Outlining Advances in AI For Breast Cancer Screening/Radiomics

Clinical trials, including the phase 3 TAILORx trial (NCT00310180), have served as validation points for radiomic models, enabling clinicians to predict responses to endocrine therapy and other treatments with CT scans.

Arturo Loaiza-Bonilla, MD, MSEd, FACP, the systemwide chief of Hematology and Oncology at Saint Luke’s University, discussed key advances regarding the implementation of artificial intelligence (AI) in breast cancer screening and treatment. First, he highlighted a new step for breast cancer: validation of breast cancer screening at a population level.

Then, he explained that he is examining the use of AI in the early detection of cancer through mammograms, but that it has been applied to genomic testing and biomarker testing as well. Additionally, citing findings presented at the 2025 San Antonio Breast Cancer Symposium, he stated that transformer-based architecture could predict recurrence in patients and identify certain patients who may require additional screening for germline alterations or risk factors.

Using radiomics as an example, he explained that a CT scan can be used to assess the probability of response with certain therapies. Citing studies such as the TAILORx trial, he concluded by suggesting that studies have validated many of these models for use in the clinic.

Transcript:

In breast cancer, the new steps are, first, validation at the population level. Each country and each region is doing its own clinical trials. I’m currently running for early detection with mammograms and others. We also have seen that the implementation of AI into the genomic testing, or the biomarker testing, on our patients is becoming relevant.

There were some updates from [the 2025 San Antonio Breast Cancer Symposium] showing how a potential transformer-based architecture can predict potential recurrence in patients. It can optimize those recurrent response scores that we are seeing from different vendors in a more meaningful way and find those niche patients that need either more screening or early detection of other things, such as germline alterations or risk factors, when we use any combination with other data sets.

In this case, for example, we can use radiomics. We know that with radiomics, we can, just by looking at a CT scan, understand if the patient is going to respond to, for example, endocrine therapy. That’s something that, for us, is mind blowing because we did not have that information before. Now, using the data sets for many clinical trials that have been done before––the [phase 3 TAILORx trial] and others––has been a major validation point for many of those models that are being deployed in the clinic, or at least in clinical practice for further validation.

Reference

Feng C, Muhammad H, Chavan SS, et al. Artificial intelligence predicts OncotypeDX recurrence scores directly from H&E-stained whole slide images of ER+/HER2- node-negative breast cancer surgical sections. Presented at: 2025 San Antonio Breast Cancer Symposium; December 9-12, 2025; San Antonio, TX. PS3-06-02