#17 · ML / AI methods
Individualized brain network models and multivariate comparison of subject parcellations
The dominant thread is individualized brain network analysis, represented here by IndivSTATIS, a multivariate STATIS-based method that compares individualized parcellations and networks within a shared component space. The other two preprints do not address brain network modeling. One is a multiscale circulation model coupling systemic hemodynamics, cerebral autoregulation, and imaging-derived Circle of Willis networks to simulate flow under anatomical variations and stenosis. The other is a MICCAI 2024 challenge report on deep learning for enlarged perivascular space MRI segmentation, in which top methods degrade on an unseen cohort. What is new in IndivSTATIS is the explicit comparison of individual brain network configurations within a single shared component space.
Preprints
Standardized Evaluation of Automatic Methods for Perivascular Spaces Segmentation in MRI -- MICCAI 2024 Challenge Results
MICCAI 2024 challenge benchmarks deep learning for enlarged perivascular space MRI segmentation; top methods degrade on an unseen cohort.
Multiscale modeling of blood circulation with cerebral autoregulation and network pathway analysis for hemodynamic redistribution in the vascular network with anatomical variations and stenosis conditions
Multiscale circulation model coupling systemic hemodynamics, cerebral autoregulation, and imaging-derived Circle of Willis networks to simulate flow…
IndivSTATIS: A multivariate approach to analyze brain network configurations with individualized parcellation
IndivSTATIS, a multivariate STATIS-based method that compares individualized brain parcellations and networks in a shared component space for predicting…
Topic history
| Date | Rank |
|---|---|
| #17 | |
| #13 | |
| #11 | |
| #11 | |
| #8 | |
| #31 | |
| #32 | |
| #37 | |
| #38 | |
| #34 | |
| #22 | |
| #38 |