Related Experiment Video
Updated: Aug 5, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.9K
A Novel IoT-Enabled Healthcare Monitoring Framework and Improved Grey Wolf Optimization Algorithm-Based Deep
Reyazur Rashid Irshad1, Shahid Hussain2, Shahab Saquib Sohail3
1Department of Computer Science, College of Science and Arts, Najran University, Sharurah 68341, Saudi Arabia.
Sensors (Basel, Switzerland)
|March 30, 2023
Summary
This study introduces an improved deep learning model for early lung cancer detection using an Internet-of-Things (IoT) platform. The novel approach enhances diagnostic accuracy for lung nodules, aiding radiologists and improving patient outcomes.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Internet of Things (IoT)
Background:
- Lung cancer is a leading cause of global mortality, with early diagnosis crucial for improved patient survival rates.
- Lung nodules are key indicators for early lung cancer detection, but manual analysis by radiologists can be time-consuming and prone to error.
- Standard artificial intelligence (AI) models for lung nodule detection often rely on manually extracted features, limiting their diagnostic effectiveness.
Purpose of the Study:
- To develop a novel IoT-enabled healthcare platform for real-time patient monitoring.
- To introduce an improved grey-wolf optimization (IGWO)-based deep convolution neural network (DCNN) for enhanced lung nodule detection and lung cancer diagnosis.
- To leverage the Tasmanian Devil Optimization (TDO) algorithm for optimal feature selection in lung nodule diagnosis.
Main Methods:
- An IoT-based patient monitoring system was developed to acquire patient data.
- A novel IGWO algorithm was created by modifying the standard grey wolf optimization (GWO) algorithm for improved convergence.
- The TDO algorithm was employed to select the most relevant features for lung nodule diagnosis, which were then used to train the IGWO-based DCNN model.
Main Results:
- The IGWO-based DCNN model, trained on optimal features from the IoT platform, demonstrated high accuracy in detecting lung nodules.
- The developed model, implemented on an Android platform using Python libraries, showed competitive performance against existing lung cancer detection models.
- Findings were stored in the cloud, facilitating prompt review and judgment by medical professionals.
Conclusions:
- The proposed IoT-enabled healthcare platform and IGWO-based DCNN model offer a promising solution for accurate and early lung cancer detection.
- This AI-driven approach can significantly assist radiologists by automating lung nodule detection, thereby reducing workload and improving diagnostic rates.
- The integration of advanced optimization algorithms and deep learning within an IoT framework represents a significant advancement in computer-aided diagnosis for lung cancer.
