CT-RATE
PulseAugur coverage of CT-RATE — every cluster mentioning CT-RATE across labs, papers, and developer communities, ranked by signal.
-
New 3D CT generation method improves accuracy and efficiency
Researchers have developed a new method for generating 3D CT scans from radiology reports, addressing limitations in existing text-to-CT approaches. The proposed technique utilizes a generation-oriented 3D-CLIP encoder …
-
New frameworks and leaderboards aim to standardize AI radiology report generation
Researchers have introduced ReXrank, a public leaderboard and challenge designed to standardize the evaluation of AI models for radiology report generation. This framework utilizes a large test dataset, ReXGradient, and…
-
Lightweight LLMs outperform rule-based systems in medical report labeling
A new study published on arXiv evaluated five lightweight, open-weight large language models (LLMs) for their ability to label chest, abdomen, and pelvis CT reports without prior fine-tuning. The LLMs, including MedGemm…
-
New ORCA method compresses 3D CT visual tokens for AI models
Researchers have developed ORCA (ORgan-Centroid Aggregation), a novel method for compressing visual tokens from 3D CT scans. This training-free approach merges adjacent tokens with organ guidance and incorporates centro…
-
Spectrum framework learns CT scan burden order across patients
Researchers have developed a new framework called Spectrum for volumetric CT vision-language pretraining. This method aims to improve how AI models understand the severity of medical conditions in CT scans by learning t…
-
New framework adapts CT foundation models for better radiology report alignment
Researchers have developed Anatomy Contextualized Adaptation (ACA), a novel framework designed to improve CT vision-language foundation models. ACA efficiently adapts existing frozen models for anatomy-level alignment w…
-
OrganLens framework learns organ-specific representations from CT scans
Researchers have developed OrganLens, a novel self-supervised learning framework designed to create organ-specific representations from CT scans. Unlike existing models that produce a single representation for an entire…
-
New CT Vision-Language Pretraining Frameworks Improve Abnormality Diagnosis · 3 sources tracked
Researchers have developed new frameworks for fine-grained vision-language pretraining (VLP) specifically for understanding computed tomography (CT) scans and radiology reports. One approach, OCP-CT, introduces organ-co…
-
New frameworks enhance medical image understanding with VLM-specialist synergy
Researchers have developed new frameworks for medical image understanding that combine the broad capabilities of vision-language models (VLMs) with specialized diagnostic tools. The Tool Bottleneck Framework (TBF) uses …
-
New CA-GCL Framework Enhances 3D Medical Image Understanding
Researchers have developed a new framework called CA-GCL to improve the understanding of 3D medical images. This method addresses the issue of text embeddings becoming too similar, making it difficult to distinguish bet…
-
New CORTEX benchmark aims for trustworthy AI in 3D chest CT analysis
Researchers have introduced CORTEX, a new benchmark designed to improve the trustworthiness of multimodal large language models (MLLMs) in 3D chest CT analysis. Existing datasets often reduce complex radiology reports t…
-
New AI methods boost efficiency and accuracy in 3D medical imaging analysis · 7 sources tracked
Researchers are developing new methods to improve the efficiency and accuracy of vision-language models (VLMs) for 3D medical imaging. MedPruner introduces a training-free framework to prune redundant tokens in 3D medic…
-
LLM-assisted cleaning improves chest CT dataset labels, study finds
A new study published on Hugging Face demonstrates the effectiveness of large language models (LLMs) in cleaning and verifying labels within large-scale medical imaging datasets. Researchers utilized GPT-5.4 to compare …
-
LLM-assisted label cleaning improves chest CT dataset accuracy
Researchers have developed a method using large language models (LLMs) to improve the accuracy of labels in large-scale medical imaging datasets. By comparing existing labels in the CT-RATE chest CT dataset with labels …
-
SliceWorld model enhances CT report generation with predictive world-state
Researchers have introduced SliceWorld, a novel framework designed for generating radiology reports from CT scans. Unlike previous methods that directly map images to text, SliceWorld models the evolution of anatomical …
-
New CA-GCL framework enhances 3D medical image understanding
Researchers have developed a new framework called CA-GCL to improve 3D medical image understanding through vision-language pre-training. Existing methods often struggle with text embeddings becoming too similar, making …
-
MedScribe framework uses agentic workflows for accurate CT scan reporting
Researchers have developed MedScribe, a new framework designed to improve the accuracy and clinical grounding of automated radiology report generation from CT scans. Unlike previous methods that compress entire scans in…
-
AI analyzes compressed CT scans efficiently with new FAST and SFP techniques
Researchers have developed a new framework called CT-Lite to enable AI analysis of compressed chest CT scans, addressing the computational burden of medical imaging data. The system utilizes Feature Attention Style Tran…
-
CT-FineBench benchmark evaluates fine-grained factual consistency in CT reports
Researchers have introduced CT-FineBench, a new benchmark designed to more accurately evaluate the fine-grained factual consistency of AI-generated Computed Tomography (CT) reports. Existing metrics often fail to captur…