[Research progress on computed tomography image detection and classification of pulmonary nodule based on deep...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Oncology

Background:

• Computer-aided diagnosis using computed tomography (CT) is crucial for early lung cancer detection and classification.
• Deep learning is rapidly advancing auxiliary lung cancer diagnosis, becoming a key research area.

Purpose of the Study:

• To review research progress in deep learning for pulmonary nodule detection and classification from CT images.
• To provide a reference for future applications in AI-driven lung cancer diagnosis.

Main Methods:

• Review of recent domestic and international literature on deep learning for lung nodule detection and classification.
• Introduction to prominent lung CT image databases: LIDC-IDRI and Data Science Bowl 2017.
• Detailed discussion of pulmonary nodule detection and classification using various deep learning network structures.

Main Results:

• Deep learning models show significant potential in analyzing lung CT images for nodule detection and classification.
• Different network architectures offer varying performance characteristics for this task.
• Identified challenges and limitations in current deep learning applications for lung CT analysis.

Conclusions:

• Deep learning is a promising tool for enhancing the accuracy and efficiency of pulmonary nodule detection and classification.
• Further research is needed to address existing challenges and optimize deep learning models for clinical application.
• The field shows a strong development prospect for AI in early lung cancer diagnosis.