Transforming Breast Imaging: A Narrative Review of Systematic Evidence on Artificial Intelligence in Mammographic Practice

Abstract

<b>Background</b>: Breast cancer is still the most common type of cancer worldwide. Advances and the global use of artificial intelligence (AI) have opened up new opportunities to improve diagnostic accuracy and optimize breast cancer screening. This review summarizes the findings from systematic reviews to assess the current situation of AI integration in mammography. <b>Methods</b>: A total of 28 systematic reviews were included and analyzed using a standardized narrative checklist to assess the impact of AI on mammography imaging. Bibliometric analysis and thematic synthesis were used to assess trends, evaluate the performance of AI in different modalities and identify challenges and opportunities for clinical implementation. <b>Results and Discussion</b>: AI technologies show an overall performance comparable to radiologists in terms of sensitivity and specificity, especially when integrated with human interpretation to detect breast cancer in mammography. However, most studies are retrospective, which raises concerns about their generalizability to real-world clinical settings. Key limitations include potential dataset bias-often stemming from the over-representation of specific imaging equipment or clinical environments-limited ethnic and demographic diversity, the lack of model explainability that hinders clinical trust, and an unclear or evolving legal and regulatory framework that complicates integration into standard practice. <b>Conclusions</b>: AI has the potential to transform mammography screening, but its integration into the real world requires prospective validation, ethical safeguards and robust regulatory oversight. Coordinated international efforts are essential to ensure that AI is used safely, fairly and effectively in breast cancer diagnostics.

Ähnliche Arbeiten