A dense kernel point convolutional neural network for chronic liver disease classification with hybrid chaotic slime mould and giant trevally optimizer

Dimensions

Saranya, R. and R, Jaichandran K. (2025) A dense kernel point convolutional neural network for chronic liver disease classification with hybrid chaotic slime mould and giant trevally optimizer. Biomedical Signal Processing and Control, 102. ISSN 17468108; 17468094

Full text not available from this repository.

Abstract

Chronic liver disease affects liver tissues and may lead to liver failure. This paper presents the DKPCNN-CLDC-HybCSM-GTO model integrating fuzzy segmentation and wavelet-scattering features. It significantly outperformed existing methods with improvements of 22.36% to 25.42% in accuracy, sensitivity, and specificity. The model provides a valuable framework for early diagnosis of chronic liver disease.

Item Type: Article
Additional Information: Cited by: 3
Uncontrolled Keywords: Computerized tomography; Diseases; Fuzzy clustering; Fuzzy inference; Fuzzy neural networks; Image segmentation; Ultrasonic applications; Wavelet transforms; Chaotics; Convolutional neural network; Dense kernel point convolutional neural network; Dense kernels; Hybrid chaotic slime mold and giant trevally optimizer; Intuitionistic fuzzy; Intuitionistic fuzzy C-ordered mean clustering; Invariant wavelet scattering transform; Means clustering; Optimizers; Scattering transforms; Slime moulds; Biopsy; Article; chronic liver disease; computer assisted tomography; controlled study; convolutional neural network; diagnostic accuracy; disease classification; echography; fatty liver; feature extraction; fuzzy c means clustering; hepatitis; human; image segmentation; k fold cross validation; liver cancer; liver cirrhosis; liver fibrosis; machine learning; nuclear magnetic resonance imaging; radiomics; sensitivity analysis; sensitivity and specificity
Subjects: Computer Science > Artificial Intelligence
Divisions: Arts and Science > School of Arts and Science, Chennai > Computer Science
Depositing User: Unnamed user with email techsupport@mosys.org
Date Deposited: 26 Nov 2025 10:04
Last Modified: 26 Nov 2025 10:04
URI: https://vmuir.mosys.org/id/eprint/219

Actions (login required)

View Item
View Item