This website is intended for healthcare professionals only.
Take a look at a selection of our recent media coverage:
4th July 2022
The combination of an artificial intelligence (AI) system and a radiologist provides better screening accuracy for breast cancer as demonstrated by a higher sensitivity and specificity according to the findings of a retrospective analysis by an international team of radiologists.
The use of screening mammography is designed to identify breast cancer at earlier stages as treatment will be more successful. Moreover, in recent years there has been increased interest in the use of AI systems and a recent study found that the use of an AI system outperformed all of the human readers, with a greater area under the receiver operating characteristic curve margin of 11.5% for screening breast cancer mammograms. Nevertheless, a 2021 systematic review which considered the use of AI for image analysis in breast cancer screening programs concluded that the current evidence for AI does not yet allow judgement of its accuracy in breast cancer screening programmes, and it is unclear where on the clinical pathway AI might be of most benefit. Other work that considered the role of AI for breast cancer screening suggested that an AI system can correctly identify a proportion of a screening population as cancer-free and also reduce false positives and therefore has the potential to improve mammography screening efficiency.
But what if an AI and radiologists worked together, so that the AI could initially triage scans and identify normal cases but those with suspected cancer and where there was diagnostic uncertainty, were referred to the radiologist? This was the question addressed in the retrospective analysis by the research team. The system was designed so that the AI system would flag potential cancerous scans and where it was unsure about the diagnosis, for a second read by a radiologist. The team initially trained the AI system using an internal dataset and then used an external data set and compared the interpretation with that of a radiologist. The performance of both the AI and radiologists was assessed in terms of sensitivity and specificity and the test sets contained a mix of both normal and cancerous scans.
AI and radiologists combined performance
For the external data set the radiologist had a higher sensitivity (87.2% vs 84.6%, radiologist vs AI system) and specificity (93.4% vs 91.3%) and in both cases this difference was statistically significant (p < 0.001 for both).
However, when the AI and radiologists worked together, the radiologist’s sensitivity was 89.7% and the specificity 93.8%. In other words, the combination improved both sensitivity and specificity. The authors calculated that this corresponded to a triaging performance, i.e., the fraction of scans which could be automated) of 60.7%.
Based on these findings, the authors concluded that their system leverages the strength of both the radiologist and the AI system and had the potential to improve upon the screening accuracy of radiologists.
Leibig C et al. Combining the strengths of radiologists and AI for breast cancer screening: a retrospective analysis Lancet Digit Health 2022
7th April 2022
Women having breast tomosynthesis screening over a 10-year period experience a lower cumulative probability of receiving at least one false-positive result compared to conventional mammography. This was according to the results of a study by researchers from the Division of Biostatistics, Department of Public Health Sciences, University of California Davis School of Medicine, California, US.
Screening for breast cancer, even among asymptomatic women, enables the early detection of cancer which is easier to treat than later-stage disease and has a higher probability of survival. Breast cancer screening is undertaken with mammography and while the technique helps to identify cancer, there is always the risk of a false positive result. In fact, one 10-year study found that one third of women screened had an abnormal test result that required additional evaluation, even though no breast cancer was present. Other data suggests that that false positive rate is 12% and though the absence of a cancer diagnosis brings relief to women, false-positive findings on screening mammography causes long-term psychosocial harm.
Digital breast tomosynthesis, which approximates a 3D mammogram of the breast, has been found to improve on the cancer detection rate and reduce recall, compared to the more conventional 2-D mammogram. However, effective screening requires women to have many examinations over a period of years and for the present study, the US team wanted to estimate the probability of women receiving at least 1 false-positive result after 10 years of screening with breast tomosynthesis compared to traditional mammography. They looked at data held within mammography registers covering the period 2005 to 2018 and collected data on self-reported information and the time since the last mammogram from questionnaires. The primary outcomes of interest were false-positive recall, false-positive short-interval follow-up and false-positive biopsy recommendations. The researchers also compared the two approaches based on whether the screening was annual or biennial.
Breast tomosynthesis and false positives
A total of 903,495 women with a mean age at the time of screening of 57.6 years, had 444,704 digital breast tomosynthesis and 2,524,351 mammography examinations. During the period of follow-up, women underwent a mean of 3.3 examinations.
Overall, 7.6% of tomosynthesis and 9% of mammograms resulted in a false-positive recall; 1.8% of tomosynthesis and 2.1% of mammograms led to a false-positive short-interval follow-up recommendation and finally, 1.1% of tomosynthesis and 1.2% of mammograms resulted in a false-positive biopsy recommendation.
The authors calculated that for annual screening the 10-year cumulative probability of at least 1 false-positive with tomosynthesis was 49.6% compared to 56.3% with mammography (difference = -6.7%, 95% CI -7.4 to -6.1) for recall. The cumulative probability of a false-positive for biennial screening was also lower with tomosynthesis compared to mammography (35.7% vs 38.1%).
The researchers concluded that breast tomosynthesis screening led to modest reductions of 2.4% for biennial and 6.7% for annual screening but added how in practise, these percentages equated to thousands of individuals in absolute terms.
Thao-Quyen HH et al. Cumulative Probability of False-Positive Results After 10 Years of Screening With Digital Breast Tomosynthesis vs Digital Mammography JAMA Netw Open 2022