Exploring emerging breast cancer screening tools, technology
New breast cancer screening tools, ranging from 3D mammography to AI-assisted screening analysis play a critical role in the evolving breast cancer screening landscape.
As breast cancer awareness month continues, understanding the impact of breast cancer nationwide and the emerging tools for detecting and treating breast cancer is critical.
According to the National Breast Cancer Foundation, one in eight women in the United States are diagnosed with breast cancer in their lifetime, accounting for roughly 310,720 diagnoses of invasive breast cancer annually among women and 2,800 cases annually among men.
The survival outcomes for breast cancer have increased dramatically. The National Breast Cancer Foundation estimates that the five-year relative survival rate for early-stage, localized breast cancer is 99%. As science and technology have advanced, early detection and treatment of breast cancer have become more common, contributing to better overall health outcomes.
Emerging technologies in breast cancer screening are enhancing early detection and improving outcomes. Notable advancements include 3D mammography, magnetic resonance imaging, ultrasound innovations, molecular breast imaging, positron emission mammography, artificial intelligence, liquid biopsies, wearable technology, thermal imaging, and genetic screenings.
3D mammography
Traditional mammography is a type of X-ray imaging of the breast that is often the standard for breast cancer screening. This process requires compressing a patient's breast tissue between two firm surfaces and using an X-ray to capture 2D images of the breast.
However, for some patients, traditional mammography might provide inconclusive results.
Digital breast tomosynthesis, also called 3D mammography, provides a more comprehensive image of the breast tissue. Again, the image is taken as the patient's breast tissue is compressed between two surfaces. Unlike 2D mammography, 3D mammography generates a digital tomographic image that can be viewed or manipulated on the computer so that radiologists can detect discrepancies in breast tissue.
The Mayo Clinic recommends 3D mammograms for all women who are at the appropriate age for breast cancer screening regardless of their risk level.
In an interview with NPR, Liane Philpotts, M.D., a radiology professor at the Yale School of Medicine, emphasized that 3D mammography produces fewer false positives than traditional mammography. She also explained that incorporating this screening tool might be linked to increased breast cancer detection and a lower rate of advanced cancers.
However, the National Cancer Institute notes that it is unclear whether 3D mammography is better at detecting early-stage breast cancer than 2D mammography. According to the NPR interview with Philpotts and an editorial in Radiology by two Korea University Guro Hospital radiology professors, a definitive answer will not be available until 2030, when a large-scale randomized control study concludes.
The benefits of AI in breast cancer screening include enhanced accuracy, efficiency, speed, consistency, workflow support, data integration and cost savings.
For PET scans, a radioactive tracer, most commonly a radioactive sugar, tags cancer cells. A scanner detects the radioactive tracer and generates 3D images. According to the American Cancer Society, fluoroestradiolF-18has recently been used as a new radioactive tracer for estrogen receptor-positive breast cancers.
PEM scans use the same radioactive tracer as PET scans that tag cancer cells. Once a patient is injected, their breasts are lightly pressed between two plates, like in mammography, while the images are taken.
The American Cancer Society notes, "PEM may be better able to detect small clusters of cancer cells within the breast than standard mammography. This is because it takes into account how active the breast cells are, as opposed to just their structure. PEM is being studied mainly in women with breast cancer to see if it can help determine the extent of the cancer. PEM exposes the whole body to radiation, so it isn't likely to be used every year for breast cancer screening."
Contrast-enhanced mammography
Contrast-enhanced mammography (CEM) is another newer type of breast cancer screening. In this procedure, a patient is injected with an iodine-containing contrast dye and then undergoes two sets of mammograms with varying energy levels.
Using contrast dye can highlight abnormal areas that might not be immediately evident in traditional mammography. Recent investigations into CEM have attempted to compare it with breast MRIs for screening women with dense breasts who may be unable to get an MRI.
If studies find that the two are comparable, CEM might be favored over MRIs because CEMs are less expensive and faster than MRIs.
Molecular breast imaging
Molecular breast imaging (MBI), also called scintimammography or breast-specific gamma imaging, is another breast cancer screening technology that uses a gamma camera to detect breast cancer. For MBI, a patient is injected with a radioactive tracer, technetium-99m sestamibi, which travels to the breast tissue. Cancerous cells that grow faster than non-cancerous cells take up the tracer faster, which can be detected by the gamma camera.
MBI can be a beneficial screening option for those with dense breasts or an intermediate breast cancer risk. Although it does not replace mammography, MBI can provide additional data for breast cancer screenings.
Breast MRI
A breast MRI is often used once breast cancer has been diagnosed to identify the extent of cancer or investigate findings from a previous screening; however, a breast MRI can also be an effective screening tool for those with elevated breast cancer risks due to strong family history and genetic risks.
AI-assisted breast cancer screening
Beyond the actual imaging technology, researchers have been examining ways to incorporate AI and machine learning into breast cancer imaging analysis. AI has already been explored as a critical tool in radiology workflows that can help detect certain imaging abnormalities and streamline workflows.
Washington University Medicine notes that using AI to supplement radiological evaluations of mammograms can help minimize the risk of false positives while still identifying cancerous cases.
In a 2024 article analyzing the role of AI in breast cancer screening, the Breast Cancer Research Foundation highlighted models that incorporate AI. For example, Constance D. Lehman, M.D., Ph.D., and Regina Barzilay, Ph.D., developed and tested Mirai, a mammography-based deep learning model trained on large and diverse patient datasets. Research shows that the model can provide consistent and individualized improvements in breast cancer risk prediction.
Ongoing studies evaluate how Mirai can predict cancer risk across patients with varying risk levels and ages.
Overall, AI can be implemented in breast cancer screening to identify cancer earlier, prevent unnecessary biopsies, predict cancer risk, and reduce the prevalence of false positives. The benefits of AI include enhanced accuracy, efficiency, speed, consistency, workflow support, data integration and cost savings.
"Adoption has been slow because we want to get this right for patients, and we want to make sure we can implement these tools to best serve them and not just for secondary gain [by companies that make AI systems]," said Amy K. Patel, M.D., breast radiologist and medical director of the Breast Care Center at Liberty Hospital.
Veronica Salib has covered news related to the pharmaceutical and life sciences industry since 2022.
Dig Deeper on Medical devices and imaging technology
