论文信息 - Combining Shape Priors with Conditional Adversarial Networks for Improved Scapula Segmentation in Mr Images

Combining Shape Priors with Conditional Adversarial Networks for Improved Scapula Segmentation in Mr Images

This paper proposes an automatic method for scapula bone segmentation from Magnetic Resonance (MR) images using deep learning. The purpose of this work is to incorporate anatomical priors into a conditional adversarial framework, given a limited amount of heterogeneous annotated images. Our approach encourages the segmentation model to follow the global anatomical properties of the underlying anatomy through a learnt non-linear shape representation while the adversarial contribution refines the model by promoting realistic delineations. These contributions are evaluated on a dataset of 15 pediatric shoulder examinations, and compared to state-of-the-art architectures including UNet and recent derivatives. The significant improvements achieved bring new perspectives for the pre-operative management of musculo-skeletal diseases.

[1] Konstantinos Kamnitsas,et al. Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation , 2017, IEEE Transactions on Medical Imaging.

[2] Seyed-Ahmad Ahmadi,et al. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[3] Thomas Brox,et al. U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4] Vivek Kumar Singh,et al. Conditional Generative Adversarial and Convolutional Networks for X-ray Breast Mass Segmentation and Shape Classification , 2018, MICCAI.

[5] Alexei A. Efros,et al. Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6] Josef Pauli,et al. Deep Learning With Anatomical Priors: Imitating Enhanced Autoencoders In Latent Space For Improved Pelvic Bone Segmentation In MRI , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[7] E. Flatow,et al. Pediatric shoulder trauma. , 2005, Clinical orthopaedics and related research.

[8] Dimitris N. Metaxas,et al. Effective 3D humerus and scapula extraction using low-contrast and high-shape-variability MR data , 2019, Medical Imaging.