Share Email Print
cover

Proceedings Paper

Cerebral vessels segmentation for light-sheet microscopy image using convolutional neural networks
Author(s): Chaoen Hu; Hui Hui; Shuo Wang; Di Dong; Xia Liu; Xin Yang; Jie Tian
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Cerebral vessel segmentation is an important step in image analysis for brain function and brain disease studies. To extract all the cerebrovascular patterns, including arteries and capillaries, some filter-based methods are used to segment vessels. However, the design of accurate and robust vessel segmentation algorithms is still challenging, due to the variety and complexity of images, especially in cerebral blood vessel segmentation. In this work, we addressed a problem of automatic and robust segmentation of cerebral micro-vessels structures in cerebrovascular images acquired by light-sheet microscope for mouse. To segment micro-vessels in large-scale image data, we proposed a convolutional neural networks (CNNs) architecture trained by 1.58 million pixels with manual label. Three convolutional layers and one fully connected layer were used in the CNNs model. We extracted a patch of size 32x32 pixels in each acquired brain vessel image as training data set to feed into CNNs for classification. This network was trained to output the probability that the center pixel of input patch belongs to vessel structures. To build the CNNs architecture, a series of mouse brain vascular images acquired from a commercial light sheet fluorescence microscopy (LSFM) system were used for training the model. The experimental results demonstrated that our approach is a promising method for effectively segmenting micro-vessels structures in cerebrovascular images with vessel-dense, nonuniform gray-level and long-scale contrast regions.

Paper Details

Date Published: 13 March 2017
PDF: 6 pages
Proc. SPIE 10137, Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging, 101370K (13 March 2017); doi: 10.1117/12.2254714
Show Author Affiliations
Chaoen Hu, Harbin Univ. of Science and Technology (China)
Key Lab. of Molecular Imaging, Institute of Automation (China)
Hui Hui, Key Lab. of Molecular Imaging, Institute of Automation (China)
Shuo Wang, Key Lab. of Molecular Imaging, Institute of Automation (China)
Di Dong, Key Lab. of Molecular Imaging, Institute of Automation (China)
Xia Liu, Harbin Univ. of Science and Technology (China)
Xin Yang, Key Lab. of Molecular Imaging, Institute of Automation (China)
Jie Tian, Key Lab. of Molecular Imaging, Institute of Automation (China)


Published in SPIE Proceedings Vol. 10137:
Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging
Andrzej Krol; Barjor Gimi, Editor(s)

© SPIE. Terms of Use
Back to Top