Brain lesion segmentation of diffusion-weighted MRI using gray level co-occurrence matrix

This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and absce...

Penerangan Penuh

Disimpan dalam:
Butiran Bibliografi
Pengarang-pengarang Utama: Mohd. Saad, N., Syed Abu Bakar, Syed Abdul Rahman, Muda, S., Musa, Mohd. Mokji, Salahuddin, L.
Format: Book Section
Diterbitkan: IEEE Explorer 2011
Subjek-subjek:
Capaian Atas Talian:http://eprints.utm.my/28922/
http://eprints.utm.my/28922/
http://eprints.utm.my/28922/
Penanda-penanda: Tambah Penanda
Tiada Penanda, Jadilah orang pertama menanda rekod ini!
Penerangan
Ringkasan:This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, GLCM is computed to segment the lesions. Different peaks from the GLCM cross-section indicate the present of normal brain region, cerebral spinal fluid (CSF), hyperintense or hypointense lesions. Minimum and maximum threshold values are computed from the GLCM cross-section. Region and boundary information from the GLCM are introduced as the statistical features for segmentation of hyperintense and hypointense lesions. The proposed method provides very good segmentation results even in a small brain lesion.