Radiologists work with AI to better detect breast cancer

By James Gamble via SWNS

Radiologists assisted by AI technology are better at detecting breast cancer than two radiologists working together, suggests a new study.

The finding paves the way for accurate diagnoses in the face of fewer radiologists.

Swedish researchers pitted teams of radiologists working with artificial intelligence (AI) against human radiographers screening mammograms from more than 55,000 women.

The study concluded that a team of two radiologists working alongside AI unsurprisingly detected the most cancer cases, whilst one radiographer working with AI also outperformed two radiologists.

And, interestingly, AI alone diagnosed only a few less cases than two radiographers.

The researchers, from the Karolinska Institutet, in the Swedish capital of Stockholm, said their study demonstrated that the technology was ready to be deployed in breast cancer screening programs to assist with current shortages of radiographers across the world.

The study, published in the journal Lancet Digital Health, was conducted at Capio St Göran’s Hospital in Stockholm between April 2021 and June 2022, where more than 55,500 women between the ages of 40 and 74 were screened for mammogram exams.

The screening method uses a mammographer to take several X-rays of each breast to check for signs of breast cancer that are too small to see or feel.

Under the NHS Breast Screening Programme (NHSBSP), women usually receive their first invitation for mammographic screening between the ages of 50 and 53.

They are then invited back for continual tests every three years up to the age of 70.

However, the screening does not detect every breast cancer, and false-positive interpretations of tests can lead to women undergoing unnecessary imaging and even biopsies.

One method that can improve both the sensitivity and specificity of screening is for each mammogram to be read by two separate readers.

But this type of strategy is labour-intensive and increasingly difficult to achieve with shortages in readers all across the world.

The researchers discovered that the traditional approach of using two radiologists detected a total of 250 cancers.

As expected, the researchers found that adding AI to the team of two radiologists detected the most cases of cancer, at 269.

However, one radiologist working with AI detected 261 cancer cases in the same cohort and AI alone detected 246 - just four less than two radiologists.

Study author Dr. Karin Dembrower, an affiliated researcher at the Department of Oncology-Pathology at the Karolinska Institutet, explained: "AI and humans perceive images slightly differently, which creates a synergy that improves our chances of detecting cancer.

"With this study, we wanted to examine how well two radiologists performed compared with one radiologist and AI, and AI alone."

The study's principal investigator, radiologist Dr. Fredrik Strand, added: "Compared with the current two-radiologist standard, assessment by one radiologist and AI resulted in a four per cent increase in breast cancer detection and halved the radiologists’ image reading time."

The researchers also found that, compared with two radiologists, one radiologist plus AI and AI alone led, respectively, to a six and a 55 per cent reduction in false positives; meaning the recall rate for healthy women, a procedural error that causes unnecessary suffering and cost.

Dr. Strand added the study was clear evidence that AI technology was ready to be integrated into breast cancer screening programs.

"Our study shows that AI is ready for controlled implementation in screening mammography," Dr. Strand said.

"However, you must choose an AI system that has been properly tested on images from the same type of mammography equipment and ensure continuous monitoring after clinical implementation.

"In the longer term, AI has the potential to take over the majority of screening mammography assessments."