Kidney Cancer Prediction Empowered with Blockchain Security Using Transfer Learning.

Area of Science:

• Oncology
• Artificial Intelligence
• Medical Informatics

Background:

• Kidney cancer poses a significant threat due to limited early prediction methods.
• Early detection is crucial for timely treatment and improved patient survival rates.
• Artificial intelligence offers potential for automated cancer prediction.

Purpose of the Study:

• To develop an AI-driven model for early kidney cancer prediction.
• To integrate Internet of Medical Things (IoMT) and blockchain for secure and efficient prediction.
• To enhance diagnostic capabilities for kidney cancer.

Main Methods:

• Utilized a transfer learning technique with deep learning algorithms.
• Incorporated Internet of Medical Things (IoMT) for data acquisition.
• Employed blockchain technology for secure data management and private clouds.
• Trained the model on kidney biopsy data across three classes.

Main Results:

• Achieved a training accuracy of 99.8% and prediction accuracy of 99.20%.
• Demonstrated 93.75% prediction accuracy during validation.
• Transfer learning combined with IoMT and blockchain showed significant promise.

Conclusions:

• The proposed model effectively predicts kidney cancer in early stages.
• The integration of IoMT and blockchain enhances data security and diagnostic accuracy.
• Transfer learning offers a robust framework for improving kidney cancer diagnosis.