Leveraging Machine Learning and Artificial Intelligence in Cancer Diagnostics Imaging: A Systematic Review

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Artificial intelligence (AI) is increasingly utilized in oncology to improve cancer detection, diagnosis, and treatment planning.
• Uncertainty persists regarding the robustness and generalizability of current AI applications in cancer imaging and pathology.

Purpose of the Study:

• To systematically review evidence on AI applications in cancer imaging and pathology.
• To synthesize findings on AI effectiveness, limitations, and clinical implications.

Main Methods:

• Systematic review of studies evaluating AI systems in cancer imaging and pathology.
• Focus on diagnostic performance, clinical utility, and methodological limitations.

Main Results:

• AI demonstrated strong diagnostic performance, often matching or exceeding clinician accuracy across various cancer types and imaging modalities.
• AI shows promise in early cancer detection and decision support, potentially reducing errors and personalizing treatment.
• Limitations include lack of real-world validation, weak integration of multimodal data, underrepresentation of minority groups, and unresolved issues of transparency and bias.

Conclusions:

• AI can serve as an effective triage and decision-support tool in oncology.
• Addressing data diversity, validation, and clinical workflow integration is crucial for safe and equitable AI implementation.
• Future research should focus on prospective studies in diverse populations to ensure trustworthy AI integration into routine cancer care.