Related Experiment Video
Updated: Jun 9, 2025
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
2.4K
Deep transfer learning with improved crayfish optimization algorithm for oral squamous cell carcinoma cancer
Mahmoud Ragab1, Turky Omar Asar2
1Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, 21589, Saudi Arabia. mragab@kau.edu.sa.
Scientific Reports
|October 25, 2024
Summary
This study introduces a deep learning model for accurate Oral Squamous Cell Carcinoma (OSCC) detection from histopathology images. The novel SEHDL-OSCCR technique achieves 98.75% accuracy, improving early cancer diagnosis.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Oral Squamous Cell Carcinoma (OSCC) diagnosis is challenging due to histopathology complexity and variability.
- Current diagnostic methods for OSCC have limitations in efficiency and accuracy.
- Deep learning (DL) offers potential for automated, accurate medical image analysis in oncology.
Purpose of the Study:
- To develop and evaluate a hybrid deep learning model for accurate Oral Squamous Cell Carcinoma (OSCC) recognition from histopathological images.
- To streamline the OSCC diagnostic process, enabling earlier detection and improved patient survival rates.
Main Methods:
- A Squeeze-Excitation with Hybrid Deep Learning for Oral Squamous Cell Carcinoma Recognition (SEHDL-OSCCR) model was developed.
- The technique involves bilateral filtering for noise reduction, SE-CapsNet for feature extraction, and an improved crayfish optimization algorithm (ICOA) for performance enhancement.
- Classification was performed using a Convolutional Neural Network with a Bidirectional Long Short-Term Memory (CNN-BiLSTM) model.
Main Results:
- The SEHDL-OSCCR technique demonstrated high accuracy in identifying OSCC from histopathological images.
- Experimental validation on a benchmark dataset yielded an accuracy of 98.75%.
- The proposed method outperformed recent approaches in OSCC detection accuracy.
Conclusions:
- The SEHDL-OSCCR technique shows significant promise for automated and accurate OSCC diagnosis.
- This deep learning approach can assist pathologists, reduce diagnostic turnaround times, and improve the efficacy of oral cancer detection.
- The high accuracy achieved suggests potential for clinical application in early oral cancer diagnosis.
