Medical Image Segmentation

         Image segmentation is a very important application in the field of image processing of medical images. Segmentation of medical image is a challenging task due to the poor contrast and noise present in the images. The aim of segmentation in medical imaging is more significant in the diagnosis and treatment of many diseases. because of emergence of new trends in the engineering technologies many medical analyzing methods are automated using the image processing principles. Several techniques exist in segmentation of medical image such as intensity value, edge detection, region growing, a novel deep learning-based interactive segmentation framework by incorporating CNNs(Convolutional neural networks) into a bounding box and scribble based segmentation pipeline and A novel CNN architecture, called Dense-Res-Inception Net (DRINet) is used to overcome the problem of intensity, location, shape, and size this challenging problem.

        Medical images in their raw form are represented as arrays of numbers in the computer, indicates the contrast of different types of body tissue. Thresholding method is used  for medical image segmentation which discriminates foreground objects from the background. This can be done based on the similarity of gray levels. From the histogram of an image as shown in Fig.1  by selecting an adequate threshold value in between two peaks, the required object can be segmented shown in Fig.2.

       All the gray level values below this T will be classified as black (0), and those above T will be the white (1) and vice versa. Thresholding converts input gray image into binary image. The benefit of obtaining a binary image is that it reduces the complexity of the data and simplifies the process of recognition and classification. The important aspect in segmentation is selecting the proper value for the threshold  T.