNs above became 1.22 years, 1.25 years, and 1.63 years, respectively, and the MAE became 0.93 years, 0.96 years, and 1.23 years. Bland-Altman plots and attention maps were also generated to provide a visual comparison. The proposed segmentation network can be used to reduce the influence of restrictions like image overlapping of organs and can thus increase the accuracy of pelvic bone age estimation.
Collapse
|
4
|
Naik P, Ganjwala D, Bhatt C, Vora KS. Usefulness of the Sauvegrain Method of Bone Age Assessment in Indian Children. Indian J Orthop 2020; 55:116-124. [PMID: 33569105 PMCID: PMC7851268 DOI: 10.1007/s43465-020-00189-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Accepted: 06/25/2020] [Indexed: 02/04/2023]
Abstract
INTRODUCTION Bone age estimation is very useful in children undergoing epiphysiodesis or guided growth surgery especially during the years of accelerated growth. It may be noted that no data are available on bone age estimation for Indian children of this age group. Sauvegrain (French) method is a very useful and simple method for bone age assessment during the years of accelerated growth. We decided to check the usefulness and the accuracy of the Sauvegrain method in Indian children. MATERIALS AND METHODS A team of two pediatric orthopaedic surgeons and a radiologist scored elbow X-rays of 80 healthy children (40 boys and 40 girls), using the Sauvegrain method twice. Interobserver reliability and intraobserver reproducibility of the Sauvegrain scoring were assessed. RESULTS There was a very strong correlation between all observers in both rounds (r = > 0.8) and an excellent reproducibility by the same observer in both rounds (r = 0.955). Chronological and bone age are considered the same if the difference between them is less than 6 months. With this criterion bone and chronological ages matched in > 37% of boys and girls, similar to the study done in French children. In the nonmatching group, more children had delayed bone age compared to their chronological age. CONCLUSION The Sauvegrain method of bone age assessment described for French children was found to be useful in estimating bone age in Indian children. It is especially helpful in the clinical practice for detecting mismatch between the chronological and the radiological age before undertaking guided growth or epiphysiodesis.
Collapse
Affiliation(s)
- Premal Naik
- Rainbow Superspeciality Hospital and Children’s Orthopaedic Centre, Next To Asia School, Behind HDFC Bank, Opposite Drive in Cinema Bodakdev, Ahmedabad, Gujarat 380054 India ,Smt S C L Hospital, Smt NHL Municipal Medical College, Ahmedabad, Gujarat India
| | - Dhren Ganjwala
- Ganjwala Orthopedic Hospital, 302, Anshi Avenue, Polytechnic, Ahmedabad, Gujarat 380015 India
| | - Chhaya Bhatt
- Smt NHL Municipal Medical College and Sardar Vallabhbhai Patel Institute of Medical Sciences & Research, Ahmedabad, Gujarat India
| | - Kranti Suresh Vora
- Indian Institute of Public Health Gandhinagar, Opp. Airforce quarters, Lekawada, Gandhinagar, Gujarat India ,University of Canberra, Bruce, Australia
| |
Collapse
|