Authors:
V. Asha, Swathi Baswaraju, M. Arunadevi Thirumalraj, S. Gopikha, Chou Yi Hsu

Addresses:
Department of Computer Applications, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Computer Science and Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Computer Science and Engineering, Karunya Institute of Technology and Science, Coimbatore, Tamil Nadu, India.  Department of Computer Science and Business Management, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India. Department of Information Technology, St. Joseph's College of Engineering, Chennai, Tamil Nadu, India. Department of Pharmacy, Chia Nan University of Pharmacy and Science, Rende, Tainan, Taiwan.

Abstract:

Cancer of the uterus (UC), which arises from the cells that line the interior of the uterus, has the potential to multiply in an uncontrolled manner, causing damage to the tissues that are in proximity and initiating the formation of malignant cells.  The purpose of this study is to present a new model that begins with preprocessing through convolution to reduce noise.  The purpose of the study is to combine four distinct properties, namely the Grey Level Co-occurrence Matrix (GLCM), the Grey Level Run Length Matrix (GLRLM), the Local Binary Pattern (LBP), and the Speeded Up Robust Feature (SURF), to incorporate qualities that are oriented towards texture. The following aspects can be extracted comprehensively and systematically using these features: contrast, long-run emphasis, short-run low grey-level run emphasis, short-run high grey-level run emphasis, and other features. These combinations of hybrid features are essential for accurately predicting cancer. The Robust Extreme Learning Machine (RELM) and the Adaptive Manta-Ray Foraging Optimisation (AMRFO) are the two modules that make up the suggested classification model.  The purpose of AMRFO is to pick the best possible kernel functions for RELM.  

Keywords: Uterine Cancer; Carcinoma Prediction; Grey Level Run Length Matrix; Local Binary Pattern; Speeded up Robust Feature; Hybrid Feature; Kernel Functions; Cancerous Cells.

Received on: 23/12/2024, Revised on: 03/03/2025, Accepted on: 27/04/2025, Published on: 06/12/2025

DOI: 10.69888/FTSHSL.2025.000509

FMDB Transactions on Sustainable Health Science Letters, 2025 Vol. 3 No. 4, Pages: 192-201

• Views : 229
• Downloads : 19

Download PDF