Automated brain extraction and separation in triphenyltetrazolium chloride-stained rat images

Ischemic stroke is one of the leading causes of death among aged population worldwide. To understand the mechanism and damage of cerebral ischemia, the middle cerebral artery occlusion (MCAO) model in rodents has been generally adopted. For its celerity and veracity, the 2,3,5-triphenyltetrazolium chloride (TTC) staining has been widely utilized to visualize the infarct lesion. An important precursor is to segment the brain regions and compute the midline that separates the brain for subsequent processing. This paper develops an automated brain extraction and hemisphere separation framework in TTC-stained rat images captured by a smartphone. A saliency feature detection scheme associated with superpixels is exploited to extract the brain region into individual slices from the compound image. A chain of edge detection, morphological operation, and polynomial regression methods are introduced to compute the midline. Massive experiments were conducted to quantitatively evaluate the proposed framework. Experimental results indicated that our brain extraction algorithm outperformed competitive methods and our hemisphere separation scheme provided high accuracy.