Initial results from an ECOG-ACRIN and Caris Life Sciences collaboration show AI-driven multimodal models can more accurately predict recurrence risk in early-stage breast cancer.
Key Details
- 1Collaboration leverages ECOG-ACRIN's clinical trial data and Caris' molecular profiling and imaging AI platforms.
- 2Over 4,000 TAILORx trial patient cases used to train and validate new multimodal deep learning models.
- 3Models integrate histopathologic slide imaging, clinical, and expanded gene expression data.
- 4AI models outperformed established recurrence risk assessment methods, especially for late recurrence (after 5 years).
- 5Potential shown for a scalable, cost-effective diagnostic test based on routine histology and clinical data rather than solely on genomic assays.
- 6Results presented at the 2023 San Antonio Breast Cancer Symposium.
Why It Matters
The study demonstrates unprecedented large-scale integration of imaging, molecular, and clinical data for recurrence prognostication, charting a path toward more personalized and precise breast cancer management. Imaging AI's role in such multimodal frameworks signifies a promising advance for the development of new diagnostic tools in oncologic pathology.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.