China 
Africa 
Explore chapters and articles related to this topic
Computer Assisted Health Care Framework for Breast Cancer Detection in Digital Mammograms
Published in Vineet Kansal, Raju Ranjan, Sapna Sinha, Rajdev Tiwari, Nilmini Wickramasinghe, Healthcare and Knowledge Management for Society 5.0, 2021
Laxman Singh, Preeti Arora, Yaduvir Singh, Vinod M. Kapse, Sovers Singh Bisht
There are two kinds of breast calcifications: Macro-calcifications and Microcalcifications (MC). Macro-calcifications look like enormous white dabs on a mammogram (breast X-ray) and are randomly dispersed within the breast. Full scale calcifications are found in around 50% of women who are above 50 years of age, and in 10% of women who are below the age of 50 years. Such kinds of calcifications are very common and are considered non-cancerous. Miniature calcifications are little calcium stores that resemble white spots on a mammogram. They may indicate signs of early breast cancer, when they have certain patterns and forms a cluster by joining together (Zaheeruddin et al., 2012). A mass on the other hand can be described as swelling, protuberance, or lump that develops within the breast. A breast mass may be benign, or malignant. It may be categorized on the basis of many features such as location, size, shape, and margin. On the basis of morphological features, the degree of malignancy can be decided. Shape and margins are important features that represent regardless of whether a mass is generous or harmful. Normally, the masses with oval or circular shapes are benign, while, masses with speculated shape indicate the greater likelihood of malignancy. Figure 8.1 illustrates schematic shapes and margins of different masses.
Breast imaging
Published in David A Lisle, Imaging for Students, 2012
Invasive ductal carcinoma is the most common type, accounting for about 70 per cent of cases of breast cancer. Breast cancer may present clinically as a palpable breast mass, or less commonly with other symptoms such as nipple discharge. Increasingly, breast cancer is detected in asymptomatic women through breast screening programmes. The main goal of breast imaging, whether it is in women with specific symptoms or in screening of asymptomatic women, is early diagnosis of breast cancer.
Machine Learning Model for Breast Cancer Data Analysis Using Triplet Feature Selection Algorithm
Published in IETE Journal of Research, 2023
Dhivya P., Bazilabanu A., Thirumalaikolundusubramanian Ponniah
Early detection of any cancer can prevent human’s life. Many researchers have analyzed to predict the malignant and benign of the cells to go with earlier treatment of cancer. Breast cancer dataset was collected from Kaggle repository (https://www.kaggle.com/uciml/breast-cancer Wisconsin-data). The dataset contains 32 features and 600 instances [25]. The features are taken from the breast cancer images of a fine needle aspirate of a breast mass. There are 10 features, such as radius, smoothness, compactness, concavity, texture, perimeter, area, concave points, symmetry and fractal dimension. From each image, there are worst (mean of the three largest values), mean and standard error is identified for 10 features. The dataset description and attribute naming for each feature is given in Table 2. In Table 2 where M represents the mean, SE is the standard error and W is worst [26]. The dataset instances are classified into train and test. In the proposed work, 70% of instances are training data and remaining 30% as a test data.
Imbalanced medical disease dataset classification using enhanced generative adversarial network
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2022
T. Suresh, Z. Brijet, T. D. Subha
This is developed by Dr. William and H. Wolberg (physicians), University of Wisconsin Hospitals Madison, Wisconsin, USA. The dataset is openly accessible and extensively used on breast cancer diagnosis. This dataset comes from UCI repository. In Breast Cancer Wisconsin Dataset, 3 tasks are carried out with various imbalance ratio, that is, W1, W2 and W3 (https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Original%29). The Gaussian noise is included with the test data, to check efficiency of proposed against unwanted distribution of information (noise). By this, every task is assessed by noisy data, like W1 + NOISE, W2 + NOISE, W3 + NOISE. Breast Cancer Wisconsin (Original) Dataset also features are extracted from the digitized image of breast mass fine needle aspirate from the UCI machine learning repository. Here, the data is gathered via 699 persons. The details regarding the features are given in Table 1. This dataset has 241 benign cases and 458 malignant cases.
Flexible Distribution-Based Regression Models for Count Data: Application to Medical Diagnosis
Published in Cybernetics and Systems, 2020
Pantea Koochemeshkian, Nuha Zamzami, Nizar Bouguila
In this application, we used Breast Cancer Wisconsin dataset (BCD),3 which has a total of 569 observations, and each observation is computed from a digitized fine needle aspirate (FNA) of a breast mass. The prediction includes the diagnosis of each case to malignant or benign, based on the symmetry, and the fractal dimension. Figure 5 shows sample images from this dataset. After extracting the features, we have eight values that have been discretized to be used in our models. The eight real-valued features computed for each cell nucleus are; 1-radius (mean of distances from the center to points on the perimeter), 2-texture (standard deviation of gray-scale values), 3-perimeter, 4-area, 5-smoothness (local variation in radius lengths), 6-compactness, 7-concavity (severity of concave portions of the contour), 8-concave points (number of concave portions of the contour).