Introduction:

Breast cancer remains one of the most prevalent cancers globally, specifically the most common in females. The use of artificial intelligence promises to contribute to early diagnosis through imaging. Previously, the landscape and evolution of this scientific production have not been described.

Methods:

Cross-sectional bibliometric study using Scopus as the data source. The bibliometrix package in R was employed for calculating bibliometric indicators and visualizing the results.

Results:

1292 documents published between 1989 and 2024 were selected. 75.3% (n=973) were articles with primary data, followed by 16.2% (n=209) corresponding to reviews. An international collaboration rate of 26.5% was identified, with an annual production growth of 10.78%. It was observed that risk classification through screening, digital breast tomosynthesis, transfer learning, segmentation, and feature selection were the most commonly used keywords. In the last five years, deep learning and mammography have been the most popular topics. International collaboration has been led by the United States, China, and the United Kingdom.

Conclusion:

A notable growth in global research on the use of artificial intelligence in breast cancer imaging for detection was identified, particularly since the 2010s, primarily through the publication of articles with primary data. The relationship between artificial intelligence and imaging for breast cancer diagnosis has focused on risk and prediction.

        · resumen en Español     · texto en Español | Inglés     · Español ( pdf ) | Inglés ( pdf )