Dice Score
PulseAugur coverage of Dice Score — every cluster mentioning Dice Score across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Ultra-lightweight AI framework achieves high-fidelity brain tumor segmentation
Researchers have developed Uni-Light, an ultra-lightweight framework for 3D brain tumor segmentation from MRI scans. This new framework significantly reduces computational demands, boasting a 97.56% reduction in paramet…
-
Deep learning models compared for bovid tooth segmentation with imperfect data
A new research paper explores the effectiveness of convolutional and attention-based deep neural networks for segmenting bovid dentition images. The study, conducted on the B.O.V.I.D. dataset, addresses the challenge of…
-
MedSAM2 adapted for interactive ILD segmentation in CT scans
Researchers have adapted MedSAM2, a foundation model, for interactive segmentation of interstitial lung disease (ILD) in thoracic CT scans. This adaptation aims to improve quantitative disease assessment by allowing ref…
-
New SAS technique boosts AI segmentation of small ultrasound structures
Researchers have developed Segment Anything Small (SAS), a novel data augmentation technique designed to improve the accuracy of deep learning models in segmenting small anatomical structures within ultrasound images. S…
-
New AI model NerveDetNet detects nerves beneath tissue using OCT
Researchers have developed a novel label-free framework for detecting peripheral nerves beneath intact tissue using optical coherence tomography (OCT) and a deep learning model called NerveDetNet. This system integrates…
-
New AI method models geographic atrophy progression using implicit neural networks
Researchers have developed a novel method using Implicit Neural Representations (INRs) to model the progression of Geographic Atrophy (GA) in patients with Age-related Macular Degeneration (AMD). This approach aims to p…
-
New OTLesMix method generates diverse synthetic brain lesions for improved AI segmentation
Researchers have developed a novel method called OTLesMix for generating synthetic medical images, specifically focusing on brain lesions. This technique utilizes Wasserstein barycenters and optimal transport maps to cr…
-
AI model reduces need for spine degeneration grading labels via segmentation pre-training
Researchers have developed a new method for grading lumbar spine degeneration using segmentation pre-training, which significantly reduces the need for expert-annotated radiological gradings. By pre-training a 3D ResNet…
-
AI model improves uterine layer segmentation in dynamic MRI scans
Researchers have developed an unsupervised adversarial domain adaptation framework to improve uterine layer segmentation in dynamic EPI MRI scans. This method transfers segmentation knowledge from labeled cine MRI data …
-
AI model accelerates liver tumor ablation planning
Researchers have developed a physics-guided deep learning model to accelerate the planning of microwave ablation (MWA) for liver tumors. This model, trained on multiphysics simulation data, acts as a fast forward model …
-
User-prompted priors boost cancer lesion segmentation in CT scans
Researchers have explored how user-provided information, known as priors, can enhance the semi-automated segmentation of cancer lesions in computed tomography scans. The study found that more complex spatial priors, suc…
-
MRI representations benchmarked for deep learning FCD segmentation
Researchers have benchmarked different magnetic resonance imaging (MRI) representations for deep learning-based segmentation of focal cortical dysplasia (FCD). Using the nnU-Net framework on a dataset of 85 FCD subjects…
-
Human-AI collaboration boosts medical image segmentation accuracy
Researchers have developed Hi-Seg, a framework that enhances the Segment Anything Model (SAM) for pulmonary nodule segmentation in medical imaging. This human-in-the-loop system allows annotators, including non-medical …
-
AI advances medical image segmentation with new frameworks and techniques · 8 sources tracked
Researchers are developing advanced AI frameworks for medical image segmentation, focusing on improving accuracy and efficiency. Hi-Seg enhances the Segment Anything Model (SAM) for pulmonary nodule segmentation through…
-
New wavelet method improves fundus image segmentation across domains
Researchers have developed a novel wavelet-guided segmentation network called WaveSDG to address challenges in fundus image segmentation across different acquisition conditions. This method decouples anatomical structur…
-
Self-supervised MAE pretraining boosts nnFormer for medical image segmentation
Researchers have developed a self-supervised pretraining framework using Masked Autoencoders (MAE) to improve the efficiency of nnFormer models for medical image segmentation. This approach allows the model to learn ana…