An IoT-Based Deep Learning Framework for Early Assessment of Covid-19

Area of Science:

• Medical Imaging
• Artificial Intelligence in Healthcare
• Internet of Medical Things (IoMT)

Background:

• The COVID-19 pandemic highlighted the need for rapid diagnostic tools.
• Existing deep learning models for COVID-19 detection using X-rays have limitations.
• The integration of IoMT and AI offers new possibilities for remote healthcare and data analysis.

Purpose of the Study:

• To develop an IoT-based deep learning framework for early COVID-19 assessment.
• To investigate the efficacy of regional convolutional neural networks (CNNs) for COVID-19 detection.
• To reduce the workload on medical experts and aid in pandemic control.

Main Methods:

• Utilized chest X-ray images for COVID-19 detection.
• Applied a deep learning model: Faster Regions with CNNs (Faster-RCNN) with ResNet-101.
• Employed a region proposal network (RPN) for detection within the Faster-RCNN framework.

Main Results:

• Achieved a COVID-19 detection accuracy of 98% using the proposed framework.
• Demonstrated the effectiveness of the Faster-RCNN model with ResNet-101 on X-ray data.
• The system shows potential for assisting radiologists in early COVID-19 assessment.

Conclusions:

• The developed IoT-based deep learning framework enables efficient early assessment of COVID-19.
• The Faster-RCNN model shows high accuracy in detecting COVID-19 from chest X-rays.
• This technology can support healthcare professionals and contribute to managing infectious disease outbreaks.