Masseter Segmentation from Computed Tomography Using Feature-Enhanced Nested Residual Neural Network
| Autor: | Yuke Guo, Hongbin Zha, Yuru Pei, Haifang Qin, Gengyu Ma, Tianmin Xu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0301 basic medicine
Similarity (geometry) Artificial neural network Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Residual Masticatory force 03 medical and health sciences 030104 developmental biology 0302 clinical medicine Feature (computer vision) Convergence (routing) Segmentation Artificial intelligence business Feature learning 030217 neurology & neurosurgery |
| Zdroj: | Machine Learning in Medical Imaging ISBN: 9783030009182 MLMI@MICCAI |
| DOI: | 10.1007/978-3-030-00919-9_41 |
| Popis: | Masticatory muscles are of significant aesthetic and functional importance to craniofacial developments. Automatic segmentation is a crucial step for shape and functional analysis of muscles. In this paper, we propose an automatic masseter segmentation framework using a deep neural network with coupled feature learning and label prediction pathways. The volumetric features are learned using the unsupervised convolutional auto-encoder and integrated with multi-level features in the label prediction pathway to augment features for segmentation. The label prediction pathway is built upon the nested residual network which is feasible for information propagation and fast convergence. The proposed method realizes the voxel-wise label inference of masseter muscles from the clinically captured computed tomography (CT) images. In the experiments, the proposed method outperforms the compared state-of-the-arts, achieving a mean Dice similarity coefficient (DSC) of \(93\pm 1.2\%\) for the segmentation of masseter muscles. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|