Images Are Data: A Breast Imaging Perspective on a Contemporary Paradigm

Area of Science:

• Radiology
• Medical Imaging
• Computer Science

Background:

• The paradigm shift in diagnostic imaging views radiological examinations as data sources, particularly in breast imaging.
• This enables the application of computer science algorithms for innovative clinical applications and refined methods.
• Key terms include "imaging biomarker," "radiomics," and "artificial intelligence," promising noninvasive, cost-effective, and efficient clinical information delivery.

Purpose of the Study:

• To provide a narrative review of the paradigm shift in breast imaging, treating images as data.
• To explain key concepts and buzzwords like radiomics and imaging biomarkers.
• To discuss exemplary studies and potential clinical use cases in breast imaging.

Main Methods:

• This paper is a narrative review.
• It focuses on the "images as data" paradigm in breast imaging.
• Exemplary studies and clinical use cases are discussed.

Main Results:

• Radiomics treats breast images as a data source, extracting information beyond visual interpretation.
• Radiomic signatures act as imaging biomarkers, offering diagnostic, predictive, and prognostic value.
• These biomarkers can guide individualized breast cancer treatment.

Conclusions:

• Viewing radiological examinations as data sources optimizes patient management.
• It facilitates individualized breast cancer diagnosis and oncologic treatment within precision medicine.
• Radiomics-derived imaging biomarkers are crucial for personalized cancer care.