Fully Automatic Bone Age Estimation from Left Hand MR Images

Štern, Darko; Ebner, Thomas; Bischof, Horst; Grassegger, Sabine; Ehammer, Thomas; Urschler, Martin

doi:10.1007/978-3-319-10470-6_28

Cited by 20 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our group has previously contributed to the development of automated age estimation methods from hand and wrist MRI. In [33] and [34], we have shown a method based on random forests [35], which performs nonlinear regression after dedicated anatomical landmark localization [36] of age-relevant bone structures. Later, we improved performance of the age regression component by training a deep CNN (DCNN) for age estimation in [37].…”

Section: Automatic Age Estimationmentioning

confidence: 99%

Automatic Age Estimation and Majority Age Classification From Multi-Factorial MRI Data

Štern¹,

Payer

Giuliani³

et al. 2019

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Age estimation from radiologic data is an important topic both in clinical medicine as well as in forensic applications, where it is used to assess unknown chronological age or to discriminate minors from adults. In this paper, we propose an automatic multi-factorial age estimation method based on MRI data of hand, clavicle, and teeth to extend the maximal age range from up to 19 years, as commonly used for age assessment based on hand bones, to up to 25 years, when combined with clavicle bones and wisdom teeth. Fusing age-relevant information from all three anatomical sites, our method utilizes a deep convolutional neural network that is trained on a dataset of 322 subjects in the age range between 13 and 25 years, to achieve a mean absolute prediction error in regressing chronological age of 1.01 ± 0.74 years. Furthermore, when used for majority age classification, we show that a classifier derived from thresholding our regression-based predictor is better suited than a classifier directly trained with a classification loss, especially when taking into account that those cases of minors being wrongly classified as adults need to be minimized. In conclusion, we overcome the limitations of the multi-factorial methods currently used in forensic practice, i.e., dependence on ionizing radiation, subjectivity in quantifying age-relevant information, and lack of an established approach to fuse this information from individual anatomical sites.

show abstract

Section: Automatic Age Estimationmentioning

confidence: 99%

Automatic Age Estimation and Majority Age Classification From Multi-Factorial MRI Data

Štern¹,

Payer

Giuliani³

et al. 2019

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similar studies in the field of automated age estimation are the works by Stern et al [21,27,28,59,60] and Dallora et al [30]. Both research groups have developed and analyzed methods for age estimation based on machine learning (incl.…”

Section: Comparison To Similar Studiesmentioning

confidence: 68%

Automated age estimation of young individuals based on 3D knee MRI using deep learning

et al. 2020

View full text Add to dashboard Cite

Age estimation is a crucial element of forensic medicine to assess the chronological age of living individuals without or lacking valid legal documentation. Methods used in practice are labor-intensive, subjective, and frequently comprise radiation exposure. Recently, also non-invasive methods using magnetic resonance imaging (MRI) have evaluated and confirmed a correlation between growth plate ossification in long bones and the chronological age of young subjects. However, automated and user-independent approaches are required to perform reliable assessments on large datasets. The aim of this study was to develop a fully automated and computer-based method for age estimation based on 3D knee MRIs using machine learning. The proposed solution is based on three parts: image-preprocessing, bone segmentation, and age estimation. A total of 185 coronal and 404 sagittal MR volumes from Caucasian male subjects in the age range of 13 and 21 years were available. The best result of the fivefold cross-validation was a mean absolute error of 0.67 ± 0.49 years in age regression and an accuracy of 90.9%, a sensitivity of 88.6%, and a specificity of 94.2% in classification (18-year age limit) using a combination of convolutional neural networks and tree-based machine learning algorithms. The potential of deep learning for age estimation is reflected in the results and can be further improved if it is trained on even larger and more diverse datasets.

show abstract

“…As a proof of concept, the segmentations were used for the age estimation of a number of subjects. First results show the potential of this approach attaining a mean difference of 0.48 ± 0.32 years, which improve results from Stern et al of 0.85 ± 0.58 years [2]. In order to fully exploit the potential of neural networks and to supply a more precise and reliable age prediction, the approach has to be tested on a larger data collective.…”

mentioning

confidence: 59%

Abstract: Automated Segmentation of Bones for the Age Assessment in 3D MR Images using Convolutional Neural Networks

Auf-der-Mauer

Pröve

Jopp

et al. 2018

Bildverarbeitung Für Die Medizin 2018

View full text Add to dashboard Cite

The age assessment is a complicated procedure used to determine the chronological age of an individual who lacks legal documentation. Actual studies show that the ossification degree of the growth plates in the knee joint represents a suitable indicator for the majority age. To verify this hypothesis a high number of datasets have to be analysed. Therefore, approaches which enable the detection of the bone structures are necessary. In this work a fully automatic knee segmentation in 3D MR images using convolutional neural networks is presented. A total of 76 datasets were available and divided into a training set (74%), a validation set (13%) and a test set (13%). Multiple preprocessing steps were applied to correct the images and to reduce their size. Image Augmentation was employed to virtually increase the data set size during training. The proposed architecture for the segmentation task resembles the encoder-decoder model type used for the U-Net. The trained network achieves a DSC score of 98% compared to the manual segmentations and an IoU of 96%, outperforming the results by Dam et al. [1]. The precision and recall of the model are balanced and the error has a small value of 1.2%. No overfitting was observed during training. As a proof of concept, the segmentations were used for the age estimation of a number of subjects. First results show the potential of this approach attaining a mean difference of 0.48 ± 0.32 years, which improve results from Stern et al. of 0.85 ± 0.58 years [2]. In order to fully exploit the potential of neural networks and to supply a more precise and reliable age prediction, the approach has to be tested on a larger data collective. The proposed segmentation can lead to an improvement of age estimation methods.

show abstract

Fully Automatic Bone Age Estimation from Left Hand MR Images

Cited by 20 publications

References 8 publications

Automatic Age Estimation and Majority Age Classification From Multi-Factorial MRI Data

Automatic Age Estimation and Majority Age Classification From Multi-Factorial MRI Data

Automated age estimation of young individuals based on 3D knee MRI using deep learning

Abstract: Automated Segmentation of Bones for the Age Assessment in 3D MR Images using Convolutional Neural Networks

Contact Info

Product

Resources

About