Segmentation of confocal microscopic image of insect brain

Ming-Jin Wu; Chih-Yang Lin; Yu-Tai Ching

doi:10.1117/12.467125

9 May 2002 Segmentation of confocal microscopic image of insect brain

Ming-Jin Wu, Chih-Yang Lin, Yu-Tai Ching

Proceedings Volume 4684, Medical Imaging 2002: Image Processing; (2002) https://doi.org/10.1117/12.467125
Event: Medical Imaging 2002, 2002, San Diego, California, United States

Abstract

Accurate analysis of insect brain structures in digital confocal microscopic images is valuable and important to biology research needs. The first step is to segment meaningful structures from images. Active contour model, known as snakes, is widely used for segmentation of medical images. A new class of active contour model called gradient vector flow snake has been introduced in 1998 to overcome some critical problems encountered in the traditional snake. In this paper, we use gradient vector flow snake to segment the mushroom body and the central body from the confocal microscopic insect brain images. First, an edge map is created from images by some edge filters. Second, a gradient vector flow field is calculated from the edge map using a computational diffusion process. Finally, a traditional snake deformation process starts until it reaches a stable configuration. User interface is also provided here, allowing users to edit the snake during deformation process, if desired. Using the gradient vector flow snake as the main segmentation method and assist with user interface, we can properly segment the confocal microscopic insect brain image for most of the cases. The identified mushroom and central body can then be used as the preliminary results toward a 3-D reconstruction process for further biology researches.

Citation Download Citation

Ming-Jin Wu, Chih-Yang Lin, and Yu-Tai Ching "Segmentation of confocal microscopic image of insect brain", Proc. SPIE 4684, Medical Imaging 2002: Image Processing, (9 May 2002); https://doi.org/10.1117/12.467125

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available