Meeting Banner
Abstract #1136

Fully automatic segmentation of wrist cartilage on MR images by convolutional neural network

Ekaterina A. Brui1, Aleksandr Y. Efimtcev1,2, Vladimir A. Fokin1,2, Remi Fernandez3, Anatoliy G. Levchuk2, Augustin C. Ogier4, Irina V. Melchakova1, David Bendahan4, and Anna E. Andreychenko1

1The International Research Center Nanophotonics and Metamaterials, University of Information Technology Mechanics and Optics, Saint-Petersburg, Russian Federation, 2Federal Almazov North-West Medical Research Center, Saint-Petersburg, Russian Federation, 3APHM, Service de Radiologie, Hôpital de la Conception, Marseille, France, 4CRMBM, Aix-Marseille Universite, Marseille, France

A fully automatic, wrist cartilage segmentation method on magnetic resonance images is developed and validated. The method is based on convolutional neural networks (CNN). Cartilage segmentations obtained with the CNN showed a substantial agreement with manual segmentations for the full 3D wrist images and a good agreement for central coronal slices. The proposed method provided cartilage masks having a high concordance with manually obtained ones.

This abstract and the presentation materials are available to members only; a login is required.

Join Here