Automated segmentation of the knee for age assessment in 3D MR images using convolutional neural networks

Age assessment is used to estimate the chronological age of an individual who lacks legal documentation. Recent studies indicate that the ossification degree of the growth plates in the knee joint correlates with chronological age of adolescents and young adults. To verify this hypothesis, a high nu...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	International journal of legal medicine Ročník 133; číslo 4; s. 1191 - 1205
Hlavní autoři:	Pröve, Paul-Louis, Jopp-van Well, Eilin, Stanczus, Ben, Morlock, Michael M., Herrmann, Jochen, Groth, Michael, Säring, Dennis, Auf der Mauer, Markus
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2019 Springer Nature B.V
Témata:	3-D technology Adolescent Adolescents Adults Age Age Determination by Skeleton - methods Artificial neural networks Automation Bones Cartilage, Articular - diagnostic imaging Cartilage, Articular - pathology Chronology Datasets Documentation Encoders-Decoders Estimation Forensic Medicine Humans Image Processing, Computer-Assisted - methods Image segmentation Knee Knee Joint - diagnostic imaging Knee Joint - pathology Legal medicine Medical Law Medicine Medicine & Public Health Networks Neural networks Original Article Segmentation Teenagers Training Ultrasonic imaging Young Adult Young adults Knee Age estimation Segmentation Convolutional neural networks MRI
ISSN:	0937-9827, 1437-1596, 1437-1596
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Age assessment is used to estimate the chronological age of an individual who lacks legal documentation. Recent studies indicate that the ossification degree of the growth plates in the knee joint correlates with chronological age of adolescents and young adults. To verify this hypothesis, a high number of datasets need to be analysed. An approach which enables an automated detection and analysis of the bone structures may be necessary to handle large datasets. The purpose of this study was to develop a fully automatic 2D knee segmentation based on 3D MR images using convolutional neural networks. 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 image intensity values and to reduce the image size. Image augmentation was employed to virtually increase the dataset size for training. The proposed architecture for the segmentation task resembles the encoder-decoder model type used for the U-Net. The trained network achieved a dice similarity coefficient score of 98% compared to the manual segmentations and an intersection over union of 96%. The precision and recall of the model were balanced, and the error was only 1.2%. No overfitting was observed during training. As a proof of concept, the predicted segmentations were used for the age estimation of 145 subjects. Initial results show the potential of this approach attaining a mean absolute error of 0.48 ± 0.32 years for a test set of 14 subjects. The proposed automated segmentation can contribute to faster, reproducible and potentially more reliable age estimation in the future.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	0937-9827 1437-1596 1437-1596
DOI:	10.1007/s00414-018-1953-y