A single canonical neural atlas is learned jointly over thousands of ultrasound frames from five cardiac and musculoskeletal datasets via DINOv3 features and per-video generative latent optimization embeddings to support annotation transfer.
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
SpikeReg achieves Dice 0.7474 matching its ANN teacher on OASIS 3D registration at 12.8% spike rate with 55.5× projected energy reduction via ANN-to-SNN conversion and surrogate-gradient fine-tuning.
A pipeline generates patient-specific digital twins from static scans using analytical GI motion models to validate DIR accuracy and dose warping for mobile abdominal organs.
citing papers explorer
-
Cohort-Scale Neural Atlases of Ultrasound Video
A single canonical neural atlas is learned jointly over thousands of ultrasound frames from five cardiac and musculoskeletal datasets via DINOv3 features and per-video generative latent optimization embeddings to support annotation transfer.
-
SpikeReg: Energy-Efficient 3D Deformable Medical Image Registration with Spiking Neural Networks
SpikeReg achieves Dice 0.7474 matching its ANN teacher on OASIS 3D registration at 12.8% spike rate with 55.5× projected energy reduction via ANN-to-SNN conversion and surrogate-gradient fine-tuning.
-
Modality-agnostic, patient-specific digital twins modeling temporally varying digestive motion
A pipeline generates patient-specific digital twins from static scans using analytical GI motion models to validate DIR accuracy and dose warping for mobile abdominal organs.