Background:
Stroke is one of the major causes for the momentary/permanent disability
in the human community. Usually, stroke will originate in the brain section because of the neurological
deficit and this kind of brain abnormality can be predicted by scrutinizing the periphery of
brain region. Magnetic Resonance Image (MRI) is the extensively considered imaging procedure
to record the interior sections of the brain to support visual inspection process.
Objective:
In the proposed work, a semi-automated examination procedure is proposed to inspect
the province and the severity of the stroke lesion using the MRI.
associations while known disease-lncRNA associations are required only.
Method:
Recently discovered heuristic approach called the Social Group Optimization (SGO) algorithm
is considered to pre-process the test image based on a chosen image multi-thresholding
procedure. Later, a chosen segmentation procedure is considered in the post-processing section to
mine the stroke lesion from the pre-processed image.
Results:
In this paper, the pre-processing work is executed with the well known thresholding approaches,
such as Shannon’s entropy, Kapur’s entropy and Otsu’s function. Similarly, the postprocessing
task is executed using most successful procedures, such as level set, active contour and
watershed algorithm.
Conclusion:
The proposed procedure is experimentally inspected using the benchmark brain
stroke database known as Ischemic Stroke Lesion Segmentation (ISLES 2015) challenge database.
The results of this experimental work authenticates that, Shannon’s approach along with the LS
segmentation offers superior average values compared with the other approaches considered in
this research work.</P>
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-Range Dependencies
