Automated Age Estimation from Hand MRI Volumes Using Deep Learning

@inproceedings{tern2016AutomatedAE,
  title={Automated Age Estimation from Hand MRI Volumes Using Deep Learning},
  author={D. {\vS}tern and Christian Payer and V. Lepetit and M. Urschler},
  booktitle={MICCAI},
  year={2016}
}
Biological age (BA) estimation from radiologic data is an important topic in clinical medicine, e.g. in determining endocrinological diseases or planning paediatric orthopaedic surgeries, while in legal medicine it is employed to approximate chronological age. In this work, we propose the use of deep convolutional neural networks (DCNN) for automatic BA estimation from hand MRI volumes, inspired by the way radiologists visually perform age estimation using established staging schemes that… Expand
Multi-factorial Age Estimation from Skeletal and Dental MRI Volumes
TLDR
This work proposes automatic multi-factorial age estimation methods based on MRI data to extend the maximal age range from 19 years, as commonly used for age assessment based on hand bones, up to 25 years, when combined with wisdom teeth and clavicles. Expand
Automated age estimation from MRI volumes of the hand
TLDR
The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation and comprehensively evaluates machine learning methods (random forests, deep convolutional neural networks) with different simplifications of the image information used as an input for learning. Expand
Automated age estimation of young individuals based on 3D knee MRI using deep learning
TLDR
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 using a combination of convolutional neural networks and tree-based machine learning algorithms. Expand
Automatic Age Estimation and Majority Age Classification From Multi-Factorial MRI Data
TLDR
An automatic multi-factorial age estimation method based on MRI data of hand, clavicles, 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. Expand
Age-Net: An MRI-Based Iterative Framework for Biological Age Estimation
TLDR
A new imaging-based framework for organ-specific BA estimation using deep convolutional neural networks (Age-Net) is introduced and the correlation between the predicted BAs and the expected cognitive deterioration in Alzheimer's patients is demonstrated. Expand
Bone age detection via carpogram analysis using convolutional neural networks
TLDR
BoneNet is presented, a methodology to assess automatically the skeletal maturity state in pediatric patients based on Convolutional Neural Networks, which achieves over 90% accuracy for most of the critical age thresholds, when differentiating the images between over or under a given age. Expand
Age estimation based on 3D post-mortem computed tomography images of mandible and femur using convolutional neural networks
TLDR
A fully automated age prediction approach was proposed by assessing 3D mandible and femur scans using deep learning and is likely to be faster and potentially more reliable, which could be used for age assessment in the future. Expand
Ossification area localization in pediatric hand radiographs using deep neural networks for object detection
TLDR
It is shown that pre-trained networks can be utilized to produce an effective detector of ossification areas in pediatric X-ray images of hands and finetuned with 240 manually annotated radiographs from the RSNA Pediatric Bone Age Challenge was able to successfully detect ossified areas in prediatric hand radiographs. Expand
Robust Regression of Brain Maturation from 3D Fetal Neurosonography Using CRNs
TLDR
This work proposes a fully three-dimensional Convolutional Regression Network (CRN) for the task of predicting fetal brain maturation from 3D ultrasound (US) data, and outperforms the current state-of-art for automated BM estimation from3D US images. Expand
Evaluation of Skeletal Gender and Maturity for Hand Radiographs using Deep Convolutional Neural Networks
TLDR
VGG-16 and ResNet50 are two Deep Convolutional Neural Network models applied with ImageNet pre-trained weights in order to estimate correct bone age and achieve high accuracy of gender prediction using public RSNA dataset that includes 12611 radiographs. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 13 REFERENCES
From individual hand bone age estimates to fully automated age estimation via learning-based information fusion
  • D. Štern, M. Urschler
  • Computer Science
  • 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
  • 2016
TLDR
This work shows that the artificial separation into bone independent age estimates as used in established fusion techniques can be overcome, and treats aging as a global developmental process, by implicitly fusing developmental information from different bones in a dedicated regression algorithm. Expand
Fully Automatic Bone Age Estimation from Left Hand MR Images
TLDR
On a database of 56 male caucasian subjects between 13 and 19 years, this work is able to estimate the subjects age with a mean difference of 0.85 ± 0.58 years compared to the chronological age, which is in line with radiologist results using established radiographic methods. Expand
Towards Automatic Bone Age Estimation from MRI: Localization of 3D Anatomical Landmarks
TLDR
This work proposes a landmark localization algorithm using multiple random regression forests, first analyzing the shape of the hand from information of the whole image, thus implicitly modeling the global landmark configuration, followed by a refinement based on more local information to increase prediction accuracy. Expand
The BoneXpert Method for Automated Determination of Skeletal Maturity
TLDR
The method reconstructs, from radiographs of the hand, the borders of 15 bones automatically and then computes ldquointrinsicrdquo bone ages for each of 13 bones (radius, ulna, and 11 short bones) and transforms the intrinsic bone ages into Greulich Pyle or Tanner Whitehouse bone age. Expand
Age estimation: The state of the art in relation to the specific demands of forensic practise
TLDR
Here a biochemical method based on aspartic acid racemization in dentine provides the most accurate estimates of age, followed by special morphological dental and skeletal methods. Expand
Assessment of Skeletal Maturity and Prediction of Adult Height (TW2 Method)
TLDR
This book describes the Tanner-Whitehouse (TW) approach to bone age determination and presents the new TW2 standards and presents separate standards for boys and girls that recognize systematic differences between the sexes and the fact that girls are not simply more mature boys. Expand
Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting
TLDR
It is demonstrated that Random Forest regression-voting can be used to generate high quality response images quickly and leads to fast and accurate shape model matching when applied in the Constrained Local Model framework. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
The accuracy of current methods in determining the timing of epiphysiodesis.
TLDR
The accuracy of the growth remaining method of assessing leg-length discrepancy (LLD) with the straight-line graph method, the multiplier method and their variants is compared and Statistical analysis revealed that 'Expected LLD at maturity with surgery' was significantly different from 'Final LLD with surgery'. Expand
Caffe: Convolutional Architecture for Fast Feature Embedding
TLDR
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Expand
...
1
2
...