The following information was submitted:
Transactions: Please, select the Journal that you submit to
Transactions ID Number: 17-260
Full Name: Shafaf Ibrahim
Position: Student
Age: ON
Sex: Female
Address: University Technology MARA
Country: MALAYSIA
Tel: 019-2692717
Tel prefix: +6
Fax: +604-5941023
E-mail address: shafaf_ibrahim@yahoo.com
Other E-mails: elaiza@tmsk.uitm.edu.my, mazani@tmsk.uitm.edu.my
Title of the Paper: Image Mosaicing for Evaluation of MRI Brain Tissue Abnormalities Segmentation Study
Authors as they appear in the Paper: Shafaf Ibrahim, Noor Elaiza Abdul Khalid, Mazani Manaf
Email addresses of all the authors: shafaf_ibrahim@yahoo.com, elaiza@tmsk.uitm.edu.my, mazani@tmsk.uitm.edu.my
Number of paper pages: 9
Abstract: Image segmentation and its performance evaluation are vital aspects in computer vision although they are challenging to resolve. Segmentation of Magnetic Resonance Imaging (MRI) brain images is essential to facilitate the neurological diseases diagnosis. Nevertheless, evaluation of segmentation accuracy has been fundamentally subjective that leads to difficulties in judging the effectiveness of the techniques implemented. This paper proposes an implementation of evaluation method known as image mosaicing in evaluating the MRI brain abnormalities segmentation study. Fifty seven mosaic images are formed by cutting various shapes and sizes of abnormalities, and pasting it onto normal brain tissues. The knowledge of pixel sizes of abnormalities is used as the ground truth to compare with various segmentation results. Three methods of Particle Swarm Optimization (PSO), Adaptive Network-based Fuzzy Inference System (ANFIS) and Fuzzy c-Means (FCM) are used to segment the !
mosaic images formed. The accuracies of image mosaicing segmentation are assessed using statistical analysis methods of Receiver Operating Characteristic (ROC) analysis. The statistical results obtained exhibit some variations that reflect the methods implemented. Thus, the proposed implementation of image mosaicing method is found to be acceptable as it produces potential solutions to the current difficulties of brain abnormalities segmentation performances evaluation.
Keywords: Image mosaicing, Texture evaluation method, Medical imaging, Magnetic Resonance Imaging (MRI)
EXTENSION of the file: .doc
Special (Invited) Session: Evaluation Method for MRI Brain Tissue Abnormalities Segmentation Study
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 120.141.193.106
