Tumor Detection in MRI Scans Using Low Order Krawtchouk Moments

Magnetic resonance imaging is a radiology technique that generates detailed images of the human body's anatomy. These images, typically in grayscale, are particularly useful for visualizing soft tissues such as organs and muscles. MRI is especially effective in detecting tumors; however, identifying small tumors or anomalies can be challenging. In this paper, we introduce a new technique for detecting object coordinates using a type of orthogonal moments known as Krawtchouk moments. By employing these moments and their parameters, we can determine the exact coordinates of tumors in MRI scans through a straightforward optimization problem and a translation procedure that converts polynomial parameters to pixel coordinates.