article · IEEE Access
Oral cancer presents a severe health challenge, particularly across low- and middle-income nations where early and affordable diagnosis remains vital. Automating the detection of precancerous and malignant lesions from medical images offers a pathway to timely treatment, yet existing machine learning methods often lack sufficient precision. A new detection framework addresses this challenge by combining a convolutional neural network with an optimised deep belief network. To fine-tune the architecture, a hybrid meta-heuristic technique brings together particle swarm optimisation and Al-Biruni earth radius optimisation methods. When evaluated on a standard biomedical image dataset, this diagnostic strategy attained an accuracy of 97.35 percent, outperforming several alternative methods. Statistical evaluations, including analysis of variance and signed-rank tests, confirm the stability and significance of the model, which specialists can adopt subject to further validation on larger datasets.
Oral cancer is a lethal condition that heavily affects low- and middle-income regions. Automated diagnostic systems that identify malignant and precancerous lesions from routine images can lower costs and expand access to early diagnosis. Achieving high accuracy reduces diagnostic errors, potentially assisting medical specialists in detecting life-threatening tumours before they advance.
The primary application is automated diagnostic software to support medical specialists analysing clinical mouth imagery. The technology is at an applied research stage, validated on a benchmark repository dataset. Moving towards real-world adoption will require testing on larger datasets to confirm performance across broader patient populations and to incorporate additional oral characteristics.
AI-generated from the published abstract. Always read the original work before citing.
Oral cancer is a deadly form of cancerous tumor that is widely spread in low and middle-income countries. An early and affordable oral cancer diagnosis might be achieved by automating the detection of precancerous and malignant lesions in the mouth. There are many research attempts to develop a robust machine-learning model that can detect oral cancer from images. However, these are still lacking high precision in oral cancer detection. Therefore, this work aims to propose a new approach capable of detecting oral cancer in medical images with higher accuracy. In this work, a novel and robust oral cancer detection based on a convolutional neural network (CNN) and optimized deep belief network (DBN). The design parameters of CNN and DBN are optimized using a new optimization algorithm, which is developed as a hybrid of Particle Swarm Optimization (PSO) and Al-Biruni Earth Radius (BER) Optimization algorithms and is denoted by (PSOBER). Using a standard biomedical images dataset available on the Kaggle repository, the proposed approach shows promising results outperforming various competing approaches with an accuracy of 97.35%. In addition, a set of statistical tests, such as One-way analysis-of-variance (ANOVA) and Wilcoxon signed-rank tests, are conducted to prove the significance and stability of the proposed approach. The proposed methodology is solid and efficient, and specialists can adopt it. However, additional research on a larger scale dataset is required to confirm the findings and highlight other oral features that can be utilized for cancer detection.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2023.3253430
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
