Purpose: To evaluate visually and quantitatively the performance of a deep-learning-based super-resolution (SR) model for microcalcifications in digital mammography.
Method: Mammograms were consecutively collected from 5080 patients who underwent breast cancer screening from January 2015 to March 2017. Of these, 93 patients (136 breasts, mean age, 50 ± 7 years) had microcalcifications in their breasts on mammograms. We applied an artificial intelligence model known as a fast SR convolutional neural network to the mammograms. SR and original mammograms were visually evaluated by four breast radiologists using a 5-point scale (1: original mammograms are strongly preferred, 5: SR mammograms are strongly preferred) for the detection, diagnostic quality, contrast, sharpness, and noise of microcalcifications. Mammograms were quantitatively evaluated using a perception-based image-quality evaluator (PIQE).
Results: All radiologists rated the SR mammograms better than the original ones in terms of detection, diagnostic quality, contrast, and sharpness of microcalcifications. These ratings were significantly different according to the Wilcoxon signed-rank test (p <.001), while the noise score of the three radiologists was significantly lower (p <.001). According to PIQE, SR mammograms were rated better than the original mammograms, showing a significant difference by paired t-test (p <.001).
Conclusion: An SR model based on deep learning can improve the visibility of microcalcifications in mammography and help detect and diagnose them in mammograms.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ejrad.2022.110433 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Perceived everyday discrimination, socioeconomic status, and mammography behavior.
Sci Rep
December 2024
Department of Health Disparities Research, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Black women (BW) experience age-adjusted breast cancer mortality rates that are 40% higher than White women. Although, screening rates for breast cancer are similar between White and Black women, differences in mammography utilization exist among women with lower socioeconomic status (SES). Moreover, perceived everyday discrimination (PED) has been shown to have an inverse relationship on health screening behavior among BW.
View Article and Find Full Text PDFFourier analysis of signal dependent noise images.
Sci Rep
December 2024
Cancer Epidemiology Department, H. Lee Moffitt Cancer Center and Research Institute, 12902 Bruce B. Downs Blvd, Tampa, FL, 33612, USA.
An archetype signal dependent noise (SDN) model is a component used in analyzing images or signals acquired from different technologies. This model-component may share properties with stationary normal white noise (WN). Measurements from WN images were used as standards for making comparisons with SDN in both the image domain (ID) and Fourier domain (FD).
View Article and Find Full Text PDFChanges to the US Preventive Services Task Force Screening Guidelines and Incidence of Breast Cancer.
JAMA Netw Open
December 2024
Department of Surgery, University of Vermont, Burlington.
Importance: The 2009 US Preventive Services Task Force breast cancer screening guideline changes led to decreases in screening mammography, raising concern about potential increases in late-stage disease and more invasive surgical treatments.
Objective: To investigate the incidence of breast cancer by stage at diagnosis and surgical treatment before and after the 2009 guideline changes.
Design, Setting, And Participants: This population-based, epidemiologic cohort study of women aged 40 years or older used 2004 to 2019 data from the National Cancer Institute's Surveillance, Epidemiology, and End Results Program.
CNN-Based Cross-Modality Fusion for Enhanced Breast Cancer Detection Using Mammography and Ultrasound.
Tomography
December 2024
Department of Medical Imaging and Radiological Science, I-Shou University, Kaohsiung City 824005, Taiwan.
Breast cancer is a leading cause of mortality among women in Taiwan and globally. Non-invasive imaging methods, such as mammography and ultrasound, are critical for early detection, yet standalone modalities have limitations in regard to their diagnostic accuracy. This study aims to enhance breast cancer detection through a cross-modality fusion approach combining mammography and ultrasound imaging, using advanced convolutional neural network (CNN) architectures.
View Article and Find Full Text PDFTowards Robust Supervised Pectoral Muscle Segmentation in Mammography Images.
J Imaging
December 2024
Computer Science and Engineering Department, College of Engineering, University of Nevada, Reno, Main Campus, Reno, NV 89557, USA.
Mammography images are the most commonly used tool for breast cancer screening. The presence of pectoral muscle in images for the mediolateral oblique view makes designing a robust automated breast cancer detection system more challenging. Most of the current methods for removing the pectoral muscle are based on traditional machine learning approaches.
View Article and Find Full Text PDFWant 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!