Harbor seal whiskers optimization algorithm with deep learning-based medical imaging analysis for gastrointestinal...

Area of Science:

• Medical Imaging Analysis
• Artificial Intelligence in Oncology

Background:

• Early gastrointestinal (GI) cancer detection is crucial for treatment success and patient outcomes.
• Medical imaging modalities like CT, MRI, and endoscopy are vital for identifying GI lesions.
• Artificial intelligence (AI) and machine learning (ML) are increasingly used in medical imaging for cancer diagnosis.

Purpose of the Study:

• To introduce a novel Harbor Seal Whiskers Optimization Algorithm with Deep Learning based Medical Imaging Analysis for Gastrointestinal Cancer Detection (HSWOA-DLGCD).
• To enhance the accuracy and efficiency of GI cancer diagnosis through advanced AI techniques.

Main Methods:

• The HSWOA-DLGCD technique employs bilateral filtering (BF) for noise reduction in GI images.
• Feature extraction is performed using the Harbor Seal Whiskers Optimization Algorithm (HSWOA) combined with the Xception model.
• Cancer recognition is achieved using the extreme gradient boosting (XGBoost) model, with parameter optimization via moth flame optimization (MFO).

Main Results:

• The HSWOA-DLGCD technique was validated on the Kvasir database.
• Experimental outcomes demonstrated superior performance compared to existing methods for GI cancer detection.

Conclusions:

• The proposed HSWOA-DLGCD method offers a promising advancement in AI-driven medical imaging for gastrointestinal cancer detection.
• This approach has the potential to significantly improve early diagnosis and patient management in oncology.