Application of Machine Learning to Breast MR Imaging.

Area of Science:

• Radiology
• Medical Imaging
• Oncology

Background:

• Growing demand for breast imaging services, driven by expanded breast cancer diagnosis and treatment indications.
• Artificial intelligence (AI) shows promise for enhancing workflow efficiency and utilizing imaging data in breast cancer care.
• AI adoption in breast MRI lags behind mammography due to examination complexity and limited annotated datasets.

Purpose of the Study:

• To explore the implementation of AI in breast MRI across the breast cancer care pathway.
• To highlight AI's potential to revolutionize breast cancer detection and management.
• To provide a comprehensive overview of AI's impact on breast MRI and patient outcomes.

Main Methods:

• Review of current AI advancements in mammography and digital breast tomosynthesis.
• Analysis of challenges hindering AI adoption in breast MRI, including data availability and examination complexity.
• Examination of emerging AI applications in breast MRI.

Main Results:

• AI has made significant strides in mammography and digital breast tomosynthesis, with computer-aided detection (CAD) systems widely used.
• Breast MRI presents unique challenges for AI implementation, including inherent complexity and limited large, annotated datasets.
• Despite challenges, strong interest exists in AI for breast MRI due to its expanding use and indications.

Conclusions:

• AI holds significant potential to enhance breast MRI applications in breast cancer diagnosis and treatment.
• Addressing current challenges in data and complexity is crucial for broader AI implementation in breast MRI.
• AI is poised to reshape breast MRI practices, ultimately improving patient outcomes in breast cancer care.