Artificial Intelligence Could Revolutionize Early Breast Cancer Detection

AI could be a breakthrough in early breast cancer detection, pinpointing tumors that radiologists miss. A UCLA Health study found that AI can identify tumors that develop between routine screenings. With the technology, the risk of detecting breast cancer could be reduced by 30%.

Researchers at UCLA Health Jonsson Comprehensive Cancer Center have conducted a study that suggests artificial intelligence (AI) could help detect breast cancers that develop between screening exams. This important finding could improve early diagnoses and allow for more effective treatment.

For the study, the team analyzed data from mammograms taken between 2010 and 2019 using commercially available AI software Transpara. The study found that the AI ​​was able to flag 76% of mammograms that were previously considered normal but later turned out to contain cancerous tumors. The AI ​​tool, giving scores on a scale of 1 to 10, pinpointed areas of risk that radiologists might have missed.

While the results are promising, the researchers point out some inaccuracies that require further study. For example, in the case of occult cancers, which are not visible on mammography, the AI ​​detected only 69% of cases. In turn, the accuracy of pinpointing the exact location of the tumor was lower.

Experts emphasize that AI, while promising, requires further research and testing in real clinical settings. The UCLA team is planning further studies to better understand how radiologists will use AI and how these tools can aid in early detection of breast cancer.