Single-view DBT and AI setup allows for effective screening mammography

A study published in Radiology determined that a single digital breast tomosynthesis (DBT) image in combination with artificial intelligence (AI) improves radiologists' productivity.

A retrospective study of 190 women with bilateral mediolateral oblique breast images that were acquired with a wide-angle DBT system was obtained.  The examination -based reader- average AUC was higher when interpreting results with AI support than when reading unaided.  The average sensitivity increased with AI support, whereas no differences in the specificity and reading time were detected.

The authors concluded that using a single-view DBT in conjunction with an AI setup could allow for more effective screening, especially in cancers detected, than using DBT alone.  

Artificial Intelligence (AI) Outperforms Radiologists in Mammography

The aim of screening mammography is to detect breast cancer in women as early as possible before signs of the disease become clinically obvious.  In a study published in Nature McKinney et al found that AI bested radiologists in detecting breast cancer in screening mammograms. 

Mammograms of 25,856 women in the United Kingdom and 3,097 women in the United States were used to train the AI system. AI was then used to identify the presence of breast cancer in mammograms of women who were known to have had either biopsy-proven breast cancer or normal follow-up imaging results at least 365 days later. The study included mammograms; by conventional digital (2D) mammography and tomosynthesis (also known as 3D mammography). 

The authors report that the AI system outperformed diagnoses made by the radiologists who initially interpreted the mammograms, and the decisions of 6 expert radiologists who interpreted 500 randomly selected cases.

The study reports an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. The authors also performed a simulation in which the AI system participated in the double-reading process that is common in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. 

The authors suggest that further assessment of the AI system with clinical trials may lead to improvements in the accuracy and efficiency of breast cancer screening by limiting the high rates of false positives and negatives which are known to take place in the interpretation of mammograms.

Artificial Intelligence is Useful in the Interpretation of Screening Mammograms

A study published in Radiology found that breast radiologists had a slight higher diagnostic performance when using artificial intelligence (AI) with no additional time required.

Screening digital mammograms from 240 women (median age, 62 years; range, 39–89 years) performed between 2013 and 2017 were analyzed in this study. The mammograms were interpreted with and without AI support.

The researchers found that the cancer detection improved for all breast densities, and was independent of lesion type, vendor image quality, when radiologists used AI and interestingly did not lengthen interpretation time. The radiologists’ detection slightly improved when using AI support, with the average area under the receiver operating characteristic curve (AUC) increasing form 0,87 to 0.89.  Sensitivity increased with AI support 86% vs. 83%, whereas specificity improved slightly 79% vs. 77%. Reading time per case was for all practical purposes identical  (unaided, 146 seconds; supported by AI, 149 seconds).

The researchers concluded that AI assisted interpreting radiologists and improved their cancer detection at mammography when using AI without adding to the interpetation time.

American Women Prefer Annual Mammograms

The US Preventive ServicesTask Force (USPSTF) reaffirmed its recommendations to screen women ages 50-74 for breast cancer every two years stating that the harms of annual screening outweighed the benefits.  It also says the decision on frequency of screening should be individualized for women ages 40-49 based on risk.  The USPSTF found insufficient evidence to recommend for or against screening for women 75 or older.

Several professional societies like the American College of Radiology and Society of Breast Imaging advocate annual screening mammography starting at age 40.

A survey of 731 women indicated that 71% of the women who were 59 years old on average said they’d prefer a screening mammogram every year. Only 17% of participants felt having biennial screening would cause less anxiety. Of the patients who reported a prior abnormal mammogram, 13% believe biennial screening would cause less anxiety

The study was presented at the 103th annual meeting of the Radiological Society of North America.

How effective is screening mammography?

A study by Welch et al published in New Engl J Med added to the growing evidence that for every woman who was helped by screening mammography many have been harmed.

The authors used data from the SEER program from 1975 through 2012. They calculated the size-specific cancer case fatality rate in women 40 year old and older for two time periods: a baseline period before the implementation of widespread screening mammography (1975 through 1979) and a period encompassing 10 years (2000 through 2002).

Screening did result in more cancers being detected, with invasive tumors measuring <2 cm or in situ carcinomas increased from 36% to 68%; and the detected tumors that were large, which were invasive cancers and measuring ≥2 cm decreased from 64% to 32%.  Surprisingly though the data suggest that only about 30 of the 162 additional small tumors per 100,000 women that screening mammograms found would ever have progressed to a dangerous stage. That means that 132, or 81 percent, of the 162 extra tumors detected represented overdiagnosis, that resulted to treatment of tumors that were never destined to harm.

Most importantly, the incidence of metastatic cancer, which is the type that causes most deaths, was flat. 

In conclusion the findings from this study indicate that screening mammography finds many small cancers the dogma that all will grow, metastasize resulting in fatality is questionable. The authors also suggest that although screening may decrease cancer mortality as reflected by the declining incidence of larger tumors, they believe that the two thirds reduction in breast cancer mortality is due to recent advances in treatment. 

N Engl J Med 2016; 375:1438-1447

Low-Dose Digital Mammography May Be Accurate

Research by Chen et al suggests that low-dose techniques for digital mammography may be feasible, as results are not substantially affected by variations in radiation dose. Their study was published in Radiology.

The researchers analyzed retrospectively a cohort of women from the American College of Radiology Imaging Network Pennsylvania 4006 trial. All patients underwent breast screening with a combination of dose protocols, including standard full-field digital mammography, low-dose digital mammography, and digital breast tomosynthesis. A total of 5832 images from 486 women were analyzed with fully automated software for quantitative estimation of density.

Clinical Breast Imaging Reporting and Data System (BI-RADS) density assessment results were also available from the trial reports. The influence of image acquisition radiation dose on quantitative breast density estimation was investigated with analysis of variance and linear regression.

Radiation dose of image acquisition did not significantly affect quantitative density measurements, with percent density demonstrating a high overall correlation between protocols. However, differences in breast percent density were observed within high BI-RADS density categories, although they were significantly correlated across the different acquisition dose levels.

The authors concluded that reproducibility of automated breast density measurements with digital mammography are not affected by variations in radiation dose; thus, the use of low-dose techniques for the purpose of density estimation may be attainable.

Tailoring Screening Mammography

Research by Trentham-Dietz et al published in the Annals of Internal Medicine recommends that frequency of screening for breast cancer should be based on well-recognized risk factors.

The researchers who were breast-cancer epidemiologists and cancer modelers combined data-collection and conducted simulation modeling using national data for incidence, breast density, and screening performance.

It is an accepted fact that screening benefits and overdiagnosis increase with breast density and relative risk (RR) while false-positive mammograms and benign results on biopsy decrease with increasing risk.

Among women with fatty breasts and an RR of 1.0 or 1.3, breast cancer deaths averted were similar for triennial versus biennial screening for both age groups (50 to 74 years, median of 3.4 to 5.1 vs. 4.1 to 6.5 deaths averted; 65 to 74 years, median of 1.5 to 2.1 vs. 1.8 to 2.6 deaths averted).

Breast cancer deaths averted increased with annual versus biennial screening for women aged 50 to 74 years at all levels of breast density and an RR of 4.0, and those aged 65 to 74 years with heterogeneously or extremely dense breasts and an RR of 4.0. However, harms were almost 2-fold higher.

Triennial screening for the average-risk subgroup and annual screening for the highest-risk subgroup cost less than $100 000 per quality-adjusted life year (QALY) gained which is a value for money of medical interventions.

The authors concluded that average-risk women older than 50 without dense breasts should undergo triennial screening while higher-risk women with very dense breasts should receive annual mammograms.  Such frequency and tailoring of screening mammography will maintain a similar or better balance of benefits and harms than average-risk women receiving annual or biennial screening.

Computer-Aided Detection did not improve Digital Screening Mammography's Diagnostic Accuracy

Lehman et al in a paper published by JAMAInternal Medicine report on their findings that suggest that computer-assisted detection (CAD) used in most mammograms added no benefit to breast cancer screening while it substantially increased costs.

The authors compared the accuracy of digital screening mammography interpreted with (n = 495 818) versus without (n = 129 807) CAD from 2003 through 2009 in 323 973 women.  271 radiologists in 66 facilities interpreted the mammographic studies.  They found 3159 breast cancers within 1 year of the screening.

Screening performance was not improved with CAD on any metric assessed. Mammography sensitivity was 85.3% with and 87.3% without CAD. Specificity was 91.6% with and 91.4% without CAD. There was no difference in cancer detection rate (4.1 in 1000 women screened with and without CAD). Computer-aided detection did not improve intra-radiologist performance. Sensitivity was significantly lower for mammograms interpreted with versus without CAD in the subset of radiologists who interpreted both with and without CAD.

The authors concluded CAD does not improve diagnostic accuracy of mammography. These results suggest that while insurers pay an additional $400 million a year for CAD, its addition to standard mammography had no beneficial impact to women.

American Cancer Society Updated Guidelines for Breast Cancer Screening

Breast cancer is a leading cause of premature mortality among US women.   Oeffinger at al report in JAMA the American Cancer Society (ACS) 2015 update regarding the frequency of screening mammography in women at average risk. 

The ACS recommends that women with an average risk of breast cancer should undergo annual screening mammography starting at age 45 years (strong recommendation).

Women 55 years and older should transition to biennial screening (strong recommendation).

Women should continue screening mammography as long as their overall health is good and they have a life expectancy of 10 years or longer (qualified recommendation).

Women should have the opportunity to have annual screening between at the ages of 40-45 received a qualified recommendation.

The ACS does not recommend clinical breast examination for breast cancer screening among average-risk women at any age (qualified recommendation).

These updated ACS guidelines provide evidence-based recommendations for breast cancer screening for women at average risk of breast cancer.   

Screening mammography has not saved lives

Harding, et al in their article published in JAMA Intern Med report on associations between screening mammography and the incidence and mortality from breast cancer, as well as tumor size.

A study of 16 million women 40 years or older who resided in 547 US counties reporting to the Surveillance, Epidemiology, and End Results cancer registries during the year 2000. Of these women, 53 207 were diagnosed with breast cancer that year and were followed up for the next 10 years.

Across the US counties, there was a positive correlation between the extent of screening and breast cancer incidence but not with breast cancer mortality. An absolute increase of 10 percentage points in the extent of screening was accompanied by 16% more breast cancer diagnoses but no significant change in breast cancer deaths. In an analysis stratified by tumor size, they found that more screening was strongly associated with an increased incidence of small breast cancers (≤2 cm) but not with a decreased incidence of larger breast cancers (>2 cm). An increase of 10 percentage points in screening was associated with a 25% increase in the incidence of small breast cancers and a 7% increase in the incidence of larger breast cancers.

They found that screening mammography results in the diagnosis of additional small cancers but no concomitant decline in the detection of larger cancers, which might explain the absence of any significant difference in the overall rate of death from the disease. Together, these findings suggest widespread overdiagnosis.