7 papers
SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data
John Kalkhof, Boris Gutman, Emile d'Angremont +2
We introduce SMART, a framework for learning a flexible, interpretable, and scalable spatio-temporal brain atlas from longitudinal high-resolution 3D medical images. Existing appro…
OctreeNCA: Single-Pass 184 MP Segmentation on Consumer Hardware
Nick Lemke, John Kalkhof, Niklas Babendererde +1
Medical applications demand segmentation of large inputs, like prostate MRIs, pathology slices, or videos of surgery. These inputs should ideally be inferred at once to provide the…
Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge
Kang Wang, Chen Qin, Zhang Shi +46
Deep learning models have achieved state-of-the-art performance in automated Cardiac Magnetic Resonance (CMR) analysis. However, the efficacy of these models is highly dependent on…
Equitable Federated Learning with NCA
Nick Lemke, Mirko Konstantin, Henry John Krumb +3
Federated Learning (FL) is enabling collaborative model training across institutions without sharing sensitive patient data. This approach is particularly valuable in low- and midd…
MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion Segmentation
Avni Mittal, John Kalkhof, Anirban Mukhopadhyay +1
Denoising Diffusion Models (DDMs) are widely used for high-quality image generation and medical image segmentation but often rely on Unet-based architectures, leading to high compu…
NCAdapt: Dynamic adaptation with domain-specific Neural Cellular Automata for continual hippocampus segmentation
Amin Ranem, John Kalkhof, Anirban Mukhopadhyay
Continual learning (CL) in medical imaging presents a unique challenge, requiring models to adapt to new domains while retaining previously acquired knowledge. We introduce NCAdapt…