Related Experiment Video
Updated: Sep 5, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.9K
Intelligent Deep Learning Enabled Oral Squamous Cell Carcinoma Detection and Classification Using Biomedical Images
Adwan A Alanazi1, Manal M Khayyat2, Mashael M Khayyat3
1Department of Computer Science and Information, University of Hail, Hail, Saudi Arabia.
Computational Intelligence and Neuroscience
|July 11, 2022
Summary
This study introduces an intelligent deep learning model for early oral cancer detection. The IDL-OSCDC technique accurately identifies oral squamous cell carcinoma from biomedical images, improving diagnostic capabilities.
Area of Science:
- Biomedical Imaging
- Computational Intelligence
- Machine Learning
Background:
- Oral cancer poses a significant global health challenge, with poor prognosis often due to late-stage diagnosis.
- Current oral cancer screening relies heavily on expert knowledge, highlighting the need for automated detection tools.
- Advancements in computational intelligence and computer vision offer potential for improved medical image analysis.
Purpose of the Study:
- To develop an intelligent deep learning enabled oral squamous cell carcinoma detection and classification (IDL-OSCDC) technique.
- To enhance early detection and classification of oral cancer using biomedical images.
- To improve the accuracy and efficiency of oral cancer diagnosis through an automated system.
Main Methods:
- Utilized Gabor filtering (GF) for noise reduction in biomedical images.
- Employed the NasNet model for deep feature extraction.
- Implemented an enhanced grasshopper optimization algorithm (EGOA)-based deep belief network (DBN) for classification, with EGOA optimizing DBN hyperparameters.
Main Results:
- The IDL-OSCDC model achieved high performance on a benchmark dataset.
- Achieved maximum accuracy of 95%, precision of 96.15%, recall of 93.75%, and F1-score of 94.67%.
- Demonstrated superior performance compared to existing methods for oral cancer detection and classification.
Conclusions:
- The proposed IDL-OSCDC technique shows significant promise for accurate and automated oral cancer detection.
- The integration of deep learning, computer vision, and optimization algorithms enhances diagnostic capabilities.
- This automated approach can aid in earlier detection, potentially improving patient outcomes for oral squamous cell carcinoma.
