Artificial intelligence in oncology: Current status and possibilities (Review)

Area of Science:

• Oncology
• Artificial Intelligence
• Machine Learning

Background:

• Artificial intelligence (AI) is increasingly integrated into oncology, impacting diagnostic accuracy, prognostication, and personalized treatment strategies.
• Machine learning (ML) and deep learning (DL) models, including convolutional neural networks (CNNs) and transformers, show significant promise in cancer research.

Purpose of the Study:

• To critically review current AI applications in oncology, covering imaging, digital pathology, outcome prediction, and treatment planning.
• To synthesize recent advancements and identify challenges hindering the clinical translation of AI in cancer care.

Main Methods:

• Review of contemporary literature on AI applications in various oncology domains.
• Analysis of machine learning and deep learning model performance in tasks like lesion detection, tumor grading, and survival prediction.

Main Results:

• AI models demonstrate expert-level or superior accuracy in specific oncological tasks, including image analysis and outcome prediction.
• Significant barriers to clinical implementation exist, such as dataset bias, limited generalizability, lack of standardization, interpretability issues, and regulatory hurdles.

Conclusions:

• AI holds immense potential to advance precision oncology and improve global cancer outcomes.
• Overcoming challenges through multidisciplinary collaboration, prospective validation, and ethical governance is crucial for realizing AI's full potential in cancer care.