Classification Methods, Deep Learning Architecture, Data Source and Challenges in Detection of Breast Cancer
Nalini Sampath1, N. K. Srinath2

1Mrs. Nalini, Department of Computer Science, Amrita Vishwa Vidyapeethamin, University, Coimbatore (Tamil Nadu), India.

2Dr. N K Srinath, Professor, Department of Computer Science and Engineering, RV College of Engineering, Bangalore (Karnataka), India.

Manuscript received on 05 December 2019 | Revised Manuscript received on 13 December 2019 | Manuscript Published on 31 December 2019 | PP: 477-481 | Volume-9 Issue-2S December 2019 | Retrieval Number: B11231292S19/2019©BEIESP | DOI: 10.35940/ijitee.B1123.1292S19

Open Access | Editorial and Publishing 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: Different types of cancer can be prevented, screened for and/or detected and treated at an early stage. According to recent statistics breast cancer has a mortality rate of 12.7 per one lakh women. Mutation of genes at an abnormal rate leads to cancer. Changes in the size, color, texture and constant pain are the initial symptoms of breast cancer. A person presented with these symptoms requires breast cancer screening which would help in the diagnosis. Early detection can help health care professionals to start with the treatment, thereby reducing the mortality rate. Recent advances in breast cancer detection have proven to aid both medical professional and patients in making health care decisions. In this paper image acquisition technique, classification techniques, deep learning models and data sets available are highlighted.

Keywords: Classification, Dataset, Deep Learning, Imaging Modality, Transfer Learning.
Scope of the Article: Deep Learning