Lymph node disease in 2-deoxy-2-fluorodeoxyglucose positron emission tomography/computed tomography imaging: Advances...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Oncology

Background:

• Traditional lymph node imaging analysis suffers from low efficiency and inconsistency.
• Deep learning, particularly convolutional neural networks, offers advanced solutions for radiomics analysis.

Purpose of the Study:

• To review artificial intelligence (AI) applications in lymph node disease management.
• To provide a basis for AI-assisted clinical decision-making in lymph node pathology.

Main Methods:

• Focus on automatic lymph node segmentation models.
• Review of treatment response prediction algorithms.
• Analysis of benign and malignant differential diagnosis systems using multimodal imaging.

Main Results:

• Deep learning significantly improves radiomics in lymph node analysis.
• AI enhances automatic detection, precise segmentation, and 3D reconstruction of lymph nodes.
• AI facilitates efficacy monitoring and pathological characteristic analysis.

Conclusions:

• AI-driven radiomics shows promise for accurate lymph node disease diagnosis.
• AI can support personalized treatment and prognostic evaluation.
• Further research in AI is crucial for advancing lymph node disease management.