November, 2024
November 2024
M T W T F S S
 123
45678910
11121314151617
18192021222324
252627282930  
Sahar Mansour: Advancing Breast Microcalcification Detection with AI
Nov 20, 2024, 19:12

Sahar Mansour: Advancing Breast Microcalcification Detection with AI

Sahar Mansour, Professor of Radiology in the Women’s Imaging Unit at Kasr El Ainy Hospital, shared a post on LinkedIn about a recent paper by her and colleagues published in British Journal of Radiology:

” ‘Advancing Breast Microcalcification Detection with AI: New Research Insights’

A recent study performed in Baheya Foundation for early breast cancer and treatment titled ‘Artificial Intelligence Reading Digital Mammogram: Enhancing Detection and Differentiation of Suspicious Microcalcifications’ has shed light on the significant role of AI in improving mammogram accuracy published at the British Journal of Radiology.

The study utilized advanced AI technology to provide heat maps, demarcation, and quantitative evaluations, significantly aiding radiologists in their assessments for suspicious microcalcifications. This collaboration between human expertise and AI technology marks a pivotal step forward in breast microcalcification screening and diagnosis.

Key points and strengths:

  • The AI system enhanced the sensitivity of mammograms in detecting suspicious microcalcifications, showing a high correlation between AI color coding and the probability of malignancy.
  • Significant improvements in diagnostic performance with AI support to guide biopsy of the detected grouped calcifications.
  • The optimal AI cutoff value for estimating suspicion was 89%, with a sensitivity of 61% and a specificity of 80%.
  • The BI-RADS category ‘4b,’ assigned by the radiologist, demonstrated the highest sensitivity (68%) and specificity (75%).
  • The main strength of this work lies in its reproducibility, as the mammogram findings and AI scoring values were referenced against the histopathological results of surgery.

Special thanks to the dedicated authors Ola Magdy, Omnia Mokhtar, Menna Samir, Sherif Nasser Taha who made this study possible.

Methods:

  • Digital mammography (Senographe Prestina 3D, GE HealthCare.
  • AI-MMG Lunit Cancer Screening insight ver. 1.10.2, Seoul, South Korea.”

“Artificial intelligence reading digital mammogram: enhancing detection and differentiation of suspicious microcalcifications”

Authors: Sahar Mansour, Ola Magdy, Omnia Mokhtar, Menna Samir, Sherif Nasser Taha.

Sahar Mansour: Advancing Breast Microcalcification Detection with AI

More posts featuring Sahar Mansour.

Dr. Sahar Mansour is a Professor of Radiology in the Women’s Imaging Unit at Kasr El Ainy Hospital, Cairo University. She serves as Chief of the Scientific Committee for the Egyptian Society of Breast Imaging and is the Research Program Coordinator for the Radiology Department at Baheya Foundation.

Dr. Mansour also consults in breast imaging and intervention at Baheya Charity Women’s Cancer Hospital and is the Cairo Regional Coordinator for Egypt’s National Breast Cancer Screening Program with the Ministry of Health and Population.