[Research progress in medical imaging based on deep learning of neural network]

Area of Science:

• Medical Imaging Analysis
• Machine Learning
• Radiology

Background:

• Advancements in computer hardware enable rapid accumulation of medical imaging data.
• Deep learning (DL) has emerged as a powerful tool for analyzing this complex data.
• DL represents a significant new area within machine learning for healthcare.

Purpose of the Study:

• To introduce commonly used deep learning models.
• To summarize DL applications in medical imaging, including detection, classification, diagnosis, segmentation, and identification.
• To propose DL applications in oral and maxillofacial radiology and other stomatology disciplines.

Main Methods:

• Review of existing literature on deep learning models.
• Categorization of DL applications across various medical imaging tasks.
• Exploration of DL's potential in specialized fields like oral and maxillofacial radiology.

Main Results:

• Deep learning models demonstrate substantial potential in medical imaging data analysis.
• Established applications include image detection, classification, diagnosis, segmentation, and identification.
• Emerging applications are proposed for oral and maxillofacial radiology and stomatology.

Conclusions:

• Deep learning offers transformative capabilities for medical imaging analysis.
• Further research is needed to address existing challenges in implementing DL in medical imaging.
• The integration of DL holds promise for advancing diagnostic accuracy and efficiency in radiology and dentistry.