Breast Cancer Detection and Classification using Analysis and Gene-Back Proportional Neural Network Algorithm
Amandeep Kaur1, Prabhjeet Kaur2

1Amandeep kaur,Research Scholar, Department of CSE, Sachdeva Engineering College for Girls, Gharuan, Mohali,India.
2Prabhjeet Kaur,Assistant Professor, Department of CSE, Sachdeva Engineering College for Girls,Gharuan, Mohali,India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 2798-2803 | Volume-8 Issue-8, June 2019 | Retrieval Number: H6992068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Breast cancer disease history goes back to around 1,500 years B.C. Old Egyptians were the first to report the infection over 3,500 years ago. Breast cancer is the main cause of death among technologically advanced and underdeveloped countries. After lung cancer, more than 10% of women are diagnosed with Breast cancer. Breast Cancer can be determined by features like as redness of the skin, change in size, abdominal pain and texture change. Though the main cause of breast cancer is ambiguous in some cases, stoppage of the disease becomes difficult. However, detection of Tumour in the breast at an early stage is the only method to cure this disease. Radiologist recognizes breast cancer using various technologies like mammography, thermography etc. Optical coherence tomography is new invention found in medical services before five years; it is microscopic needle method for detection of Breast Cancer. Computer-aided diagnosis is the most appropriate method for diagnosis of disease. Quantitative Assessment of lower half of breast can be done using contour outlining with related measures such as breast symmetrical approach, the mass of breast can be recognized. In Existing research, two classifiers were used namely Naïve Bayes and k nearest neighbor (KNN) for the classification of breast cancer. The experimental result improves the performance with high accuracy and less error rate with k nearest neighbor. In research work, the data sets are gathered which is downloaded from the UCI (University of California Irvine) machine Knowledge Depository Site. Machine learning methods are used for the prediction and classification of features of breast cancer. Various stages used for extraction of the feature of breast cancer. Firstly, the pre-processing phase is used for searching for the missed attributes and then feature extraction method is used for finding feature vectors in BCD (Breast Cancer Dataset). Experimental result use classification method (gene-BPNN) for the prediction of benign and malign in MATLAB (Matrix Laboratory) 2016a Simulation metrics are evaluated using accuracy, specificity and sensitivity.
Keyword: Breast Cancer, Mammography, Quantitative Assessment, Contour outlining, Machine learning.
Scope of the Article: Computer Network.