Tumour Delineation using Statistical Properties of The Breast US Images and Vector Quantization based Clustering Algorithms

Abstract

-Breast cancer is most common and leading cause of death among women. With improvement in the imaging modalities it is possible to diagnose the cancer at an early stage moreover treatment at an early stage reduces the mortality rate. B-mode ultrasound (US) imaging is very illustrious and reliable technique in early detection of masses in the breast. Though it is complimentary to the mammography, dense breast tissues can be examined more efficiently and detects the small nodules that are usually not observed in mammography. Segmentation of US images gives the clear understanding of nature and growth of the tumor. But some inherent artifact of US images makes this process difficult and computationally inefficient. Many methods are discussed in the literature for US image segmentation, each method has its pros and cons. In this paper, initially region merging based watershed and marker-controlled watershed transforms are discussed and implemented. In the subsequent sections we proposed a method for segmentation, based on clustering. Proposed method consists of three stages, in first stage probability images and its equalized histogram images are obtained from the original US images without any preprocessing. In the next stage, we used VQ based clustering technique with LBG, KPE and KEVR codebook generation algorithm followed by sequential cluster merging. Last stage is the post processing, where we removed unwanted regions from the selected cluster image by labeling the connected components and moreover used morphological operation for closing the holes in the final segmented image. Finally, results by our method are compared with initially discussed methods.

A novel breast tumor classification algorithm using neutrosophic score features

“…than benign ones. The main characteristics of malignant tumors are: irregular shape, malady boundaries, microlobulated margins and heterogeneous echo texture [19]. On the other hand, benign tumors have a rounded shape, well defined margins, and homogeneous echo texture.…”

“…On the other hand, benign tumors have a rounded shape, well defined margins, and homogeneous echo texture. However, the boundary and shape characteristics are the most important information in tumor's detection or differentiation [18,19].…”

“…Morphologic features are used to describe shape and margin of the tumors [15]. The shape is an effective feature for classifying breast tumors into benign and malignant [19]. Some popular morphological features of interest are defined as follows [11][12][13]:…”

Boundary-oriented Network for Automatic Breast Tumor Segmentation in Ultrasound Images

“…Zhou et al 15 developed a semi-automatic BUS image segmentation using Gaussian filtering, histogram equalization, mean shift, and graph cuts. Clustering-based methods [16][17][18][19] belong to machine learning algorithms. Moon et al 18 proposed a computer-aided detection system based on a quantitative tissue clustering algorithm to identify potential tumors.…”

Tumor Demarcation of Breast US Images using VQ Based Clustering Algorithms on Proba bility and its Histogram Equalized Images

“…Euclidean Distance calculation is removed in KFCG, but it used in other VQ based algorithms such as LBG, KPE, and KEVR given by H. B. Kekre [30]. KFCG algorithm also eliminates sorting process, which is required in KMCG.…”