Future of Breast Cancer Screening and Artificial Intelligence


The goal of screening mammography is to detect early-stage breast cancers in asymptomatic women (screening guidelines). A recent 15-year study concluded that women who participated in a mammographic screening program had a 41% reduction in their risk of dying from breast cancer (ref. 1).

Despite the progress, there is one issue that needs urgent attention. A report from the National Cancer Institute (NCI) concluded that screening mammograms fail to detect 20% of breast cancers that are present in the breast at the time of the mammogram (ref. 2). When the mammogram fails to detect a breast cancer it is referred to as a false negative. A new technology, referred to as artificial Intelligence, has the potential to markedly reduce the rates of false negative mammograms (ref. 3).


What is Artificial Intelligence?

Artificial Intelligence is a new technology that allows computers to perform tasks that are commonly associated with human intelligence such as the ability to reason or the ability to learn from past experiences (ref. 4). Learning from past experiences is referred to as machine learning (ref. 5).

In standard mammographic screening, the mammogram is read by a single radiologist. With AI assisted mammography, a report is issued from both the radiologist and by the AI-based imaging system. This double reading facilitates the process of machine learning. For example, assume the AI based system fails to identify a small cancer, but the cancer is detected by the radiologist. In this situation, the AI-assisted algorithm can be modified to avoid making a similar mistake in the future.

Over time, machine learning will lead to continued improvements in the accuracy of detecting small breasts that are not visualized on standard mammographic imaging (ref. 6-7).


Cause of False Negative Mammogram

The primary reason that so many early-stage breast cancers are missed on mammographic screening is directly related to the issue of breast density. A recent study found that 98% of the breast cancer that were not detected on the screening mammogram occurred in women with dense breasts (ref. 8).

The explanation for why breast density makes it so challenging to detect early-stage breast cancers is that density appears white on the mammogram and early-stage breast cancers are also white. Detecting a small cancer in a dense breast has been compared to the challenge of finding a snowman in a snowstorm.


Benefits of AI Assisted Mammography

Early studies of AI assisted mammography evaluated the previous year’s negative mammogram using AI assisted mammography. In many cases, AI was able to detect breast cancers 1-2 years earlier than they could be detected using standard mammographic imaging (ref. 9-10). A more recent study determined that AI assisted mammography could identify breast cancers in 79% of cases in which the previous year’s mammogram was reported to be normal (ref. 11).


False-Positive Biopsies

A second limitation of standard mammographic screening is the issue of unnecessary biopsies. When a radiologist identifies an area of concern on the screening mammogram, additional views are typically recommended. If the area of concerns persists, a biopsy is recommended. If the biopsy proves to be benign, it is referred to as a false positive biopsy (ref 12.).

A recent study concluded that half of all women who had regular mammographic screening for a period of 10 years had at least one false positive biopsy (ref. 13). Recent studies have determined that AI assisted mammography can reduce false positive biopsies rates by approximately 70% (ref. 14-15). There is also evidence that AI assisted ultrasound in women with dense breasts can further lower the rates of false positive breast biopsies (ref. 16).


Other Benefits of AI

Reduce Callbacks: Callbacks refers to the situation in which a woman receives a phone call a few days following her mammogram informing her that see must return to the imaging center for additional views. This phone call usually results in a major spike in anxiety levels (ref. 17-18). Recent studies conclude that AI assisted mammography reduces the rates of callbacks. As a result, fewer women go through the anxiety of returning to the imaging center for additional views (ref. 19-21).

Improves Efficiency: AI can also reduce the time it takes to complete the imaging process (ref. 22-23). One example of how this can be accomplished occurs when the mammographer detects an area of concern on the screening mammogram and recommends additional imaging. In these cases the patient waits in the imaging center to have her additional views performed. She then waits for the mammographer to issue a report.

With AI, the computer provides the technician with an initial report within minutes. If extra views are recommended, they can quickly be performed. Once the extra views have been performed the images are sent to the mammographer for review. In most cases, the additional imaging will be negative, and the patient can be discharged.

Reduces Costs: One example of how AI can reduce the costs of breast care is to reduce the rates of false positive biopsies. It is estimated that the cost of covering false positive biopsies in the USA is in the range of 2.2 billion dollars (ref. 24). AI can reduce rates of false positive biopsies rates by more than 50%.


The Future

The future looks bright for AI assisted mammography. We are convinced that there is conclusive evidence that AI can outperform standard mammography both in terms of early detection and in lowering the costs of care. We believe that there is an urgent need to make this new technology available to all women in the USA.

To improve rates of early detection, the issue of breast density must be addressed. Average risk women with dense breasts are advised to have a yearly screening ultrasound in addition to the AI assisted mammogram (ref. 25). Women with strong family histories of breast cancer are advised to have yearly screening MRI in addition to the AI assisted mammogram (ref. 26).

We also believe that women should be given the option to start yearly screening mammography in their 30’s (ref. 27). The primary reason for starting screening at an early age is to determine a woman’s density status. Women who have dense breasts are advised to continue yearly screening if they are in good health. In cases in which the breast is not dense, women can be given the option to delay future screening until they reach the age of 40.

Critics are likely to disagree with our conclusions. They will undoubtedly express concern about the costs of implementing our aggressive guidelines. They are also likely to conclude that more research is needed before any major alterations in screening guidelines are incorporated into standard practice.

We are convinced that when the lifetime costs of care are taken into consideration, the benefits of aggressive screening become more apparent. When asymptomatic women are found to have a breast cancer on screening mammography, they have a 98% probability of survival (ref. 29). The lifetime cost of treating early-stage breast cancer is in the range of $100,000 (Screening Mammography: costs & benefits).

When the diagnosis of breast cancer is delayed, long-term survival rates are markedly reduced, and the lifetime cost of care can easily exceed a million dollars (ref. 29). One recent study reported that the cost of immunotherapy treatments was in the range of 200,000 dollars per year. This million-dollar estimate focused on the costs of immunotherapy and chemotherapy. It did not consider the added cost of radiation therapy or surgery. Other studies have reported similar findings (ref. 30-33).

We conclude that AI assisted mammography will soon become a game changer in terms of reducing breast cancer mortality rates and reducing the long-term costs of breast cancer care.


Questions? Contact us


Ref. 1: Mammography screening reduces rates of advanced and fatal breast cancers: Results in 549,091 women

Ref. 2: Mammograms (from NCI)

Ref. 3: artificial intelligence

Ref. 4: What is AI? Learn about Artificial Intelligence

Ref. 5: How machine learning works

Ref. 6: Artificial intelligence (AI) to enhance breast cancer screening: protocol for population-based cohort study of cancer detection

Ref. 7: Breast Cancer Detection Accuracy of Mammography with the Concurrent Use of an Artificial Intelligence Tool

Ref.8: Mammographically occult breast cancers detected with AI-based diagnosis supporting software: clinical and histopathologic characteristics

Ref. 9: 6 Benefits of Artificial Intelligence (AI)

Ref. 10: RadNet touts AI offshoot’s early success, pinpointing cancer a year earlier than current practice

Ref. 11: Retrospective Review of Missed Cancer Detection and Its Mammography Findings with Artificial-Intelligence-Based, Computer-Aided Diagnosis

Ref. 12: Limitations of Mammogram

Ref. 13: Half of all women experience false positive mammograms after 10 years of annual screening

Ref. 14: Reduction of False-Positive Markings on Mammograms: A Retrospective Comparison Study Using an Artificial Intelligence-Based CAD

Ref. 15: Can an Artificial Intelligence Decision Aid Decrease False Positive Breast Biopsies?

Ref. 16: Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams

Ref. 17: Psychosocial consequences of false-positive results in screening mammography

Ref. 18: False-Positive Mammograms Can Trigger Long-Term Distress

Ref. 19: Getting Called Back After a Mammogram

Ref. 20: What I Wish I’d Known About Mammogram Callbacks

Ref. 21: The Costs of Callbacks: What it Means for Your Radiology Practice and Your Patients

Ref. 22: Artificial Intelligence for Reducing Workload in Breast Cancer Screening with Digital Breast Tomosynthesis

Ref. 23: AI Tool Improves Breast Cancer Detection on Mammography

Ref. 24: Can AI Help Make Screening Mammography “Lean”?

Ref. 25: Annual Cost of False-Positive Breast Biopsies Exceeds $2 Billion According to Recent Study

Ref. 26: The Role of Ultrasound in Screening Dense Breasts—A Review of the Literature and Practical Solutions for Implementation

Ref. 27: Breast MRI (Magnetic Resonance Imaging)

Ref. 28: Some Women Should Start Mammograms at 30

Ref. 29: Free Breast Cancer Screening & Prevention

Ref. 30: The Value and Cost of Immunotherapy Cancer Treatments

Ref. 31: Study Shows US Cancer Drug Costs Increasing Despite Competition

Ref. 32: How Much Does Breast Cancer Treatment Cost?

Ref. 33: The High Cost of Cancer Drugs and What We Can Do About It

Ref. 34: Comparison of Treatment Costs for Breast Cancer, by Tumor Stage and Type of Service

For more information see the next section or contact us.


Your donation supports our mission to provide breast cancer education to EVERY woman.