A Novel Approach for Automatic Detection and Classification of Suspicious Lesions in Breast Ultrasound Images

Abstract

In this research, a new method for automatic detection and classification of suspected breast cancer lesions using ultrasound images is proposed. In this fully automated method, de-noising using fuzzy logic and correlation among ultrasound images taken from different angles is used. Feature selection using combination of sequential backward search, sequential forward search and distance-based methods is obtained. A new segmentation method based on automatic selection of seed points and region growing is proposed and classification of lesions into two malignant and benign classes using combination of AdaBoost, Artificial Neural Network and Fuzzy Support Vector Machine classifiers and majority voting is implemented.

Segmentation and Classification of White Blood SMEAR Images using Modified CNN Architecture

“…Pre-processing such as Hierarchical fuzzy c-means Clustering were also used. Following the ABUS dataset for breast cancer lesion detection, Karimi et al, 2013 [14] proposed Pre-processing techniques such as Fuzzy compounding. Feature selection algorithms like Mutual Information, Sequential Backward Search and Sequential Forward Search are also used.…”

Bag-of-features image indexing and classification in microsoft SQL server relational database

“…Thanks to content-based image retrieval (CBIR) [1][2][3][4] [5][6] [7] [8] we are able to search for similar images and classify them [9][10] [11][12] [13]. Images can be analyzed based on color representation [14][15] [16], textures [17] [18][19] [20], shape [21] [22] [23] or edge detectors [24].…”

Information Granules in Application to Image Recognition

“…Moreover, our approach does not require any methods for image segmentation like e.g. those applied in medical image processing [19], [4], [9], [6], and any algorithms for edge detection (see e.g. [5]).…”