Abstract
Breast cancer is a serious disease among women, and its early detection is very crucial for the treatment of cancer. To assist radiologists who manually delineate the tumour from the ultrasound image an automatic computerized method of detection called CAD (computer-aided diagnosis) is developed to provide valuable inputs for radiologists. The CAD systems is divided into many branches like pre-processing, segmentation, feature extraction, and classification. This chapter solely focuses on the first two branches of the CAD system the pre-processing and segmentation. Ultrasound images acquired depends on the operator expertise and is found to be of low contrast and fuzzy in nature. For the pre-processing branch, a contrast enhancement algorithm based on fuzzy logic is implemented which could help in the efficient delineation of the tumour from ultrasound image.
TopBackground
The ultrasound images acquired during ultrasonography were found to be of low contrast, fuzzy in nature, not having properly defined shapes, and in cases having tumours of different densities. The pre-processing branch of CAD does contrast enhancement to visually enhance the image without changing the features of the images and is subjected to further steps like segmentation and classification of tumours.
So, what is image enhancement? It is the process of applying transformations to obtain a visually enhanced image to reveal more details is referred to as image enhancement. Many algorithms have been specifically developed by researchers to enhance ultrasound images. According to (Gonzalez & Woods, 2001), the majority of the image enhancement algorithms developed can be grouped within categories like point operations, spatial operations, and transform operations.
Point operations consist of contrast stretching, window slicing, and histogram modelling. Algorithms like histogram equalization and linear contrast stretching are automatic. The limitation of the point operations is that these operations process the image pixel by pixel. Now let us see what spatial operations are. The term spatial refers to the image plane and spatial operations mean direct manipulation of pixels in an image. The limitations of these operations are there is excessive enhancing of noise and smoothening particular areas of the image which need sharpening.
Key Terms in this Chapter
Fuzzy Logic: A logic based on computing degrees of truth rather than the Boolean approach (true or false).
Texture: An entity consisting of mutually related pixels and a group of pixels having similar properties.
Computer-Aided Diagnosis: Systems assisting doctors or radiologists in the interpretation of medical images like X-ray, MRI, and ultrasound.
Tumour: It is a mass of abnormal tissue. There are two types of tumours – benign and malignant. Benign is non-cancerous and malignant is cancerous
Segmentation: Partitioning of a digital image I into multiple non-overlapping regions such that the union of any two adjacent regions is not homogenous is called Image Segmentation.
Membership Function: The membership function for a fuzzy set on the universe of discourse X is defined as and every element of is mapped to a value between 0 and 1. The value called membership value or degree of membership quantifies the grade of membership of the element in X to the fuzzy set A.