AI potential in PET/CT cancer imaging.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Nuclear Medicine

Background:

• Positron emission tomography/computed tomography (PET/CT) is a hybrid imaging technique vital for oncology and medical diagnosis.
• AI offers potential solutions to enhance various aspects of medical imaging in Nuclear Medicine.

Purpose of the Study:

• To review the state-of-the-art applications of Artificial Intelligence (AI) in PET/CT imaging.
• To focus on AI's role in enhancing tumor segmentation, classification, diagnosis, and survival prediction in oncology.

Main Methods:

• Review of recent advancements in AI, machine learning (ML), and deep learning (DL) applied to PET/CT.
• Analysis of AI's utilization in conjunction with radiomics for quantitative image analysis.

Main Results:

• AI applications demonstrate reliable results, particularly in classification and diagnosis within PET/CT oncology.
• Radiomics facilitates AI model implementation through quantitative feature extraction from medical images.

Conclusions:

• AI, ML, and DL significantly enhance PET/CT oncology imaging capabilities.
• Addressing dataset size, standardization, and ethical considerations is crucial for widespread clinical adoption of AI in PET/CT.