INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Image mining relates and an exhibition reference to a data mining technique where images are used as data. Image mining technique can extract knowledge and exciting patterns that are not stored in the database by analyzing the images using various tools. Image data mining is one of the core functions of this current scenario as image data plays a vital role in every aspect of the system. Breast cancer is a ubiquitous common cancer in women, as well as in several men. Mammography is the first imaging method to detect breast cancer, although it is highly dependent on the radiologist's diagnosis. Computer aided diagnosis has advanced a lot to diagnose cancer correctly. In this paper, the author uses a novel and time-saving approach to breast cancer diagnosis using rough set theory and association rule mining. The accuracy level of the system is quite acceptable and can help the doctor easily detect breast cancer without double reading with guaranteed results. The accuracy level reaches above 98% which can be acceptable and the time complexity is also too less. The main objective of this paper is to apply image mining on mammography images to classify and detect cancerous tissue by discovering insights from the hidden pattern of cancerous tissue. Data mining extended to image fields are techniques generally more suitable for larger databases. The features need to be calculated and their correct subset should significantly increase the classification accuracy. Association rule algorithms generally adopt an iterative method to discover frequent itemsets, which requires very extensive calculations and a complicated transaction process. For this reason, a modified algorithm of association rules is proposed in this paper. Experimental results show that this method can quickly discover frequent item sets and efficiently mine potential association rules. Texture features are the most predictive features, which include intensity histogram features and GLCM features that are extracted from mammography images containing knowledge discovery attributes. In this work, a new feature subset selection approach using Rough Set Improved Harmony Search Quick Reduct is proposed, which reduces approximately 50-60% of the features, and the proposed association rule is used for classification. Most interestingly, the Rough Set Improved Harmony Search Quick Reduct (RSIHSQR) algorithm provides the best optimal features. The experiments were taken from a dataset of 322 MIAS images of various types with the aim of improving accuracy by generating a minimum numbers of rule to cover multiple patterns.
Keywords:
Cite Article:
"Effect of Image Mining Technique to Detect Breast Cancer from Mammograms synthesizing Rough Set Theory and Association Rule Approach", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 2, page no.b468-b480, February-2024, Available :http://www.ijnrd.org/papers/IJNRD2402160.pdf
Downloads:
000118759
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn