Multiple sclerosis (MS) could be considered one of the most severe neurological diseases, which can cause damage to the central nervous system. Because of the regular change in size, location and anatomical variation of MS lesions, it is a challenge to accurately identify, characterize and quantify MS lesions on magnetic resonance imaging (MRI). Therefore, MS lesion segmentation and detection become an active point of research. Recently, deep neural networks (DNN) have seen a rapid advance in various medical image analysis fields, i.e., image registration, image segmentation, lesion detection, and shape modeling. Furthermore, convolution neural networks (CNN) have gained popularity in medical imaging, especially in brain imaging. In this study, an automated technique is proposed to segment MS lesions in MRI. This technique depends on a 3D patchwise region-based convolution neural network (R-CNN) for MS lesion segmentation in T2-w and FLAIR. The proposed method is evaluated using the public MICCAI2008 MS lesion segmentation data set, which is compared to other MS lesion segmentation tools.
Al-Desouky, D., Essa, E., Rashad, M. Z., & Hussein, S. E. (2019). Automatic Multiple Sclerosis lesion segmentation using Patch-wise R-CNN. Mansoura Journal for Computer and Information Sciences, 15(2), 1-9. doi: 10.21608/mjcis.2019.321063
MLA
Doaa Al-Desouky; Ehab Essa; M. Z. Rashad; Sherif E. Hussein. "Automatic Multiple Sclerosis lesion segmentation using Patch-wise R-CNN". Mansoura Journal for Computer and Information Sciences, 15, 2, 2019, 1-9. doi: 10.21608/mjcis.2019.321063
HARVARD
Al-Desouky, D., Essa, E., Rashad, M. Z., Hussein, S. E. (2019). 'Automatic Multiple Sclerosis lesion segmentation using Patch-wise R-CNN', Mansoura Journal for Computer and Information Sciences, 15(2), pp. 1-9. doi: 10.21608/mjcis.2019.321063
VANCOUVER
Al-Desouky, D., Essa, E., Rashad, M. Z., Hussein, S. E. Automatic Multiple Sclerosis lesion segmentation using Patch-wise R-CNN. Mansoura Journal for Computer and Information Sciences, 2019; 15(2): 1-9. doi: 10.21608/mjcis.2019.321063
)
View on SCiNiTO