Diagnostic performance of an experienced radiologist and Quantra artificial intelligence software in the assessment of mammographic breast density

Introduction: The diagnostic performance of the current version of Quantra artificial intelligence (AI) software has not been evaluated. This study aimed to compare the diagnostic performance of an experienced radiologist and Quantra AI in assessing mammographic breast density (MBD). Material and methods: In this prospective cohort study, a radiologist with 32 years of experience interpreting breast images and AI Quantra v2.2.2 assessed MBD in 2D mammograms and tomosynthesis of women over 35. Four and two MBD categories based on American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) 5th Edition lexicon were analyzed. Diagnostic performance parameters of Quantra AI and an experienced radiologist were calculated and compared as the gold standard for MBD. Results: The highest sensitivity of Quantra AI compared to an experienced radiologist as the gold standard in four MBD categories was in category d, and the lowest was in category b. In contrast, specificity was high in categories a and b. The accuracy of Quantra AI was highest in categories a and d. Sensitivity in two categories was best for dense breasts and specificity for non-dense breasts. The accuracy was the same for both categories. When the Quantra AI was the gold standard, the experienced radiologist showed the best sensitivity in category b and the lowest in category d. Specificity was higher in categories a and d and accuracy was better in category c. In two MBD categories, sensitivity was highest for non-dense breasts and specificity for dense breasts. The accuracy was equally high in both categories. Conclusion: The diagnostic performance of Quantra AI was good with the current software version in four and two MBD categories compared to an experienced radiologist as the gold standard. On the other hand, the experienced radiologist showed good sensitivity and specificity for non-dense and dense breasts and a wide range of results in diagnostic performance in four MBD categories compared to Quantra AI as the gold standard. Even if the radiologist is experienced, subjectivity still exists, and the help of a tool like AI can be valuable.

Authors

Publication Details

Journal
Journal of the Mexican Federation of Radiology and Imaging
Published
2025-04-23
DOI
https://doi.org/10.24875/jmexfri.m25000094
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Diagnostic performance of an experienced radiologist and Quantra artificial intelligence software in the assessment of mammographic breast density

Claudia B. Corona-Gonzalez, Beatriz E. Gonzalez-Ulloa, Rosa L. Molina-Gutierrez
Journal of the Mexican Federation of Radiology and Imaging
AI in cancer detection
article

Diagnostic performance of an experienced radiologist and Quantra artificial intelligence software in the assessment of mammographic breast density

Claudia B. Corona-Gonzalez, Beatriz E. Gonzalez-Ulloa, Rosa L. Molina-Gutierrez
article en

Abstract

Introduction: The diagnostic performance of the current version of Quantra artificial intelligence (AI) software has not been evaluated. This study aimed to compare the diagnostic performance of an experienced radiologist and Quantra AI in assessing mammographic breast density (MBD). Material and methods: In this prospective cohort study, a radiologist with 32 years of experience interpreting breast images and AI Quantra v2.2.2 assessed MBD in 2D mammograms and tomosynthesis of women over 35. Four and two MBD categories based on American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) 5th Edition lexicon were analyzed. Diagnostic performance parameters of Quantra AI and an experienced radiologist were calculated and compared as the gold standard for MBD. Results: The highest sensitivity of Quantra AI compared to an experienced radiologist as the gold standard in four MBD categories was in category d, and the lowest was in category b. In contrast, specificity was high in categories a and b. The accuracy of Quantra AI was highest in categories a and d. Sensitivity in two categories was best for dense breasts and specificity for non-dense breasts. The accuracy was the same for both categories. When the Quantra AI was the gold standard, the experienced radiologist showed the best sensitivity in category b and the lowest in category d. Specificity was higher in categories a and d and accuracy was better in category c. In two MBD categories, sensitivity was highest for non-dense breasts and specificity for dense breasts. The accuracy was equally high in both categories. Conclusion: The diagnostic performance of Quantra AI was good with the current software version in four and two MBD categories compared to an experienced radiologist as the gold standard. On the other hand, the experienced radiologist showed good sensitivity and specificity for non-dense and dense breasts and a wide range of results in diagnostic performance in four MBD categories compared to Quantra AI as the gold standard. Even if the radiologist is experienced, subjectivity still exists, and the help of a tool like AI can be valuable.

Journal of the Mexican Federation of Radiology and ImagingVol. 4(1)
Openalex Percentile: Top 96%
AI in cancer detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Diagnostic performance of an experienced radiologist and Quantra artificial intelligence software in the assessment of mammographic breast density — Claudia B. Corona-Gonzalez, Beatriz E. Gonzalez-Ulloa, et al. · Journal of the Mexican Federation of Radiology and Imaging (2025) | TGRS Research Map | TGRS