Loading…
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Red blood cell morphology foundation model pretrained on 1.25 million single-cell crops, released as small, base, and large ViT feature extractors.
Histology vision transformer with 80M parameters that predicts spatial gene expression from H&E tissue images and transfers to tumor detection.
Histopathology segmentation model aligning SAM to clinical intent through direct preference optimization, tested zero-shot on 12 external datasets.
Histopathology and multi-omics foundation model pretrained with masked omics modeling on 4,718 pan-cancer TCGA cases spanning 32 cancer types.
Contrastive alignment framework that projects H&E histology and single-cell transcriptomic foundation model embeddings into one shared latent space.
Sparse autoencoder for blood-cell microscopy that decomposes hematology foundation model embeddings into expert-validated sub-cellular concepts.
Attention-based multiple instance learning heads for whole-slide pathology, pretrained on a 108-way pan-cancer slide classification task.
Histopathology foundation model trained with direct slide-level supervision on 37k whole-slide images. Averages 0.784 AUROC on 10 biomarker tasks.
Medically tuned SigLIP encoder from Google that maps medical images and text into one embedding space for zero-shot classification and retrieval.
Whole-slide histopathology foundation model trained end-to-end on slide-level labels across 18 tasks, on 5% of the energy of SSL-trained peers.
Self-supervised medical imaging foundation model pretrained on 3.3 million CT, X-ray, ultrasound, pathology, OCT, fundus, and dermoscopy images.
Histopathology image synthesis from a latent diffusion model conditioned jointly on unpaired diagnostic text reports and cell-type masks.
Text-prompted pathology image segmentation across 160 tissue, cell, and nuclei categories, replacing point and box inputs with natural language.
Genome-anchored histopathology embeddings that predict molecular biomarkers, subtypes, and survival from whole-slide images alone at inference.
Medical multimodal LLM (2B and 8B) trained for generalizable, step-by-step clinical reasoning via Mentor-Intern Collaborative Search.
Generative histopathology foundation model: a diffusion transformer trained on 30M H&E tiles, conditioned on self-supervised slide embeddings.
Spatial proteomics foundation model, marker-aware and panel-agnostic, pretrained on 47 million multiplexed tissue-imaging patches from 175 markers.
Agent-based pathology model that navigates whole-slide images by zooming and panning like a pathologist, scoring 88.6% on the PathMMU-HR2 benchmark.
Cytogenetics foundation model detecting numerical and structural chromosome abnormalities from metaphase images, pretrained on 84,000 specimens.