An adaptive multiscale local mesh ternary pattern technique with extensive pre-processing and Grey Wolf optimisation based classifiers for oral cancer image classification
Abstract
This study introduces an enhanced texture-based algorithm for the classification of oral cancer images. The images are first extensively preprocessed to enhance the affected area with techniques like gamma correction, adaptive histogram equalization, and sharpening of images using a Laplacian filter. Then a feature descriptor is extracted using an Adaptive Multiscale Local Mesh ternary patterns, which uses an adaptive threshold, and a sliding window of multiple scales. A machine learning model is then used for classification, which is also optimised using Grey Wolf optimisation. The pedagogy yields an overall average accuracy of 98.29% and 99.89% on two publicly available datasets. Also, the model is compared to three state-of-the-art techniques for oral cancer detection and is found to give an average improvement of 9.21% and 20.67% on the respective datasets.
Read the paper
Related studies
- eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses
- Online Survival Analysis Software to Assess the Prognostic Value of Biomarkers Using Transcriptomic Data in Non-Small-Cell Lung Cancer
- OptiType: precision HLA typing from next-generation sequencing data
- Nicotinic Cholinergic System and COVID-19: In Silico Identification of an Interaction between SARS-CoV-2 and Nicotinic Receptors with Potential Therapeutic Targeting Implications
- Saccharomyces cerevisiae cells have three Omega class glutathione S-transferases acting as 1-Cys thiol transferases
- Hemolysis at low blood flow rates: in-vitro and in-silico evaluation of a centrifugal blood pump
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.