Authors:
S. Karthik, Edwin Shalom Soji, S. Silvia Priscila, L. Sarala Deve, P. Paramasivan, A. Senthil Kumar
Addresses:
Department of Computer Science and Engineering, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India, karthiks1087@gmail.com. Department of Computer Science, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India, edwinshalomsoji.cbcs.cs@bharathuniv.ac.in, silviaprisila.cbcs.cs@bharathuniv.ac.in, saraladeve.cse@bharathuniv.ac.in. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India, paramasivanchem@gmail.com. Department of Computer Science, Skyline University, Kano, Nigeria, senthil.kumar@sun.edu.ng.
Image processing is a rapidly advancing innovation for managing large data volumes in a single repository, enabling high-level abstraction for specific requirements. In the healthcare sector, image-based systems are used to store extensive patient records. Conducting data mining on images is simplified by advanced protocols that extract relevant datasets from image repositories. This paper presents a solution for detecting brain cancer using MRI datasets stored in a centralized repository. The patient's MRI scan is analyzed alongside reference samples using two data mining techniques: Significant Mining and Structural Mining. Two modified algorithms are employed the Partially Augmented Linear Mean Analysis Algorithm and the Vertically Augmented Tensor-Load Interface Algorithm to ensure precise tumour detection from all data points. The Unified Structural Architecture integrates both algorithms to improve efficiency and effectiveness. The performance of these algorithms is evaluated against established methods, focusing on average accuracy. Simulation results using tools like MATLAB, MS Excel, and SPSS demonstrate the system's high efficiency in processing high-dimensional data.
Keywords: Substantial Mining; Structure Mining; Big Data; Image Dataset Mining; Unified Structural Architecture; Algorithm Performance Evaluation; Fully Convolutional Networks (FCNs).
Received on: 25/10/2023, Revised on: 07/12/2023, Accepted on: 18/01/2024, Published on: 03/06/2024
AVE Trends in Intelligent Health Letters, 2024 Vol. 1 No. 2, Pages: 51-68