Paper

Time-to-event Pretraining for 3D Medical Imaging

With the rise of medical foundation models and the growing availability of imag- ing data, scalable pretraining techniques offer a promising way to identify imaging biomarkers predictive of future disease risk. While current self-supervised meth- ods for 3D medical imaging models capture local structural features like organ morphology, they fail to link pixel biomarkers with long-term health outcomes due to a missing context problem. Current approaches lack the temporal context necessary to identify biomarkers correlated with disease progression, as they rely on supervision derived only from images and concurrent text descriptions. To address this, we introduce time-to-event pretraining, a pretraining framework for 3D medical imaging models that leverages large-scale temporal supervision from paired, longitudinal electronic health records (EHRs). Using a dataset of 18,945 CT scans (4.2 million 2D images) and time-to-event distributions across thousands of EHR-derived tasks, our method improves outcome prediction, achieving an av- erage AUROC increase of 23.7% and a 29.4% gain in Harrell’s C-index across 8 benchmark tasks. Importantly, these gains are achieved without sacrificing diag- nostic classification performance. This study lays the foundation for integrating longitudinal EHR and 3D imaging data to advance clinical risk prediction.

Download:

• ICLR 2025 - Time-to-event pretraining

Format

• Paper shared 1 week ahead for pre‑reading
• 5–10 min summary by a volunteer (no slides — we’ll scroll through the PDF together)
• Open discussion on methodology, strengths/weaknesses, clinical relevance, and future directions
• Papers chosen collaboratively to balance foundational ML research and cutting‑edge medical AI
• Who should attend? Researchers, clinicians, students — anyone curious about ML/AI in medicine.
• How to join? Simply show up (no registration required). Looking forward to seeing you there!

Organizers

Questions or paper suggestions? Contact us via Email.