Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/134472
Title: INTEGRATING MACHINE LEARNING WITH LEVEL SET METHOD FOR MEDICAL IMAGE SEGMENTATION
Authors: AGUS PRATONDO
Keywords: active contour, region-based, edge-based, initialization, class probability
Issue Date: 8-Aug-2016
Source: AGUS PRATONDO (2016-08-08). INTEGRATING MACHINE LEARNING WITH LEVEL SET METHOD FOR MEDICAL IMAGE SEGMENTATION. ScholarBank@NUS Repository.
Abstract: Many segmentation methods have been proposed but none is universally applicable, especially for medical images. Integrated methods have become popular since they can benefit from the advantages of each component method. This thesis presents several algorithms that integrate machine learning (ML) and the level set method and implemented in the form of edge-based and region-based active contour models. First, we use ML algorithms to provide a good initialization for the edge-based active contour models. Second, we propose a framework which incorporates gradient information as well as probability scores from an ML algorithm to construct a group of edge-stop functions for edge-based active contour models. The framework was used to segment objects with poorly defined boundaries. Finally, we propose a method which integrates ML algorithms with region-based active contour models to segment objects containing intensity inhomogeneity. Results indicate that the integrated algorithms generate better results compared to the original approaches.
URI: http://scholarbank.nus.edu.sg/handle/10635/134472
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
PratondoA.pdf7.76 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

97
checked on Jan 14, 2018

Download(s)

77
checked on Jan 14, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.