Open Access

ARTICLE

Machine Learning Enabled Early Detection of Breast Cancer by Structural Analysis of Mammograms

by Mavra Mehmood¹, Ember Ayub¹, Fahad Ahmad^1,6,*, Madallah Alruwaili², Ziyad A. Alrowaili³, Saad Alanazi², Mamoona Humayun², Muhammad Rizwan¹, Shahid Naseem⁴, Tahir Alyas⁵

1 Department of Computer Sciences, Kinnaird College for Women, Lahore, 54000, Pakistan
2 College of Computer and Information Sciences, Jouf University, Sakaka, Aljouf, 72341, Saudi Arabia
3 Physics Department, College of Science, Jouf University, Sakaka, Aljouf, 72341, Saudi Arabia
4 Division of Computer Science & Information Technology, University of Education, Lahore, 54000, Pakistan
5 Department of Computer Science, Lahore Garrison University, Lahore, 54000, Pakistan
6 Department of Basic Sciences, Deanship of Common First Year, Jouf University, Sakaka, Aljouf, 72341, Saudi Arabia

* Corresponding Author: Fahad Ahmad. Email:

(This article belongs to the Special Issue: Machine Learning-based Intelligent Systems: Theories, Algorithms, and Applications)

Computers, Materials & Continua 2021, 67(1), 641-657. https://doi.org/10.32604/cmc.2021.013774

Received 20 August 2020; Accepted 30 October 2020; Issue published 12 January 2021

Abstract

Clinical image processing plays a significant role in healthcare systems and is currently a widely used methodology. In carcinogenic diseases, time is crucial; thus, an image’s accurate analysis can help treat disease at an early stage. Ductal carcinoma in situ (DCIS) and lobular carcinoma in situ (LCIS) are common types of malignancies that affect both women and men. The number of cases of DCIS and LCIS has increased every year since 2002, while it still takes a considerable amount of time to recommend a controlling technique. Image processing is a powerful technique to analyze preprocessed images to retrieve useful information by using some remarkable processing operations. In this paper, we used a dataset from the Mammographic Image Analysis Society and MATLAB 2019b software from MathWorks to simulate and extract our results. In this proposed study, mammograms are primarily used to diagnose, more precisely, the breast’s tumor component. The detection of DCIS and LCIS on breast mammograms is done by preprocessing the images using contrast-limited adaptive histogram equalization. The resulting images’ tumor portions are then isolated by a segmentation process, such as threshold detection. Furthermore, morphological operations, such as erosion and dilation, are applied to the images, then a gray-level co-occurrence matrix texture features, Harlick texture features, and shape features are extracted from the regions of interest. For classification purposes, a support vector machine (SVM) classifier is used to categorize normal and abnormal patterns. Finally, the adaptive neuro-fuzzy inference system is deployed for the amputation of fuzziness due to overlapping features of patterns within the images, and the exact categorization of prior patterns is gained through the SVM. Early detection of DCIS and LCIS can save lives and help physicians and surgeons todiagnose and treat these diseases. Substantial results are obtained through cubic support vector machine (CSVM), respectively, showing 98.95% and 98.01% accuracies for normal and abnormal mammograms. Through ANFIS, promising results of mean square error (MSE) 0.01866, 0.18397, and 0.19640 for DCIS and LCIS differentiation during the training, testing, and checking phases.

---

Keywords

---

Citations