Research on Evaluation of CAM Image Segmentation Algorithms on a new Database

DOI

10.2991/isci-15.2015.140How to use a DOI?

Keywords

CAM; segmentation evaluation; image segmentation; image set

Abstract

The segmentation of CAM images are prerequisite and fundamental steps of studying the drug effects on angiogenesis. In this paper, an evaluation method for different segmentation algorithm of CAM images is proposed. Firstly, a CAM images dataset consists of 4 distinctive features (uneven illumination, vascular rupture, vascular disconnection and tiny vessels) is set up in order to study the performance of various CAM segmentation algorithms. Then, detailed comparisons are made among 4 classical segmentation algorithms, by comparing their outputs to our standard manual segmentation results of the dataset. Results show that the proposed evaluation method can accurately and sensitively determine the performance of these classical algorithms for CAM blood vessels under various conditions.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yongfeng Huang
AU  - Zhihan Zhang
AU  - Cairong Yan
AU  - Qi Lu
PY  - 2015/01
DA  - 2015/01
TI  - Research on Evaluation of CAM Image Segmentation Algorithms on a new Database
BT  - Proceedings of the 2015 International Symposium on Computers & Informatics
PB  - Atlantis Press
SP  - 1063
EP  - 1072
SN  - 2352-538X
UR  - https://doi.org/10.2991/isci-15.2015.140
DO  - 10.2991/isci-15.2015.140
ID  - Huang2015/01
ER  -