Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
An Exploration of Discrepant Recalls Between AI and Human Readers of Malignant Lesions in Digital Mammography Screening
4
Zitationen
10
Autoren
2025
Jahr
Abstract
Lesions missed by AI were smaller and less often calcified than cancers missed by human readers. Cancers missed by AI tended to show lower levels of suspicion than those missed by human readers. While definitive conclusions are premature, the findings highlight the complementary roles of AI and human readers in mammographic interpretation.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 14.019 Zit.
pROC: an open-source package for R and S+ to analyze and compare ROC curves
2011 · 13.808 Zit.
Dermatologist-level classification of skin cancer with deep neural networks
2017 · 13.528 Zit.
A survey on Image Data Augmentation for Deep Learning
2019 · 12.149 Zit.
QuPath: Open source software for digital pathology image analysis
2017 · 8.437 Zit.
Autoren
Institutionen
- Radboud University Nijmegen(NL)
- Radboud University Medical Center(NL)
- Vrije Universiteit Amsterdam(NL)
- Amsterdam UMC Location Vrije Universiteit Amsterdam(NL)
- Dutch Expert Centre for Screening(NL)
- University of Twente(NL)
- Leiden University Medical Center(NL)
- Istituto Oncologico Veneto(IT)
- Istituti di Ricovero e Cura a Carattere Scientifico(IT)
- Universidad Complutense de Madrid(ES)
- Vienna General Hospital(AT)
- Medical University of Vienna(AT)
- The Netherlands Cancer Institute(NL)
- Addenbrooke's Hospital(GB)