IoT based healthcare system using fractional dung beetle optimization enabled deep learning for breast cancer...

Area of Science:

• Medical Imaging
• Artificial Intelligence in Healthcare
• Biomedical Engineering

Background:

• Histopathological image analysis is vital for breast cancer diagnosis and patient monitoring.
• Traditional classification methods face accuracy limitations, impacting early detection and treatment.
• There is a need for advanced computational approaches to enhance breast cancer classification accuracy.

Purpose of the Study:

• To develop a novel Internet of Things (IoT) based healthcare system for breast cancer detection.
• To implement a SqueezeNet_Fractional Dung Beetle Optimization (Squeeze_FDBO) model for accurate classification.
• To optimize image routing and classification processes within the IoT healthcare framework.

Main Methods:

• Simulation of an IoT network for routing histopathological images to a Base Station (BS).
• Utilization of Fractional Dung Beetle Optimization (FDBO) for efficient image routing.
• Implementation of a SqueezeNet model tuned by FDBO for multigrade breast cancer classification after image pre-processing (bilateral filter) and segmentation (LadderNet).

Main Results:

• The Squeeze_FDBO model achieved high performance metrics: accuracy (0.919), sensitivity (0.913), specificity (0.923), NPV (0.920), and PPV (0.908).
• Optimized routing performance was demonstrated with low energy consumption (0.405 J), distance (6.901 m), and delay (0.650 mS).
• The proposed system significantly improves upon traditional methods for breast cancer classification.

Conclusions:

• The developed IoT-based healthcare system using Squeeze_FDBO offers a promising approach for accurate and efficient breast cancer detection.
• The integration of advanced optimization and deep learning techniques enhances diagnostic capabilities in medical imaging.
• This system has the potential to improve early detection rates and patient outcomes in breast cancer management.