PET-CT
PulseAugur coverage of PET-CT — every cluster mentioning PET-CT across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Specialized LMM shows promise for PET/CT cancer diagnosis
Researchers have developed a specialized Large Multimodal Model (LMM) by fine-tuning LLaVA-NeXT to interpret PET/CT scans for head and neck cancer. This specialized model significantly outperformed generalist models lik…
-
New dataset and benchmark advance 3D medical vision-language models
Researchers have introduced MetaStructAtlas, a novel dataset designed for interpreting whole-body PET/CT scans. This dataset includes co-registered 3D PET and CT volumes, along with extensive organ-level segmentation ma…
-
AI model enhances PET/CT lesion segmentation with interactive scribbles
Researchers have developed a novel interactive lesion segmentation method for PET/CT scans, utilizing a scribble-conditioned ResEnc U-Net. This approach leverages user-provided scribbles to mark foreground and backgroun…
-
LLMs evaluated for radiology report accuracy and longitudinal data extraction · 2 sources tracked
Researchers are exploring the use of large language models (LLMs) for improving radiology report quality and extracting longitudinal information. One study compared domain-specific BERT models with open-weight LLMs like…
-
AI model tackles PET/CT lesion segmentation challenge
Libo Zhang has developed a novel three-phase curriculum learning approach for interactive lesion segmentation in PET/CT scans, addressing the autoPETV Grand Challenge. This method utilizes a U-Net architecture with appr…
-
New research explores multimodal AI for PET/CT lesion segmentation
Two new research papers explore multimodal self-supervised learning for PET/CT lesion segmentation in cancer patients. The first paper, MUST-PET, proposes a framework that uses both PET and CT scan data, trained across …
-
New framework evaluates AI for lymphoma detection in medical scans
Researchers have developed a new framework to evaluate deep neural networks used for segmenting lymphoma from PET/CT images. This framework addresses limitations in current research by incorporating out-of-distribution …
-
AI predicts lung cancer mutations from scans using multi-label learning
Researchers have developed a multi-label learning approach using deep learning to predict specific gene mutations (EGFR, TP53, and KRAS) in non-small cell lung cancer (NSCLC) from PET/CT scans. The study, conducted on a…
-
New benchmarks and methods advance medical vision-language models
Researchers have developed new benchmarks and distillation techniques to improve the capabilities of vision-language models (VLMs) in the medical domain. PathAgentBench focuses on evaluating VLMs' ability to acquire and…
-
LLMs and RL enhance PET/CT lesion segmentation in new RADIANT-PET framework
Researchers have developed RADIANT-PET, a novel framework for improving lesion segmentation in PET/CT scans for oncology. This system integrates a voxel-level segmentation model with a large language model (LLM) for les…
-
HECKTOR 2025 challenge benchmarks AI for head and neck cancer analysis · 2 sources tracked
The HECKTOR 2025 challenge, building on previous iterations, established a benchmark for automated head and neck cancer analysis using multimodal PET/CT imaging and electronic health records. This challenge involved ove…
-
New MuDuo framework uses dual-foundation models for semi-supervised PET/CT segmentation
Researchers have developed a novel semi-supervised learning framework called MuDuo for segmenting organs in PET/CT scans. This method leverages dual-foundation models, utilizing SAM-Med3D for CT imaging and SegAnyPET fo…
-
AI framework MuDuo enhances PET/CT segmentation with dual-foundation models
Researchers have developed a novel mutual distillation framework called MuDuo for semi-supervised segmentation of PET/CT scans, addressing the high cost of manual annotation in oncology. This framework leverages dual-fo…
-
AI models predict lung cancer survival from PET/CT scans
Researchers have developed new AI models, ATCS and MTS, to predict overall survival in lung cancer patients using PET/CT scans. These models outperformed a baseline TCS model, achieving AUCs of 0.794 and 0.793 respectiv…
-
AI models struggle with unseen PET/CT tracer combinations despite segmentation gains
The autoPET3 challenge, held in conjunction with MICCAI 2024, focused on automated lesion segmentation in whole-body PET/CT scans, specifically testing compositional generalization. The challenge utilized a large datase…