A Web Based MATLAB Solution for Classifying Micro-Calcification on Mammograms
Karuna Sharma1, Saurabh Mukherjee2
1Karuna Sharma, Assistant Professor in the Department of Computer Science, Banasthali Vidyapith, Rajasthan.
2Saurabh Mukherjee, Professor in the department of Computer Science, Banasthali Vidyapith, Rajasthan.
Manuscript received on January 12, 2020. | Revised Manuscript received on January 21, 2020. | Manuscript published on February 10, 2020. | PP: 2439-2446 | Volume-9 Issue-4, February 2020. | Retrieval Number: D2108029420/2020©BEIESP | DOI: 10.35940/ijitee.D2108.029420
Open Access | Ethics and Policies | Cite | Mendeley
© 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 the aeon of deep learning, CNN outperform significant part in medical image analysis. CADx(“Computer Aided Detection and Diagnosis “) for Mammography utilizes significant features to detect and diagnose breast malignancy. Now a day CNNs based CADx are worth popular due to automatic relevant features extraction. CNNs can be trained from ground up for medical images but due to finite number of medical images transfer learning and data augmentations are used for training. And also performance of CADx can be decreased due to some factors like appearance of noise, artifacts, low contrast in both CC and MLO views of Mammogram and pectoral muscles which appears in MLO view of Mammogram. Mammograms can contain different types of abnormality like Micro-Calcification, Masses, Architectural distortion in case of breast cancer. In this work we developed a Web Based MATLAB Solution for the classification of Micro-Calcification malignancy either benign or malignant. This web based solution performs different steps to remove artifact, to enhance contrast, to segment pectoral muscle and to extract breast profile. At the final step proposed system classify mammograms either into benign or malignant. It has been examined on mammographic images containing both views from CBIS-DDSM database.
Keywords: Computer Aided Detection and Diagnosis, Image Enhancement, Segmentation, Deep learning, Convolutional Neural Network, Transfer Learning, Data Augmentation, Breast Tumor Classification, Micro-Calcification.
Scope of the Article: Deep learning