Share Email Print
cover

Proceedings Paper

Automatic segmentation of eyeball structures from micro-CT images based on sparse annotation
Author(s): Takaaki Sugino; Holger R. Roth; Masahiro Oda; Seiji Omata; Shinya Sakuma; Fumihito Arai; Kensaku Mori
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A surgical simulator with elaborate artificial eyeball models has been developed for ophthalmic surgeries, in which sophisticated skills are required. To create the elaborate eyeball models with microstructures included in an eyeball, a database of eyeball models should be compiled by segmenting eye structures based on high-resolution medical images. Therefore, this paper presents an automated segmentation of eye structures from micro-CT images by using Fully Convolutional Networks (FCNs). In particular, we aim to construct a method for accurately segmenting eye structures from sparse annotation data. This method performs end-to-end segmentation of eye structures, including a workflow from training the FCN based on sparse annotation to obtaining the segmentation of the entire eyeball. We use the FCN trained on the slices sparsely annotated in a micro-CT volume to segment the remaining slices in the same volume. To achieve accurate segmentation from less annotated images, the multi-class segmentation is performed by using the network trained on the preprocessed and augmented micro-CT images; in the preprocessing, we apply filters for removing ring artifacts and random noises to the images, while in the data augmentation process, rotation and elastic deformation operations are performed on the sparsely-annotated training data. From the results of experiments for evaluating segmentation performances based on sparse annotation, we found that the FCN trained with data augmentation could achieve high segmentation accuracy of more than 90% even from a sparse training subset of only 2.5% of all slices.

Paper Details

Date Published: 12 March 2018
PDF: 6 pages
Proc. SPIE 10578, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging, 105780V (12 March 2018); doi: 10.1117/12.2293431
Show Author Affiliations
Takaaki Sugino, Nagoya Univ. (Japan)
Holger R. Roth, Nagoya Univ. (Japan)
Masahiro Oda, Nagoya Univ. (Japan)
Seiji Omata, Nagoya Univ. Graduate School of Engineering (Japan)
Shinya Sakuma, Nagoya Univ. Graduate School of Engineering (Japan)
Fumihito Arai, Nagoya Univ. Graduate School of Engineering (Japan)
Kensaku Mori, Nagoya Univ. (Japan)


Published in SPIE Proceedings Vol. 10578:
Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging
Barjor Gimi; Andrzej Krol, Editor(s)

© SPIE. Terms of Use
Back to Top