The Cancer Genome Atlas
PulseAugur coverage of The Cancer Genome Atlas — every cluster mentioning The Cancer Genome Atlas across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
New framework FTU-Seek improves tissue unit segmentation using foundation models
Researchers have developed FTU-Seek, a new framework designed to improve the segmentation of sparse functional tissue units (FTUs) in whole-slide images. This approach utilizes features from the UNI pathology foundation…
-
New MODIS framework integrates multi-omics data for rare diseases
Researchers have developed MODIS, a novel semi-supervised framework designed to integrate multi-omics data, particularly for small and unpaired datasets common in rare disease studies. The framework addresses challenges…
-
New PANDA framework enhances multimodal medical prediction with incomplete data
Researchers have developed PANDA, a novel two-stage framework designed to enhance multimodal medical prediction models by effectively utilizing auxiliary data that is not available for all subjects. The framework learns…
-
New model extracts signals from high-dimensional, small-sample data
Researchers have developed a novel method for extracting signals from high-dimensional, small-sample data by treating variables as points in a sample-coordinate space representing underlying multivariate dynamics. This …
-
New PerturbRx Framework Enhances Cancer Drug Response Prediction
Researchers have developed PerturbRx, a novel framework designed to improve patient-level cancer treatment-response prediction. This method learns latent molecular transitions induced by drug treatments, even without po…
-
New AI methods enhance Whole Slide Image analysis for pathology reports
Researchers have developed new methods for analyzing Whole Slide Images (WSIs) in pathology. One approach decomposes WSI report generation into distinct stages, using graph-constrained multiple instance learning (MIL) t…
-
LLMs advance cancer survival prediction with new comparative learning framework
Researchers have developed CACSurv, a novel framework that leverages large language models (LLMs) for cancer survival prediction using patient reports. This method addresses two key challenges: a formulation mismatch wh…
-
New Gated SRP Module Enhances Transformer Models for Pathology
Researchers have developed Gated Spatial Redundancy Projection (Gated SRP), a new module designed to improve the performance of Transformer models in computational pathology. This method addresses the issue of spatial r…
-
Transformer-based TransNRank model advances neoantigen prediction accuracy
Researchers have developed TransNRank, a novel deep learning framework utilizing the Transformer architecture for more accurate neoantigen prediction. This model addresses challenges like data scarcity and class imbalan…
-
New agentic framework predicts gene perturbation effects using patient data
Researchers have developed CASCADE, a novel agentic framework designed to predict the downstream transcriptional effects of gene perturbations. This framework leverages precomputed ARACNe regulatory networks and is vali…
-
New survival model validation method shows cohort-dependent performance
Researchers have developed and validated a method called drcosarc, a post-hoc conformal wrapper for discrete-time multiple-instance learning survival models. This method was tested across multiple cohorts from The Cance…
-
New diffusion models enhance pathological image resolution for better diagnostics · 2 sources tracked
Two new research papers propose advanced diffusion models for enhancing the resolution of pathological images, aiming to improve diagnostic accuracy. S$^3$-Diff utilizes a Structural Semantic Synergy approach with speci…
-
New CIGTSurv framework enhances cancer survival prediction using multimodal data
Researchers have developed CIGTSurv, a novel framework for survival prediction that integrates clinical information with pathology images and genomic data. This approach addresses the challenge of underutilizing discret…
-
New SAGE framework offers semantic explanations for AI in pathology
Researchers have developed SAGE, a new post-hoc framework designed to provide semantic, language-grounded explanations for attention-based multiple instance learning (ABMIL) models used in computational pathology. Unlik…
-
New benchmark OncoTriad-QA tests AI's cancer diagnosis integration skills
Researchers have introduced OncoTriad-QA, a new benchmark designed to evaluate the capabilities of large language models (LLMs) and vision-language models (VLMs) in integrating diverse patient data for cancer diagnosis.…
-
PathSelect framework enables efficient WSI processing for vision-language models
Researchers have developed PathSelect, a novel framework for efficiently processing gigapixel Whole-Slide Images (WSIs) with vision-language models. This method reformulates token pruning as a sequential selection proce…
-
AI model predicts colorectal cancer survival from histology images
Researchers have developed a graph neural network called INSIGHT that can predict patient survival rates directly from routine histology images of colorectal cancer. This model, trained on TCGA and SURGEN datasets, demo…
-
Copula-based fusion of clinical and genomic scores improves breast cancer risk stratification
Researchers have developed a new method using copula functions to fuse clinical and genomic risk scores for breast cancer stratification. While this approach did not improve predictive accuracy (ROC-AUC) compared to usi…
-
PathSelect framework tackles WSI processing for vision-language models
Researchers have developed PathSelect, a novel framework designed to address the computational challenges of processing gigapixel whole-slide images (WSIs) with vision-language models (VLMs). PathSelect reformulates tok…
-
Deep learning predicts gene expression from tissue images
Researchers have developed and validated deep regression models capable of predicting gene expression directly from whole-slide images (WSIs) of cancer tissue. These models, utilizing attention-based multiple instance l…