Designers of a project called the National Digital Mammography Archive are assembling a prototype national database comprising thousands of digital mammograms. Their goal is to assist and improve breast cancer detection and diagnosis. The NDMA, a
Designers of a project called the National Digital Mammography Archive are assembling a prototype national database comprising thousands of digital mammograms. Their goal is to assist and improve breast cancer detection and diagnosis.
The NDMA, a collaborative effort among four universities, is expected to be complete in 2003. Planners hope the archive will create unique opportunities for researchers to study and understand many epidemiological issues associated with breast cancer.
"With mammograms stored in one central location, researchers will have better access to certain demographic information, enabling them to develop educational or interventional programs," said Dr. Mitchell Schnall, chief of MRI at the University of Pennsylvania and the project's principal investigator. Also participating are the University of Chicago, the University of Toronto, and the University of North Carolina.
Clinicians accessing this new database will be able to instantly retrieve a woman's mammogram prior to her appointment, relieving her of the responsibility for obtaining prior studies when seeing a new physician. The system will also offer an avenue for obtaining expert consultation from a third party in real-time, assisting difficult diagnostic evaluations and improving patient care in underserved areas that lack access to breast imaging expertise.
Proponents believe the prototype will also solve problems associated with the current system of mammography retrieval and storage.
"Digital images are very large files that take up a lot of computer space, so storing and transferring them is just one major challenge of this project," Schnall said.
To meet these challenges, the researchers have enlisted Next Generation Internet technology, a superfast network specially equipped to transfer large data files, execute real-time queries, and access information securely. The University of Toronto is responsible for this area of the project.
"This is particularly challenging because these images are much larger than most digital x-rays," said Martin J. Yaffe, Ph.D., a professor of medical physics at the University of Toronto.
Digital mammograms typically consume 160 Mb of storage per study per patient. High-speed Internet connections can transfer 70 Mb images in one second, although speeds of 100 Mb per second and beyond are imminent.
The system, funded by grants from the National Library of Medicine and the Department of Health and Human Services, also makes use of distributed processing so physicians anywhere will have access to computer-aided diagnosis (CAD) tools.
"Anyone who has a CAD algorithm that's effective or a powerful computer for performing these calculations will be able to use that algorithm or computer from remote locations," Yaffe said.
Another major NDMA focus involves patient confidentiality. Women will be asked to give electronic consent, such as a PIN number or password, authorizing the transfer of their images. Likewise, workstations may be equipped with access controls (thumbprint identification or smart cards) that allow only authorized radiologists to view the images.
The system allows for total auditability - in essence an electronic paper trail that shows exactly where the images go and who views them, Schnall said.
Can Contrast-Enhanced Mammography be a Viable Screening Alternative to Breast MRI?
June 17th 2025While the addition of contrast-enhanced mammography (CEM) to digital breast tomosynthesis (DBT) led to over a 13 percent increase in false positive cases, researchers also noted over double the cancer yield per 1,000 women in comparison to DBT alone.
Mammography AI Platform for Five-Year Breast Cancer Risk Prediction Gets FDA De Novo Authorization
June 2nd 2025Through AI recognition of subtle patterns in breast tissue on screening mammograms, the Clairity Breast software reportedly provides validated risk scoring for predicting one’s five-year risk of breast cancer.
Emerging AI Mammography Model May Enhance Clarity for Initial BI-RADS 3 and 4 Classifications
May 21st 2025In a study involving over 12,000 Asian women, researchers found that an artificial intelligence (AI) model converted over 83 percent of false positives in patients with initial BI-RADS 3 and 4 assessments into benign BI-RADS categories.