Answers are grounded in this paper and cite their sources.
Demonstrates improved segmentation accuracy of the inner ear, suggesting advancements in clinical diagnosis and treatments.
The inner ear located in the temporal bone structure, has a complex structure. It consists of semicircular canal, vestibule and cochlea. The inner ear segmentation can provide reliable anatomical information for clinical diagnosis and treatments. Due to the complicated topological structures, smooth surface and tubular properties of the inner ear, at present, automatic segmentation of inner ear is still a great challenge. In this study, we propose an innovative inner ear segmentation method. The proposed inner ear segmentation method can be described as follows. Firstly, the statistical shape models (SSMs) is created by a set of training inner ear shapes which are segmented by otologists manually; secondly, the region of interest (ROI) volume of the inner ear is determined by a rigid registration; thirdly, the mean shape model of the inner ear SSMs is creatively used as the initial contour of level set by a model to ROI volume registration; finally, the 3D threshold level set segmentation algorithm is used to refine the inner ear segmentation. The segmented inner ears are visualized by surface rendering and compared with the manual segmentations by otologists. The experimental results prove that the proposed method is capable of segmenting the inner ear automatically and the segmentation accuracy can achieve the clinical requirement.
No takes yet. Share an insight, caveat, or question.
Zhu et al. (2017) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: