Article: Application of custom ant lion optimisation convolutional neural networks for liver lesion classification system Journal: International Journal of System of Systems Engineering (IJSSE) 2025 Vol.15 No.5 pp.401 - 422 Abstract: In order to save a person's life, it's essential to categorise the lesions of liver in their early stages. The majority of scientists prefer classifying liver tumours using machine learning approaches. Recently, the use of computer-aided technology for this purpose has captured the interest of scientists. This paper classifies perceptual datasets using pre-trained network models and a lion-optimised convolution neural network (CNN) classifier. However, neural network learning can be improved, and deep learning-based neural networks and its applications are rarely studied. Additionally, the custom optimised convolution neural network (CO-CNN) is suggested in this research as a very accurate method for classifying liver lesions. The de-noising steps in this suggested method include a median filter, the Random Forest (RF) method for extracting the liver, the gray level run length matrix (GLRLM) method for extracting features, and the CO-CNN method for classification. This technique is tested on Python. Experimental results showed that the suggested approach exceeds existing approaches in accuracy, sensitivity, and specificity. It has 96% sensitivity and 97.77% accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Application of custom ant lion optimisation convolutional neural networks for liver lesion classification system

Authors: A. Bathsheba Parimala; R.S. Shanmugasundaram

Addresses: Department of Computer Applications, St. Johns College, Palayamkottai, Affiliated to Manonmanaiam Sundaranar University, Tamil Nadu, India ' Department of Computer Science, Vinayaka Missions Research Foundation, Salem, Tamil Nadu, 636308, India

Abstract: In order to save a person's life, it's essential to categorise the lesions of liver in their early stages. The majority of scientists prefer classifying liver tumours using machine learning approaches. Recently, the use of computer-aided technology for this purpose has captured the interest of scientists. This paper classifies perceptual datasets using pre-trained network models and a lion-optimised convolution neural network (CNN) classifier. However, neural network learning can be improved, and deep learning-based neural networks and its applications are rarely studied. Additionally, the custom optimised convolution neural network (CO-CNN) is suggested in this research as a very accurate method for classifying liver lesions. The de-noising steps in this suggested method include a median filter, the Random Forest (RF) method for extracting the liver, the gray level run length matrix (GLRLM) method for extracting features, and the CO-CNN method for classification. This technique is tested on Python. Experimental results showed that the suggested approach exceeds existing approaches in accuracy, sensitivity, and specificity. It has 96% sensitivity and 97.77% accuracy.

Keywords: classification system; liver lesion; RF; CO-CNN; custom optimised convolution neural network; sensitivity; GLRLM; gray level run length matrix; ALO; ant lion optimisation; lesion classification system.

DOI: 10.1504/IJSSE.2025.149711

International Journal of System of Systems Engineering, 2025 Vol.15 No.5, pp.401 - 422

Received: 25 May 2023
Accepted: 03 Aug 2023
Published online: 11 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Application of custom ant lion optimisation convolutional neural networks for liver lesion classification system

Keep up-to-date