| Autor: |
Muda, Ayuni Fateeha, Saad, Norhashimah Mohd, Low Yin Fen, Abdullah, Abdul Rahim, Waeleh, Nazreen, Muda, Ahmad Sobri |
| Předmět: |
|
| Zdroj: |
International Journal of Simulation: Systems, Science & Technology; 2016, Vol. 17 Issue 34, p3.1-3.7, 7p |
| Abstrakt: |
This study proposed automatic segmentation of brain lesions based on the integration of fuzzy C-means (FCM) with correlation template and active contour for diffusion-weighted imaging (DWI). Due to noises and intensity inhomogeneity, FCM fails in producing accurate results. Correlation template and active contour can be applied to increase the accuracy. The brain lesions studied are acute stroke and solid tumour for hyperintense lesions, and necrosis and chronic stroke for hypointense lesions. The proposed analysis framework has been validated by using Jaccard's area overlap (AO), Dice index, false negative rate (FNR) and false positive rate (FPR). FCM with correlation template provides more accurate results compared to FCM with active contour because it can separate cerebral spinal fluid (CSF) and hypointense lesions that share similar range of intensity. The results are 0.547, 0.258, 0.192 and 0.687 for Jaccard, FPR, FNR and Dice indices. The proposed technique can be used to segment brain lesions precisely for DWI images. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
