AI Shows Promise in Early Detection of Interval Breast Cancers, UCLA Study Finds

2 Sources

Share

A new study by UCLA researchers suggests that AI could help detect interval breast cancers before they become more advanced, potentially improving screening practices and patient outcomes.

News article

AI's Potential in Detecting Interval Breast Cancers

A groundbreaking study led by investigators at the UCLA Health Jonsson Comprehensive Cancer Center has revealed that artificial intelligence (AI) could play a crucial role in detecting interval breast cancers - those that develop between routine screenings. The research, published in the Journal of the National Cancer Institute, suggests that AI technology could potentially improve screening practices, lead to earlier treatment, and enhance patient outcomes

1

2

.

Study Methodology and Findings

The retrospective study analyzed nearly 185,000 mammograms from 2010-2019, focusing on 148 cases of interval breast cancer. Researchers used a commercially available AI software called Transpara to review initial screening mammograms performed before cancer diagnosis. The AI tool scored each mammogram from 1 to 10 for cancer risk, with scores of 8 or higher flagged as potentially concerning

1

2

.

Key findings from the study include:

  1. AI was able to identify "mammographically-visible" types of interval cancers earlier by flagging them at the time of screening.
  2. Researchers estimate that incorporating AI into screening could reduce the number of interval breast cancers by 30%.
  3. The AI tool flagged 69% of screening mammograms that had occult cancers, which are typically invisible on mammography.

Implications for Breast Cancer Screening

Dr. Tiffany Yu, assistant professor of Radiology at UCLA and first author of the study, emphasized the importance of these findings: "For patients, catching cancer early can make all the difference. It can lead to less aggressive treatment and improve the chances of a better outcome"

1

2

.

The study is among the first to explore the use of AI for detecting interval breast cancers in the United States, taking into account the differences between U.S. and European screening practices. In the U.S., most mammograms use digital breast tomosynthesis (3D mammography) with annual screenings, while European programs typically use digital mammography (2D) with screenings every two to three years

1

2

.

Challenges and Future Directions

Despite the promising results, researchers also identified areas for improvement. Dr. Hannah Milch, senior author of the study, noted: "While we had some exciting results, we also uncovered a lot of AI inaccuracy and issues that need to be further explored in real-world settings"

1

2

.

Some challenges include:

  1. The AI tool's accuracy in pinpointing the exact location of cancer was limited, marking the actual cancer only 22% of the time in occult cases.
  2. Larger prospective studies are needed to understand how radiologists would use AI in practice.
  3. Questions remain about handling cases where AI flags areas as suspicious that aren't visible to the human eye.

Conclusion

While AI shows promise in improving early detection of interval breast cancers, researchers emphasize that it should not be used on its own. Dr. Yu concluded, "This is about giving radiologists better tools and giving patients the best chance at catching cancer early, which could lead to more lives saved"

1

2

.

The study, supported by various organizations including the National Institutes of Health and the National Cancer Institute, represents a significant step forward in the integration of AI technology in breast cancer screening and early detection.

TheOutpost.ai

Your Daily Dose of Curated AI News

Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.

© 2025 Triveous Technologies Private Limited
Instagram logo
LinkedIn logo