Medical image segmentation is one of the rarest parts of medical segmentation which divides medical images into meaningful regions. It is the most important process of image processing. Image segmentation is a technique of partitioning images into multiple tiny parts called segments. In this paper, three image segmentation techniques are compared including watershed, region growing, and thresholding. The performance of these techniques is evaluated on a dataset such as medical brain, cancerous brain, tumor detection, cancer-related brain, and pulmonary and liver cancer. The techniques are examined using both qualitative and quantitative approaches. The results reveal that watershed is one of the best image segmentation techniques in medical contexts by offering exceptional accuracy in segmenting challenging areas, region growing performed rather well, and often it can be sensitive to the selection of initial seed points while thresholding struggled with noise and complex borders. The analysis also quantified mean intensity, processing time, and segmented area to understand the effectiveness of these techniques in medical image settings.