CAHAL introduces a physics-informed mixture-of-experts super-resolution network for clinical MRI that conditions on resolution and anisotropy and uses edge-penalised, Fourier, and segmentation-guided losses to reduce hallucinations compared with prior generative methods.
year 2012
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
NeuroAgent uses a hierarchical LLM agent framework with Generate-Execute-Validate loops to automate neuroimaging preprocessing, reaching 84.8% end-to-end correctness and 0.9518 AUC for Alzheimer's classification on 1470 ADNI subjects using four modalities.
Tuning a human connectome model via standardized metrics yields emergent alpha-band oscillations, infra-slow rhythms, and higher perturbational complexity in both spontaneous and evoked regimes.
SwinUNETR model with 32x32x32 patch sampling achieves DSC of 0.868 for LVCP segmentation in MS, outperforming UXNET with 99% lower computation.
HCP data analysis clusters individuals by social profiles into two groups where the more socially beneficial cluster scores higher on positive mental health measures and shows lower interconnectivity especially in the default mode network.
citing papers explorer
-
CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans
CAHAL introduces a physics-informed mixture-of-experts super-resolution network for clinical MRI that conditions on resolution and anisotropy and uses edge-penalised, Fourier, and segmentation-guided losses to reduce hallucinations compared with prior generative methods.
-
NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research
NeuroAgent uses a hierarchical LLM agent framework with Generate-Execute-Validate loops to automate neuroimaging preprocessing, reaching 84.8% end-to-end correctness and 0.9518 AUC for Alzheimer's classification on 1470 ADNI subjects using four modalities.
-
Emergent complexity and rhythms in evoked and spontaneous dynamics of human whole-brain models after tuning through analysis tools
Tuning a human connectome model via standardized metrics yields emergent alpha-band oscillations, infra-slow rhythms, and higher perturbational complexity in both spontaneous and evoked regimes.
-
Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis
SwinUNETR model with 32x32x32 patch sampling achieves DSC of 0.868 for LVCP segmentation in MS, outperforming UXNET with 99% lower computation.
-
Linking the "inner" and "outer" self to mental health and brain networks
HCP data analysis clusters individuals by social profiles into two groups where the more socially beneficial cluster scores higher on positive mental health measures and shows lower interconnectivity especially in the default mode network.