Probable Region Identification and segmentation in Breast Cancer using the DL-CNN

Breast Cancer in women is one of the most diagnosed diseases and it is one of the leading disease, which cause death. In past several research works have proposed various methodology to detect the cancer, however due to the Complex nature of micro calcification as well as masses it has the complex nature. Hence in this paper we have proposed a CNN based methodology named Dual layer CNN(DL-CNN), where we have used two layer Convolution Neural Network, first layer Is used for the Probable Region Identification and second layer is used for the Segmentation and false positive reduction. DL-CNN technique is robust in nature and identify the region in efficient manner. Moreover, for the evaluation we have used In Breast image dataset, other parameter considered are True Positive Rate at False positive per image. DL-CNN scores 0.9726 at 0.39706 respectively, it outperforms when compared to the other existing technique.

[1]  Boulehmi Hela,et al.  Breast cancer detection: A review on mammograms analysis techniques , 2013, 10th International Multi-Conferences on Systems, Signals & Devices 2013 (SSD13).

[2]  Mahua Bhattacharya,et al.  Classification of breast tumors as benign and malignant using textural feature descriptor , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[3]  Jianguo Zhang,et al.  Scene image classification method based on Alex-Net model , 2016, 2016 3rd International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS).

[4]  Vijay Kumar,et al.  Semi-automated breast cancer tumor detection with thermographic video imaging , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[5]  Xavier Lladó,et al.  Automatic mass detection in mammograms using deep convolutional neural networks , 2019, Journal of medical imaging.

[6]  Hui Wang,et al.  Breast Mass Classification in Mammograms using Ensemble Convolutional Neural Networks , 2018, 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom).

[7]  Behrouz Minaei,et al.  Assessment of a novel mass detection algorithm in mammograms. , 2013, Journal of cancer research and therapeutics.

[8]  Christopher C. Yang,et al.  Breast Cancer Symptom Clusters Derived From Social Media and Research Study Data Using Improved $K$ -Medoid Clustering , 2016, IEEE Transactions on Computational Social Systems.

[9]  István Csabai,et al.  Detecting and classifying lesions in mammograms with Deep Learning , 2017, Scientific Reports.

[10]  Miguel Ángel Guevara-López,et al.  Representation learning for mammography mass lesion classification with convolutional neural networks , 2016, Comput. Methods Programs Biomed..

[12]  Hui Li,et al.  Digital mammographic tumor classification using transfer learning from deep convolutional neural networks , 2016, Journal of medical imaging.

[13]  Leonid Karlinsky,et al.  Deep Learning for Automatic Detection of Abnormal Findings in Breast Mammography , 2017, DLMIA/ML-CDS@MICCAI.

[14]  Xinbo Gao,et al.  A deep feature based framework for breast masses classification , 2016, Neurocomputing.

[15]  A. Ramli,et al.  Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review. , 2013, Clinical imaging.

[16]  Kok-Swee Sim,et al.  Convolutional neural network improvement for breast cancer classification , 2019, Expert Syst. Appl..

[17]  Gustavo Carneiro,et al.  A deep learning approach for the analysis of masses in mammograms with minimal user intervention , 2017, Medical Image Anal..

[18]  Gustavo Carneiro,et al.  Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models , 2015, MICCAI.