A GPU-Based Approach for Automatic Segmentation of White Matter Lesions

ABSTRACT

White matter lesions (WMLs) in the human brain are generally diagnosed by using magnetic resonance (MR) images. Doctors working on WMLs generally need to calculate the volume of lesions for each patient at regular intervals in order to observe the course of diseases and manage the treatment process. This paper introduces an unsupervised automatic approach for segmentation of WMLs in the human brain. The approach consists of skull stripping, preprocessing, and lesion detection steps. Three skull stripping methods are proposed to increase successful stripping probability on various qualities of MR image data. After preprocessing and segmenting lesions, the system applies volumetric calculation and 3D visualization of lesions. This volumetric information can be used by doctors to observe changes in the lesions against regularly scanned MR images of patients. GPU-based parallel image processing techniques are utilized on Nvidia CUDA environment in order to improve performance by 40–50 times. Therefore, the developed system saves the time of doctors by providing them a fast automatic segmentation method for WMLs.

KEYWORDS:

• Brain segmentation
• Graphical processing units (GPU)
• Image processing
• Lesion detection
• Skull stripping, CUDA, fuzzy C-means clustering (FCM)
• White matter lesions

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Ali Seydi Keçeli

Ali Seydi Keçeli was born in Gaziantep,Turkey, 1984. He received the BSc, MSc and PhD degrees from Hacettepe University, Department of Computer Engineering. His main research areas are image processing, computer vision, data mining, and software enginnering. He is studying in Hacettepe University, Department of Computer Science and Engineering, as a research assistant.

E-mail: [email protected]

Ahmet Burak Can

Ahmet Burak Can was born in Ankara,Turkey, 1976. He received the BSc and MSc degrees from Hacettepe University, Department of Computer Science and Engineering in 1998 and 2001, respectively. He received the PhD degree from Purdue University, Department of Computer Science in 2007. He is affiliated with Hacettepe University, Department of Computer Engineering since 1998. His primary research interests include computer vision, information security, and distributed systems.

E-mail: [email protected]

Aydin Kaya

Aydin Kaya was born in Ankara,Turkey, 1983. He received the BSc, MSc and PhD degrees from Hacettepe University, Department of Computer Engineering. His main research areas are biomedical image processing, data mining, and machine learning. He is studying in Hacettepe University, Department of Computer Science and Engineering, as a research assistant.

E-mail: [email protected]