Omnia Health is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Mammography vigilance is important despite AI takeover

Article-Mammography vigilance is important despite AI takeover

More prospective studies during health screening are essential, with real numbers reported as accurately as possible.

Health screening needs to change according to advancements in technology such as in the use of artificial intelligence (AI) in process of mammography, but new methods should not affect vigilance, according to an article published in the Climacteric journal in April 2022.

Besides talking about the use of AI in mammography, the article titled ‘Changes to health screening — we need to remain vigilant’ comments on the limitations of studies to date and the characteristics of future studies that could provide the information needed to properly assess the impact of the introduction of AI into screening mammography.

The article argues that there are well-established criteria for the use of a new health screening programme described more than 50 years ago and these criteria are still appropriate. However, it should not be assumed that once a form of health screening is in place, it should be continued forever since there is always room for improvements, it adds.

Dr. Mahira Yunus, Interventional Breast Radiologist, at Fakeeh University Hospital in Dubai referring to the article says that advancements in the techniques of mammographic screening have already happened. “There is the shift from screen-film to digital mammography and the use of breast tomosynthesis as an alternative to two-view digital mammography for breast cancer screening. Another modification to screening mammography on the horizon is the incorporation of AI into the interpretation of mammographic images,” she explains.

According to the article, “Why is the introduction of AI into screening mammography being contemplated? Even the best performing screening mammography programme (with a low rate of interval cancers coupled with a low recall rate) will miss some cancers which subsequently present as interval cancers prior to the next scheduled screening round.”

The article also adds: “Early publications about the value of AI in the analysis of radiology images were optimistic and there were even predictions that AI would threaten the future of the specialty of radiology. It might sound like a simple exercise to establish whether the incorporation of AI into mammographic screening improves the performance of a screening programme. However, the reality is that, despite hundreds of publications on the subject in recent years, a systematic review by Freeman et al. has shown that the picture is still not clear.”

Explaining, Dr. Yunus adds that when incorporating AI with mammography, it is possible that AI will improve sensitivity and reduce the rate of interval cancers. “As we already know that even the best performing screening mammography programme will miss some cancers, which subsequently present as interval cancers,” she says.

Furthermore, screening programmes tend to use two independent readers and so are relatively expensive to run and the use of AI could help to reduce these costs, she adds.

According to Dr. Yunus, the article argues that although it might sound like a simple exercise to establish whether the incorporation of AI into mammographic screening improves the performance of a screening programme especially when the AI system was more likely to detect micro-calcifications that are associated with ductal carcinoma in situ, it has been argued that AI programme was detecting very slow-growing tumors (leading to overtreatment). 

The ideal approach to evaluation of AI in a mammographic screening programme would be a randomised controlled trial where the performance of a trained AI programme is evaluated prospectively in a screening setting, where the comparator was standard practice, according to the article.

The article also adds that more prospective studies need to be done while establishing the accuracy of the results need to be reported as real numbers (true positives, false positives, true negatives, and false negatives), which allows for the calculation of sensitivity and specificity in both the AI system and the comparator (and the difference between them).

However, the introduction of technology in the use of health screening should not affect vigilance. “All the above-listed reasoning does not rule out the need to be vigilant while using technology for health screening,” says Dr. Yunus.

“Healthcare providers should stay cautious when new technology is introduced into a screening programme. It should not be assumed that what seems like a simple modification, leaves the balance of benefits and harms unchanged,” she adds.

Asma Ali Zain is an independent journalist and a regular contributor at Omnia Health.

TAGS: Laboratory
Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Radiology Special | Omnia Health Magazine

Download the report

Learn more about the latest developments in the ever-changing world of medical imaging in this bite-sized radiology special.

Download your copy for insights into the importance of actively performing research, a detailed deep dive into compression sonography, the big wins within the industry, the promising work being carried out in diagnosis and prognosis prediction, and much more.