Enhancement of Non-Linear Deep Learning Model by Adjusting Confounding Variables for Bone Age Estimation in Pediatric Hand X-rays

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.

Deep focus approach for accurate bone age estimation from lateral cephalogram

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.

Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network

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.

Usefulness of the Sauvegrain Method of Bone Age Assessment in Indian Children

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.