Radiomic analysis of cohort-specific diagnostic errors in reading dense mammograms using artificial intelligence
British Journal of Radiology · 2025
DOI: 10.1093/bjr/tqae195 ↗Kurz gefasst
Fachartikel in der Zeitschrift British Journal of Radiology, 2025. Verfasst von Xuetong Tao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Discipline of Medical Imaging Science, Faculty of Health Sciences, Western Ave, Camperdown NSW 2050, Australia. Hauptthemen laut MEDLINE: Mammography, Artificial Intelligence, Breast Neoplasms, Diagnostic Errors. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cancer Institute NSW Early Career, National Breast Cancer Foundation.
Abstract (Originalsprache)
Objectives
This study aims to investigate radiologists’ interpretation errors when reading dense screening mammograms using a radiomics-based artificial intelligence approach.
Methods
Thirty-six radiologists from China and Australia read 60 dense mammograms. For each cohort, we identified normal areas that looked suspicious of cancer and the malignant areas containing cancers. Then radiomic features were extracted from these identified areas and random forest models were trained to recognize the areas that were most frequently linked to diagnostic errors within each cohort. The performance of the model and discriminatory power of significant radiomic features were assessed.
Results
We found that in the Chinese cohort, the AUC values for predicting false positives were 0.864 (CC) and 0.829 (MLO), while in the Australian cohort, they were 0.652 (CC) and 0.747 (MLO). For false negatives, the AUC values in the Chinese cohort were 0.677 (CC) and 0.673 (MLO), and in the Australian cohort, they were 0.600 (CC) and 0.505 (MLO). In both cohorts, regions with higher Gabor and maximum response filter outputs were more prone to false positives, while areas with significant intensity changes and coarse textures were more likely to yield false negatives.
Conclusions
This cohort-based pipeline proves effective in identifying common errors for specific reader cohorts based on image-derived radiomic features. Advances in knowledge This study demonstrates that radiomics-based AI can effectively identify and predict radiologists' interpretation errors in dense mammograms, with distinct radiomic features linked to false positives and false negatives in Chinese and Australian cohorts.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Discipline of Medical Imaging Science, Faculty of Health Sciences, Western Ave, Camperdown NSW 2050, Australia.
- The Daffodil Centre, The University of Sydney, A Joint Venture with Cancer Council NSW, Sydney, NSW 2006, Australia.
- Sydney School of Public Health, Faculty of Medicine and Health, The University of Sydney, Sydney, NSW 2006, Australia.
ORCID-Profile: Xuetong Tao, Warren M Reed
Förderung
- Cancer Institute NSW Early Career
- National Breast Cancer Foundation
Zitieren
APA
Tao, X., Gandomkar, Z., Li, T., Brennan, P. C., & Reed, W. M. (2025). Radiomic analysis of cohort-specific diagnostic errors in reading dense mammograms using artificial intelligence. British Journal of Radiology. https://doi.org/10.1093/bjr/tqae195
Vancouver
Tao X, Gandomkar Z, Li T, Brennan PC, Reed WM. Radiomic analysis of cohort-specific diagnostic errors in reading dense mammograms using artificial intelligence. British Journal of Radiology. 2025. doi:10.1093/bjr/tqae195
BibTeX
@article{Tao2025,
author = {Tao, Xuetong and Gandomkar, Ziba and Li, Tong and Brennan, Patrick C and Reed, Warren M},
title = {Radiomic analysis of cohort-specific diagnostic errors in reading dense mammograms using artificial intelligence},
journal = {British Journal of Radiology},
year = {2025},
doi = {10.1093/bjr/tqae195}
}
EUVIMED