Medical Image Classification Utilizing Ensemble Learning and Levy Flight-Based Honey Badger Algorithm on 6G-Enabled...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Telemedicine

Background:

• The Internet of Medical Things (IoMT) is crucial for modern healthcare systems, generating vast amounts of daily hospital data.
• Accurate automatic detection and prediction of diseases like pneumonia and retinal conditions remain challenging with traditional methods.
• Existing approaches often lack the precision required for reliable medical image diagnosis.

Purpose of the Study:

• To propose a robust 6G-enabled IoMT framework for enhanced medical image classification.
• To improve the accuracy and efficiency of disease detection using advanced machine learning techniques.
• To address the limitations of traditional diagnostic methods in handling complex medical data.

Main Methods:

• Developed a 6G-enabled IoMT framework incorporating an ensemble learning (EL) model.
• Utilized MobileNet and DenseNet architectures as feature extraction backbones within the EL model.
• Implemented a modified honey badger algorithm (HBA) with Levy flight (LFHBA) for effective feature selection, removing irrelevant data.
• Evaluated the framework using chest X-ray (CXR) and optical coherence tomography (OCT) datasets.

Main Results:

• Achieved a diagnostic accuracy of 87.10% on the chest X-ray (CXR) dataset.
• Attained a diagnostic accuracy of 94.32% on the optical coherence tomography (OCT) dataset.
• Demonstrated superior accuracy and efficiency compared to existing popular algorithms in medical image classification.

Conclusions:

• The proposed 6G-enabled IoMT framework offers a highly accurate and efficient solution for medical image classification.
• The combination of ensemble learning and the LFHBA feature selection method effectively enhances diagnostic capabilities.
• This framework shows significant potential for advancing early disease detection and risk prediction in healthcare.