Could AI Revolutionize Breast Cancer Detection in the Future?
As science continues its search for ways to improve breast cancer detection, artificial intelligence (AI) is proving to be more effective in detecting breast cancer than humans. AI advancements have the potential to revolutionize breast cancer detection and evaluation of breast cancer risk. A recent study conducted in Sweden found that AI was able to detect 20% more breast cancer cases than experienced radiologists, while also reducing their workload by over 40%. This study suggests that AI could serve as a valuable tool for breast cancer detection, helping doctors and radiologists perform their jobs more effectively.
The study, published in The Lancet Oncology, involved 80,033 mammograms from women in Sweden, aged between 40 and 80. The participants were divided into two groups. One group had their mammograms read by AI before being analyzed by a radiologist, while the second group had their mammograms read by two radiologists without the use of AI. The results showed that the group whose mammograms were read by both AI and a radiologist detected 20% more breast cancer cases than the group whose mammograms were read by two radiologists alone.
The lead researcher of the study, Kristina Lång, explained that AI was used to identify screening examinations with a high risk of breast cancer, which underwent double reading by radiologists. The remaining examinations were classified as low-risk and were read by only one radiologist. The AI highlighted suspicious findings on the images, assisting the radiologists in their analysis.
The study also found that the use of AI reduced the workload for mammogram reading by 44%. This is significant, considering that radiologists in Sweden read an average of 50 screening examinations per hour. The researchers estimated that the introduction of AI reduced the time required to read the number of screenings in the AI-supported group by approximately five months.
Despite the increased detection rate, the use of AI did not lead to an increase in false positives. False positives can cause unnecessary anxiety and additional testing for patients. The study confirmed that AI helped increase cancer detection without affecting false positive rates.
In addition to detecting invasive breast cancers, the study also detected cases of carcinoma in situ (CIS). CIS refers to the presence of abnormal cells that may indicate the early stages of cancer but have not spread beyond their original location. It is essential for women to understand the significance of CIS and make informed decisions about treatment options.
The study highlighted the potential of AI to enhance breast cancer detection and reduce the workload for radiologists. With the ongoing shortage of breast radiologists in Sweden and elsewhere, the addition of AI could help alleviate the strain on healthcare professionals involved in reading mammogram results.
Other studies have also explored the use of AI in breast cancer detection. One study demonstrated that AI algorithms outperformed standard clinical risk models in predicting breast cancer risk. Another study found that AI performed as well as human readers in detecting breast cancer when compared to a large group of human readers.
In conclusion, AI shows promise in improving breast cancer detection rates and reducing the workload for healthcare professionals. However, further research and analysis of interval cancers are needed to assess the long-term impact of AI-supported screening on accuracy and effectiveness. The goal is to find a method that can identify clinically significant cancers at an early stage while minimizing false positives and overdiagnosis of indolent cancers.
Source link
