pathology foundation models
PulseAugur coverage of pathology foundation models — every cluster mentioning pathology foundation models across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New framework DICE enhances AI pathology model reliability with uncertainty estimation
Researchers have developed a new framework called DICE to improve the reliability of pathology foundation models (PFMs) for whole-slide image analysis. This framework ensembles multiple frozen PFMs and uses their disagr…
-
New GLMP Framework Uses LLMs to Improve Pathology Model Generalization
Researchers have developed GLMP, a new framework designed to improve the generalization of pathology foundation models by mitigating batch effects. This novel approach utilizes multimodal large language models (MLLMs) t…
-
New tool guides AI model pretraining for pathology data
Researchers have developed SlideCheck, a tool designed to guide the self-supervised pretraining of pathology foundation models. This tool operates by analyzing dataset distributions and providing explicit scores for abn…
-
Gastric cancer AI model GRACE boosts pathologist accuracy
Researchers have developed GRACE, a specialized foundation model for gastric cancer pathology, trained on a large dataset of over 48,000 whole-slide images. This model demonstrated superior performance compared to gener…
-
New AI models integrate spatial omics data for biological insights
Researchers have developed HEIST, a hierarchical graph transformer model designed to analyze spatial transcriptomics and proteomics data. This model represents tissues as hierarchical graphs, capturing both spatial cell…
-
New method boosts pathology model robustness across hospitals
Researchers have developed a new method to improve the robustness of pathology foundation models (PFMs) across different hospitals. The technique, called local maximum mean discrepancy (LMMD), helps classifiers maintain…
-
New benchmark SpaPath-Bench evaluates spatial understanding in pathology AI models
Researchers have introduced SpaPath-Bench, a new benchmark designed to evaluate the spatial representation capabilities of pathology foundation models (PFMs). This benchmark assesses how well PFM embeddings can distingu…
-
Foundation models aid lung cancer growth pattern prediction with attention-based learning
Researchers have developed an attention-based multiple instance learning (ABMIL) framework to predict lung adenocarcinoma growth patterns from whole slide images. This method reduces the need for extensive annotations b…