Tumorand Stroke Lesions Recognition and Investigation for Involuntary Detection of Brain irregularity

• Main Authors: Sharma, Trapti, Khalaf, Hameed Hassan, Abdulhasan, Maki Mahdi, Shareef, Ashraf Mohammed
• Format: Conference Proceeding
• Language: English
• Subjects: CAD; CNS; Image recognition; Image segmentation; Information processing; Location awareness; Magnetic resonance imaging; MRI; Shape; Stroke (medical condition); SVM; Tumor
• ISSN: 2640-074X
• DOI: 10.1109/ICIIP61524.2023.10537649

Several computational features distinguish one type of abnormality from another, including the nature of the abnormality, its size, shape, volume, number of lesions, and distribution. Because it is challenging to classify distinct types of abnormalities using an automated approach, we use the term abnormalities to refer to tumours, blood clots, and strokes collectively. Segmentation of brain images is an attempt to assign tissue labels to individual pixels. Since MRI gives a greater contrast of soft tissue structures, it is the preferred approach for imaging the brain. Appropriate segmentation methods have a high correlation with image capture modality, the tissue of interest. In order to devise a suitable treatment plan, it is crucial to correctly diagnose brain abnormalities like tumour, stroke, or bleeding lesions. Studies have focused on developing better image processing algorithms for use in CAD systems, with the ultimate goal of assessing photos of various brain disorders. In this study, researchers employ an innovative automated method to examine brain MRIs for signs of disease. Image segmentation, area and volume calculations, and localization are only a few of the many steps of the algorithm that has been put into place. The statistical comparison of the suggested method's output with the reference image reveals encouraging results.