Predictive and Perspective Modeling for Early Detection of Malignancy in Human Breasts using Non-Invasive Imaging Modality: Deep Learning from Scratch
Ashok Kumar1, Saurabh Mukherjee2, Yogesh K Gupta3
1Ashok Kumar, Banasthali University, (Rajasthan), India.
2Dr. Saurabh Mukherjee, Banasthali University, (Rajasthan), India.
3Dr. Yogesh K Gupta, Banasthali University, (Rajasthan), India.
Manuscript received on 22 April 2019 | Revised Manuscript received on 04 May 2019 | Manuscript Published on 17 May 2019 | PP: 7-12 | Volume-7 Issue-6S4 April 2019 | Retrieval Number: F10020476S419/2019©BEIESP
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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In recent years, cancer has been one of the controversial causes and censurable reasons of the high number of deaths and could become one of the compelled causes of most deaths in the coming decades. Early detection with practical accuracy and correct diagnosis of the disease can increase the survival rate of patients suffering from cancer profoundly. Masses and micro calcification clusters are important early signs of breast cancer. Objective of this work is to deliver predictive and perspective classification model for an early detection of breast cancer using image processing and advances of soft computing techniques to provide an integration of prescription with prediction. To provide a system that can be used to classify breast tissues as benign or malignant and if malignant then can further classify which type- invasive or non-invasive type of malignancy. To provide a perspective model that can also prescribe treatment for predicted malignant class with details like time taken, degree of seriousness, probability of curing by opted treatment because treatment of a breast cancer depends on type and stage of malignancy. To achieve higher or clinical usage accuracy by deploying advances of soft computing and image analysis like deep learning and deep neural network to decrease breast cancer mortality rate. To provide the computer aided system with interface of classification and prescription for predicted type of malignancy with practical results scrapped from source of dynamic data or forum native to cancer diseases.
Keywords: Benign, Imaging Modality, Invasive, Malignant, Mammograms, Non-invasive.
Scope of the Article: Predictive Analysis