AI Article Synopsis
Article Abstract
Flat-panel digital detector systems have limited dynamic range and saturate at a particular x-ray exposure. Hence some of the breast edge may not be represented in the displayed image. We developed a model to estimate the amount of skin loss. Model predictions agreed well with phantom measurements. In our database of 884 clinical digital mammograms, 98% had saturated backgrounds. The estimated skin loss exceeded 0.5 mm in 5% of images and 1.0 mm in 0.7% of images. Any skin thickening that is present should still be visualized, so we conclude that any skin-line loss may not be of clinical significance.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1118/1.1796091 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Digital Mammography, Tomosynthesis, and Contrast-Enhanced Mammography: Intraindividual Comparison of Mean Glandular Dose for Screening Examinations.
AJR Am J Roentgenol
January 2025
Department of Radiology, Division of Breast Imaging and Intervention, Mayo Clinic, Phoenix, AZ.
Contrast-enhanced mammography (CEM) is growing in clinical use due to its increased sensitivity and specificity compared to full-field digital mammography (FFDM) and/or digital breast tomosynthesis (DBT), particularly in patients with dense breasts. To perform an intraindividual comparison of MGD between FFDM, DBT, a combination protocol using both FFDM and DBT (combined FFDM-DBT), and CEM, in patients undergoing breast cancer screening. This retrospective study included 389 women (median age, 57.
View Article and Find Full Text PDFAttention-guided erasing for enhanced transfer learning in breast abnormality classification.
Int J Comput Assist Radiol Surg
January 2025
Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Martensstr. 3, 91058, Erlangen, Bayern, Germany.
Purpose: Breast cancer remains one of the most prevalent cancers globally, necessitating effective early screening and diagnosis. This study investigates the effectiveness and generalizability of our recently proposed data augmentation technique, attention-guided erasing (AGE), across various transfer learning classification tasks for breast abnormality classification in mammography.
Methods: AGE utilizes attention head visualizations from DINO self-supervised pretraining to weakly localize regions of interest (ROI) in images.
Enhancing detection of previously missed non-palpable breast carcinomas through artificial intelligence.
Eur J Radiol Open
June 2025
Radiology Department, National Cancer Institute, Cairo University, Egypt.
Purpose: To investigate the impact of artificial intelligence (AI) reading digital mammograms in increasing the chance of detecting missed breast cancer, by studying the AI- flagged early morphology indictors, overlooked by the radiologist, and correlating them with the missed cancer pathology types.
Methods And Materials: Mammograms done in 2020-2023, presenting breast carcinomas (n = 1998), were analyzed in concordance with the prior one year's result (2019-2022) assumed negative or benign. Present mammograms reviewed for the descriptors: asymmetry, distortion, mass, and microcalcifications.
The impact of the BreastScreen NSW transition from film to digital mammography, 2002-2016: a linked population health data analysis.
Med J Aust
January 2025
Sydney School of Public Health, the University of Sydney, Sydney, NSW.
Objectives: To assess the impact of the transition from film to digital mammography in the Australian national breast cancer screening program.
Study Design: Retrospective linked population health data analysis (New South Wales Central Cancer Registry, BreastScreen NSW); interrupted time series analysis.
Setting: New South Wales, 2002-2016.
The Screening Tomosynthesis Trial with Advanced Reader Methods (STREAM): design and rationale of a population-based breast cancer screening trial.
Eur Radiol
January 2025
Radboud University Medical Center, IQ Health science department, Nijmegen, The Netherlands.
Objectives: It is uncertain what the effects of introducing digital breast tomosynthesis (DBT) in the Dutch breast cancer screening programme would be on detection, recall, and interval cancers (ICs), while reading times are expected to increase. Therefore, an investigation into the efficiency and cost-effectiveness of DBT screening while optimising reading is required.
Materials And Methods: The Screening Tomosynthesis trial with advanced REAding Methods (STREAM) aims to include 17,275 women (age 50-72 years) eligible for breast cancer screening in the Netherlands for two biennial DBT screening rounds to determine the short-, medium-, and long-term effects and acceptability of DBT screening and identify an optimised strategy for reading DBT.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!