Chronic gastritis classification using gastric X-ray images with a semi-supervised learning method based on...

Area of Science:

• Medical Imaging Analysis
• Artificial Intelligence in Medicine
• Computational Pathology

Background:

• High-quality annotations for medical images are expensive and limited, hindering deep learning applications.
• Insufficient annotated data is a significant challenge in medical image analysis for disease classification.

Purpose of the Study:

• To develop a semi-supervised learning method for chronic gastritis classification using gastric X-ray images.
• To leverage unannotated data to improve classification performance with limited annotated data.

Main Methods:

• A semi-supervised learning approach based on tri-training was employed.
• A novel learning technique, Between-Class (BC) learning, was integrated to enhance performance.
• The method was applied to chronic gastritis classification using gastric X-ray images.

Main Results:

• The proposed semi-supervised method effectively utilizes unannotated data.
• Integration of BC learning significantly boosted the performance of the semi-supervised method.
• High diagnostic accuracy for chronic gastritis was achieved.

Conclusions:

• Semi-supervised learning, particularly with BC learning, is a viable strategy to overcome data scarcity in medical image analysis.
• The developed method offers a promising approach for accurate chronic gastritis diagnosis using gastric X-ray images.
• This technique can improve the efficiency and effectiveness of deep learning models in medical diagnostics.