Description:
Risk assessment is a key tool for personalized screening and early detection of breast cancer. In recent work1, the Massachusetts Institute of Technology (MIT) team developed deep learning models (MIRAI) that assess cancer risk from full-resolution screening mammograms and found them to be significantly more accurate than the Tyrer-Cuzick (TC) model2. The MIRAI tool has not been well assessed high-risk patients screened with MRI and mammography. The purpose of this study is to compare the performance of MIRAI to that of TC in high-risk patients.
Hypothesis:
Women in the high-risk program with the top risk decile by the Hybrid DL model will have a higher cancer detection rate than women in the lower risk decile, thus better predicting breast cancer development and risk assessment than currently exists.
Specific Objective(s):
To assess screening MRI performance metrics including cancer detection rate, sensitivity, and specificity in those identified as increased risk by MIRAI vs TC.
Brief Methods:
A database of high-risk patients who underwent annual screening MRI with the Ontario Breast Screening Program (OBSP) between 06/01/2019 to 12/31/2022, with one year follow-up data will be accessed. Demographic information, TC scores, information from the MRI and mammography reports, and biopsy and surgical pathology results will be accessed using EPIC.
Artificial Intelligence Scores: Screening mammograms will be processed through MIRAI through an onsite server at The Ottawa Hospital. MIRAI scores from bilateral screening mammograms from patients who underwent high-risk screening MRI after normal mammography will be obtained.
Student skills required:
The student will be required to review patients in EPIC, have Excel and Word skills, be able to review using PACS, and collaborate with the research staff to complete tasks. Prior research collaboration and skills would be an asset.
Potential skills developed:
The student would learn about the imaging for cancer detection, the performance indicators for high quality work in breast imaging, the importance of Artificial intelligence in Radiology, as well as joining a collaborative team of researchers dedicated to early detection of breast cancer.
Timeline:
The project would begin May 1, 2025, and completed by August 31, 2025.
References:
- Yala A, Lehman C, Schuster T, Portnoi T, Barzilay R. A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction. Radiology. 2019;292:60-66. doi: 10.1148/radiol.2019182716
- Yala A, Mikhael PG, Strand F, Lin G, Satuluru S, Kim T, Banerjee I, Gichoya J, Trivedi H, Lehman CD, et al. Multi-Institutional Validation of a Mammography-Based Breast Cancer Risk Model. J Clin Oncol. 2022;40:1732-1740. doi: 10.1200/jco.21.01337