Tag: medical image segmentation

A semi-supervised diffusion model accurately segments vascular plaques across multiple arteries on non-contrast CT scans using only fourteen labeled training ...

Researchers have developed DynamicFusionNet, a decoder that adaptively fuses features across layers, scales and views to improve medical image segmentation ...

A new teacher-student framework aggregates knowledge from multiple medical imaging datasets and consistently improves segmentation, classification, and detection performance across ...

A new MLP-based segmentation method combining mixer layers with channel attention achieved a Dice coefficient of 81.45 percent on the ...

A frequency-aware sparse vision transformer outperformed comparison models on organ, cardiac, breast, skin and polyp segmentation across five public medical ...

A review of 2019–2025 research finds that transformer models show promise for lung cancer detection and classification, but variable validation ...

A new Mamba-based segmentation network combines four-directional state space scanning, spatially guided channel attention, and parameter-free anatomical constraints to outperform ...

A Portuguese team built a multi-stage AI pipeline that segments vertebrae and discs in multi-vendor lumbar MRI, then classifies each ...

Researchers have adapted Meta's Segment Anything Model for medical imaging by combining low-rank fine-tuning, Mamba-based adapters, and a prompt-free decoder, ...

Oxford researchers argue that the common practice of reducing expert annotations to single binary masks introduces a hidden source of ...