All Competitors

A neuro-oncology foundation model for brain tumor MRI that uses distributionally robust self-supervised pretraining to predict molecular markers and survival across institutions.

A SimCLR self-supervised foundation model for 3D brain MRI, pretrained on 18,759 patients across 11 neurological-disease datasets for diverse diagnostic tasks.

An open-source PPG foundation model pretrained on raw wearable signals from a 100-day field study, generalizing across lab and field health tasks.

A knowledge-enhanced ECG foundation model that pairs a ResNet signal encoder with LLM-derived diagnostic knowledge for zero- and few-shot electrocardiogram interpretation.

Multimodal contrastive model aligning clinical EEG recordings with free-text reports, enabling label-efficient and zero-shot EEG phenotyping via text prompts.

Anatomical foundation models for brain MRI, pretrained with weakly supervised contrastive learning over cortical anatomy for diagnosis and clinical score prediction.

Self-supervised CNN pretrained on 700,000 person-days of UK Biobank accelerometer data for human activity recognition, transferable across devices and cohorts.

A self-supervised 3D CT foundation model that extracts general-purpose tumor representations for cancer imaging biomarker discovery across diverse downstream tasks.

Self-supervised vision foundation model pretrained on ~1.3M medical images via second-order graph matching, transferable across 15 medical imaging tasks.