Histopathology
PulseAugur coverage of Histopathology — every cluster mentioning Histopathology across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New ELF model integrates foundation models for precision oncology
Researchers have developed ELF (Ensemble Learning of Foundation models), a novel approach that integrates five pretrained pathology foundation models to create unified slide-level representations for precision oncology.…
-
New AI framework improves PET image retrieval for cancer heterogeneity
Researchers have developed a novel framework for learning representations from 18F-FDG PET imaging data, specifically designed for content-based retrieval of intra-tumour heterogeneity. This weakly supervised method lev…
-
New Active Learning Framework Slashes Histopathology Annotation Costs
Researchers have developed SHAL (Slide-level Hybrid Active Learning), a novel framework designed to significantly reduce the annotation burden in deep learning models for histopathology image segmentation. This patient-…
-
New Locus framework guides AI attention to relevant anatomy in medical images
Researchers have developed Locus, a new framework designed to improve medical image classification by guiding a model's attention to diagnostically relevant anatomical regions. This method leverages pretrained segmentat…
-
TCLA method enhances medical vision-language models without training
Researchers have developed TCLA, a novel method for adapting medical vision-language models (VLMs) without requiring additional training. This approach corrects inference logits using a small set of support samples, enh…
-
AI detects toxicity in preclinical histopathology using novel anomaly detection
Researchers have developed an AI framework to detect toxicity in preclinical histopathology using whole-slide images. This system can identify healthy tissue, known pathologies, and flag samples with novel anomalies. By…
-
New AI framework improves medical image anomaly detection across modalities
Researchers have developed a novel training-free framework for medical image anomaly detection that can be applied across various imaging modalities without requiring modality-specific architectures or retraining. This …
-
New CADRE framework enhances safe adaptation of medical vision-language models
Researchers have developed CADRE, a new framework for adapting medical vision-language models (VLMs) efficiently and safely. This method focuses on preventing catastrophic forgetting and prior drift, crucial for clinica…
-
Vision-Language Models Achieve Zero-Annotation Histopathology Segmentation
Researchers have developed a novel approach using vision-language models (VLMs) to perform foreground segmentation in histopathology images without requiring manual annotations. This method treats tissue-versus-backgrou…
-
DualGate-Net improves histopathology cell detection with adaptive priors
Researchers have developed DualGate-Net, a novel framework for detecting cells in histopathology images. This system utilizes a dual-encoder approach, combining local and global encoders with a learnable prior-gated fus…
-
STREAM framework enhances histopathology image generation using Riemannian flow matching
Researchers have developed STREAM, a novel framework for generating synthetic histopathology images. This method addresses the issue of "conditioning collapse" seen in existing models by using pretrained Vision Foundati…
-
New method boosts AI diagnostics in histopathology
Researchers have developed a new method called Geometry-Aware Uncertainty Coresets (GAUC) to improve the reliability of visual in-context learning in histopathology. This training-free approach optimizes the selection o…
-
New method improves medical segmentation model calibration using ordinal learning
Researchers have developed a new method to improve the calibration of medical image segmentation models, particularly when multiple expert annotations show significant disagreement. The approach reformulates multi-rater…