An Effective Noise Removal Technique for Enhancing Ischemic Brain Stroke Computed Tomography Images

Ischemic stroke significantly affects millions of people motor and cognitive skill. Early identification of ischemic stroke helps in preventing loss of life. Usually, noise is present in Computed-Tomography (CT) during acquisition and the noise degrades the visibility of anatomical structures and subtle abnormalities, making it difficult for radiologists to accurately diagnose and interpret medical conditions. Thus, denoising CT medical images is crucial in preserving information and restoring images contaminated with noise. The Convolution-Neural-Network (CNN) has been used to remove the noise with good effect; however, the performance resulted in a loss of clarity and fine details preservation that rendered the CT images unsuitable. In addressing this, presented an enhanced noise removal techniques namely Morphology-Aware CNN (MA-CNN) to enhance brain CT image of ischemic stroke patients for better segmentation, classification to enhance diagnosis. The MA-CNN performance is studied in term of Peak-signal-to-noise-ratio (PSNR); the overall result attained shows the proposed model exhibit higher PSNR in comparison with existing denoiser methods and assures good performance in maintaining the quality of the image and fine details’ preservation.