Sahar Mansour, Professor of Radiology at Kasr Al-Ainy Hospital, Cairo University, and Consultant of Breast Imaging and Intervention at Baheya Charity Women’s Cancer Hospital, shared a post on LinkedIn about an article she co-authored published on Spring Nature Link:

“Thrilled to share my latest publication, ‘How artificial intelligence is changing the way we understand grouped breast microcalcifications’

Grouped breast microcalcifications are often the only sign of early breast cancer on mammography. Yet they pose a major challenge:false positives can lead to unnecessary biopsies, while false negatives risk delayed diagnosis. We wanted to explore whether AI could help radiologists improve accuracy, reduce patient stress, and optimize decision‑making.

We applied an FDA‑approved AI solution to read mammograms showing grouped microcalcifications, comparing its abnormality scoring with histopathology results.

What we found

Coarse heterogeneous calcifications:strongest sensitivity (87.5%) for malignancy detection.
Amorphous calcifications: most reliably identified as benign, with the highest accuracy (80.6%).
Fine linear calcifications: lowest performance, highlighting areas for model improvement.

Conclusion
AI can enhance diagnostic precision, especially in detecting malignancy in coarse heterogeneous calcifications and ruling out benign cases in amorphous types. This could reduce unnecessary biopsies and support radiologists in early breast cancer detection.”

Title: How artificial intelligence is changing the way we understand grouped breast microcalcifications?

Authors: Sahar Mansour, Abeer Ali El-Sharawy, Salma Moheeb Abdelghaffar, Ghada Mohammed Abdel-Salam, Rehab ElSheikh