Evaluation of a deep learning-based software to automatically detect and quantify breast arterial calcifications on digital mammogram.

Autor: Saccenti L; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France; Henri Mondor Institute of Biomedical Research -Inserm, U955 Team N 18, Paris Est Creteil University, 94000, Creteil, France. Electronic address: laetitia.saccenti@aphp.fr., Ben Jedida B; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France., Minssen L; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France., Nouri R; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France., Bejjani LE; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France., Remili H; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France., Voquang A; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France., Tacher V; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France; Henri Mondor Institute of Biomedical Research -Inserm, U955 Team N 18, Paris Est Creteil University, 94000, Creteil, France., Kobeiter H; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France; Henri Mondor Institute of Biomedical Research -Inserm, U955 Team N 18, Paris Est Creteil University, 94000, Creteil, France., Luciani A; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France; Henri Mondor Institute of Biomedical Research -Inserm, U955 Team N 18, Paris Est Creteil University, 94000, Creteil, France., Deux JF; Department of Radiology, Geneva University Hospitals, 1205, Geneva, Switzerland., Dao TH; Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France.
Jazyk: angličtina
Zdroj: Diagnostic and interventional imaging [Diagn Interv Imaging] 2024 Oct 25. Date of Electronic Publication: 2024 Oct 25.
DOI: 10.1016/j.diii.2024.10.001
Abstrakt: Purpose: The purpose of this study was to evaluate an artificial intelligence (AI) software that automatically detects and quantifies breast arterial calcifications (BAC).
Materials and Methods: Women who underwent both mammography and thoracic computed tomography (CT) from 2009 to 2018 were retrospectively included in this single-center study. Deep learning-based software was used to automatically detect and quantify BAC with a BAC AI score ranging from 0 to 10-points. Results were compared using Spearman correlation test with a previously described BAC manual score based on radiologists' visual quantification of BAC on the mammogram. Coronary artery calcification (CAC) score was manually scored using a 12-point scale on CT. The diagnostic performance of the marked BAC AI score (defined as BAC AI score ≥ 5) for the detection of marked CAC (CAC score ≥ 4) was analyzed in terms of sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (AUC).
Results: A total of 502 women with a median age of 62 years (age range: 42-96 years) were included. The BAC AI score showed a very strong correlation with the BAC manual score (r = 0.83). Marked BAC AI score had 32.7 % sensitivity (37/113; 95 % confidence interval [CI]: 24.2-42.2), 96.1 % specificity (374/389; 95 % CI: 93.7-97.8), 71.2 % positive predictive value (37/52; 95 % CI: 56.9-82.9), 83.1 % negative predictive value (374/450; 95 % CI: 79.3-86.5), and 81.9 % accuracy (411/502; 95 % CI: 78.2-85.1) for the diagnosis of marked CAC. The AUC of the marked BAC AI score for the diagnosis of marked CAC was 0.64 (95 % CI: 0.60-0.69).
Conclusion: The automated BAC AI score shows a very strong correlation with manual BAC scoring in this external validation cohort. The automated BAC AI score may be a useful tool to promote the integration of BAC into mammography reports and to improve awareness of a woman's cardiovascular risk status.
Competing Interests: Declaration of competing interest The deep learning software have been developed by iCAD. No financial support was received to conduct the study. A research agreement for the use of the software was signed prior to the study. Data collection and data analysis were performed by the authors. The final version of the submitted manuscript was read by iCAD representatives before submission, to ensure that it did not contain any confidential information.
(Copyright © 2024. Published by Elsevier Masson SAS.)
Databáze: MEDLINE
Externí odkaz: