A Survey on AI Techniques for Thoracic Diseases Diagnosis Using Medical Images

Area of Science:

• Medical imaging analysis
• Artificial intelligence in healthcare
• Radiology and thoracic medicine

Background:

• Thoracic diseases affect millions globally, necessitating early and accurate detection.
• Traditional diagnosis relies on expert radiologists, which can be time-consuming and resource-intensive.
• Advancements in image processing and deep learning present opportunities for automated thoracic disease detection.

Purpose of the Study:

• To provide a comprehensive review of deep learning applications for thoracic disease detection.
• To systematically analyze various deep learning models, image pre-processing techniques, and transfer learning strategies.
• To compare the performance of different models and datasets used in thoracic image analysis.

Main Methods:

• Review of existing literature on deep learning models for thoracic disease detection.
• Analysis of image pre-processing techniques relevant to medical imaging.
• Exploration of transfer learning and ensemble learning methodologies.
• Performance comparison of various deep learning models and datasets.

Main Results:

• Deep learning models show significant potential for automating the detection of various thoracic diseases.
• Different models exhibit varying performance levels depending on the specific disease and dataset.
• Transfer learning and ensemble methods can enhance the efficacy of deep learning models.

Conclusions:

• Deep learning offers a powerful tool for enhancing the early detection of thoracic diseases.
• Further research into optimizing models and datasets is crucial for clinical implementation.
• This review serves as a valuable resource for researchers in deep learning and medical imaging.