Developing a Toolbox for Clinical Preliminary Breast Cancer Detection in Different views of Thermogram Images using a Set of Optimal Supervised Classifiers

Abstract

A full automatic technique and a user friendly toolbox developed to assist physicians in early clinical detection of breast cancer. Database contains different degrees of thermal images obtained from normal or cancerous mammary tissues of patients with mean age of 42.3 years (SD: ±10.50) which their sympathetic nervous system activated with a cold stimulus on hands. First ROI was determined using full automatic operation and the quality of image improved. Then, some features, including statistical, morphological, frequency domain, histogram and GLCM features were extracted from segmented right and left breast. Subsequently, to achieve the best feature space decreasing complexity and increasing accuracy, feature selectors such as mRMR, SFS, SBS, SFFS, SFBS and GA have been used. Finally to classify and TH labeling, supervised learning techniques such as AdaBoost, SVM, kNN, NB and PNN were applied and compared with each other to find the best suitable one. The experimental results obtained on native database showed the mean accuracy of 88.03% for 0 degree images using combination of mRMR and AdaBoost and for combined 3 degrees using combination of GA and AdaBoost. The maximum accuracy obtained from all degrees and their combinations in before and after ice test is nearly to 100%.

Breast Cancer Segmentation From Thermal Images Based on Chaotic Salp Swarm Algorithm

“…1 for each dimension and the follower salps positions are changed by Eq. 3 in step (8)(9)(10)(11)(12)(13)(14). The boundaries (upper and lower) brought salps that can go outside the search space back in step 15.…”

“…This is achieved by converting images into grayscale for segmentation purposes [11]. Preprocessing can be also divided into three stages of detecting the region of interest, enhancing the thermal image, and normalizing the image matrix [12]. In [13], the authors processed image by converting the thermal image from RGB (Red, Green, Blue) mode to HSV (Hue, Saturation, Value) mode to enhance the image regions.…”

ICSI Protocol Advisor: A decision support system for infertility protocol suggestion

“…[18][19][20][21][22][23][24][25][26][27][28]. For example, Lashkari and Firouzmand [29], developed a toolbox to assist physicians in early clinical detection of breast cancer. Initially, Lashkari and Forouzmand [29] improved the quality of the image.…”

“…For example, Lashkari and Firouzmand [29], developed a toolbox to assist physicians in early clinical detection of breast cancer. Initially, Lashkari and Forouzmand [29] improved the quality of the image. Then, some features including statistical, morphological, frequency domain, histogram, and GLCM features were extracted and feature selection was applied [29].…”

“…Initially, Lashkari and Forouzmand [29] improved the quality of the image. Then, some features including statistical, morphological, frequency domain, histogram, and GLCM features were extracted and feature selection was applied [29]. To classify and labeling, some supervised learning algorithms such as Ada boost, SVM, KNN, NB, and PNN were used [29].…”