AI-Can Reduce Workload in Breast Cancer Screening

A study published in Radiology determined that an artificial intelligence (AI) algorithm could reduce the digital breast tomosynthesis (DBT) and mammography (DM) workload of radiologists without impacting diagnostic accuracy.

A total of 15,987 DM and DBT examinations (which included 98 screening-detected and 15 interval cancers from the 15,987 women were evaluated.  In comparison with the double reading of the DBT images, AI with DBT would result in 72.5% less workload, noninferior sensitivity, and a 16.7% lower recall rate.  Similar results were obtained for AI and DM. 

AI could obviate over 70% of radiologists' double reading thus enable DBT adoption in breast cancer screening programs.

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.

Breast MRI is the study of choice for women at high risk for breast cancer.

According to a study published in Radiology Lo et al reviewed the outcomes of 3,934 screening breast studies (MRI and mammograms) performed on 1,249 high-risk women. A total of 45 cancers (33 invasive and 12 ductal carcinomas in situ) were diagnosed, 43 were seen with MR imaging and 14 with both mammography and MR imaging.   The cancer detection rate for MR imaging was 21.8 cancers per 1000 examinations and that for mammography was 7.2 cancers per 1000 examinations. Sensitivity and specificity of MR imaging were 96% and 78% respectively, and those of mammography were 31% and 89%, respectively (P < .001).  The researchers reported that all cancers found at screening mammography were also detected on breast MRI.  

The researchers concluded that annual screening mammography adds no value to women that are at high risk for breast cancer especially since they are screened each year with breast MRI.

Preoperative Breast MRI detects additional cancers

A paper by Bae et al published in Radiology indicates that preoperative MRI in women whose breast cancer was detected by ultrasound found additional cancers.

The study was a retrospective review of 374 women, median age, 48 years, with breast cancer detected at screening ultrasound.

Of 374 women, 21 or 5.6% patients were diagnosed with additional cancer.  In premenopausal women with invasive breast cancer and in those with index invasive lobular histologic type had higher incidence of additional cancer detected at MR imaging.  Premenopausal status also put the women at risk.

The authors concluded that preoperative MRI detected additional sites of cancer in women with breast cancer detected at screening ultrasound.

Breast density assessment varies among radiologists

Sprangue et al published in Annals of Internal Medicine the findings of their study that suggests that radiologists often do not agree on what qualifies as dense breast.

The investigators looked at 216,783 mammograms from 145,123 women aged 40 to 89 years that were interpreted by 83 radiologists in 30 radiology facilities in 4 States.

Overall, 36.9% of mammograms were rated as showing dense breasts. Across radiologists, this percentage ranged from 6.3% to 84.5% (median, 38.7%). Examination of patient subgroups revealed that variation in density assessment across radiologists was pervasive in all but the most extreme patient age and BMI combinations. Among women who had consecutive mammograms interpreted by different radiologists, 17.2% (5909 of 34 271) of them suggested different density rating on the two tests.

The authors concluded because there is wide variation in density assessment across radiologists it is a fact should be carefully considered by providers and policymakers when considering supplemental screening strategies.

Increase in the cost of breast cancer screening results in no benefit for older women

Killelea et al in their paper published by the JNat Cancer Inst report that cost for breast cancer screening have increased dramatically since the introduction of newer imaging technologies such as digital mammography, computer aided detection, MRI and image guided biopsies, but the outcomes remain undefined, particularly among older women.

The authors used the Surveillance, Epidemiology, and End Results-Medicare linked database, and constructed two cohorts of women without a history of breast cancer, which they followed for 2 years. They compared the use and cost of screening mammography including digital mammography, CAD, and adjunct procedures such as CAD, breast ultrasound, MRI, and biopsies between the period of 2001 and 2002 and the period of 2008 and 2009.

There were 137150 women (mean age = 76.0 years) in the early cohort (2001-2002) and 133097 women (mean age = 77.3 years) in the later cohort (2008-2009). The use of digital image acquisition for screening mammography increased from 2.0% in 2001 and 2002 to 29.8% in 2008 and 2009 (P < .001). CAD use increased from 3.2% to 33.1% (P < .001). Average screening-related cost per capita increased from $76 to $112 (P < .001), with annual national fee-for-service Medicare spending increasing from $666 million to $962 million. There was no statistically significant change in detection rates of early-stage tumors (2.45 vs 2.57 per 1000 person-years; P = .41).

The authors concluded that although breast cancer screening-related costs increased substantially from 2001 through 2009 among Medicare beneficiaries, a clinically significant change in stage at diagnosis was not observed.