nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
PulseAugur coverage of nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation — every cluster mentioning nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation across labs, papers, and developer communities, ranked by signal.
14 day(s) with sentiment data
-
nnU-Net pipeline achieves high accuracy in brain metastasis segmentation for BraTS 2026
Researchers have developed a new segmentation pipeline for brain metastases using the nnU-Net framework, achieving a lesion-wise Dice similarity coefficient (LW-DSC) of 0.733 on the enhancing tumor region for the BraTS …
-
Federated learning boosts cross-modality medical image segmentation
A new research paper explores federated learning techniques to improve cross-modality medical image segmentation, addressing challenges posed by data distributed across institutions and varying imaging protocols. The st…
-
LightMedSeg-ISLES achieves competitive stroke lesion segmentation with 81x fewer parameters
Researchers have developed LightMedSeg-ISLES, a new segmentation pipeline for stroke lesions that significantly reduces the number of parameters compared to existing methods. This model, with 1.26 million parameters, ac…
-
Weakly supervised AI segments complex kidney structures in X-ray microCT
Researchers have developed a weakly supervised deep learning approach to segment complex structures in X-ray microCT images, significantly reducing the need for extensive manual annotation. The method, adapted from the …
-
AI improves medical imaging segmentation for cancer trials
Researchers have developed a method to improve the accuracy of deep learning models for segmenting clinical target volumes (CTVs) in medical imaging, specifically for the AGITG TOPGEAR clinical trial involving gastric c…
-
Exemplar method fuses classical priors and DINOv3 for few-shot microscopy segmentation
Researchers have developed a new few-shot segmentation method called Exemplar, which combines a frozen DINOv3 backbone with classical native-resolution filter responses. This fusion allows Exemplar to achieve high perfo…
-
New AURA strategy improves ULF pediatric brain MRI segmentation
Researchers have developed an asymmetric supervision strategy called AURA for segmenting pediatric brain MRIs using ultra-low-field (ULF) technology. This method addresses challenges in ULF imaging where anatomical boun…
-
Mamba architecture adapted for MRI-to-CT synthesis in radiotherapy planning
Researchers have adapted the SegMamba architecture, originally designed for image segmentation, to perform MRI-to-CT synthesis for radiotherapy planning. This novel approach utilizes state-space modeling to capture comp…
-
AI model performance and human variability in cancer index assessment analyzed
Researchers have evaluated how variations in human interpretation and AI model performance affect the assessment of radiological Peritoneal Cancer Index (rPCI) scores using contrast-enhanced CT scans. The study found th…
-
New AI methods boost brain tumor segmentation accuracy and generalization
Researchers have developed advanced methods for brain tumor segmentation in MRI scans, aiming to improve generalization across different datasets and patient populations. One approach utilizes the nnU-Net framework with…
-
AI model achieves 2nd place in tumor segmentation and pCR prediction challenge
A team from the Fellow of the Academy of Medical Sciences has detailed their approach for the MAMA-MIA Challenge, focusing on tumor segmentation and pathological complete response (pCR) prediction using dynamic contrast…
-
AI models tackle PET/CT lesion segmentation for AUTOPET V challenge · 2 sources tracked
Two research papers submitted to arXiv detail novel pipelines for interactive lesion segmentation in PET/CT scans, specifically for the AUTOPET V challenge. Both approaches focus on distinguishing between FDG and PSMA t…
-
AI models in pathology gain robustness through new benchmarking and artifact generation techniques
Two new research papers explore methods for improving the reliability and robustness of AI models in computational pathology. The first paper, "Reliable Benchmarking of Artifact Detection in Computational Pathology," pr…
-
AnatoProto framework improves fetal ultrasound plane detection
Researchers have developed AnatoProto, a novel framework designed to improve the detection of standard planes in fetal ultrasound blind sweeps. This method adapts a frozen BiomedCLIP encoder by incorporating anatomy-wei…
-
New geometry-guided operator boosts 3D medical image segmentation
Researchers have developed a novel geometry-guided sampling operator designed to improve volumetric segmentation in medical imaging. This operator steers feature sampling based on local orientation and step sizes, rathe…
-
Deep learning model accurately segments stroke lesions on MRI
Researchers have evaluated a pragmatic deep learning approach for segmenting acute ischaemic stroke (AIS) lesions using diffusion-weighted MRI (DWI-MRI). The study found that a baseline nnU-Net model, trained on DWI alo…
-
AI model performance in medical imaging heavily influenced by annotation quality, study finds
A new study published on arXiv investigates the impact of annotation quality on the performance of AI models for pulmonary embolism (PE) segmentation in CT scans. Researchers found that changes in evaluation annotations…
-
New AI frameworks enhance brain tumor segmentation from MRI scans
Researchers have developed new frameworks for 3D brain tumor segmentation using magnetic resonance imaging (MRI). The first, MSM-Seg, integrates multi-modal and inter-slice information with a category-agnostic prompt to…
-
AI framework improves aortic tracking in cardiac MRI scans
Researchers have developed a novel semi-supervised spatiotemporal knowledge distillation framework designed to improve aortic tracking in cardiac cine-MRI scans. This method addresses limitations in standard 2D segmenta…
-
New methods boost whole-heart segmentation accuracy in CT and MRI
Researchers have developed new methods to improve whole-heart segmentation in medical imaging, specifically for computed tomography (CT) and magnetic resonance imaging (MRI). One approach, proposed by Purdue-M2, uses a …