Publications by authors named "Rogeny Herisse"
Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Building on recent advancements in ultra-high-resolution ex vivo MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in ex vivo MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere ex vivo scans at 120 $\mu $m, we propose a Multi-resolution U-Nets framework that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.
View Article and Find Full Text PDFArticle Synopsis
- The text discusses open-source tools designed for 3D analysis of photographs from dissected human brain slices, which are often underutilized for quantitative studies.
- These tools can reconstruct a 3D volume and segment brain images into 11 regions per hemisphere, serving as a cost-effective alternative to traditional MRI imaging.
- Testing shows that the methodology provides accurate 3D reconstructions and can differentiate between Alzheimer's disease cases and healthy controls, with tools available in the FreeSurfer suite.
Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Leveraging recent advancements in ultra-high resolution MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere scans at 120 m, we propose a multi-resolution U-Nets framework (MUS) that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.
View Article and Find Full Text PDFArticle Synopsis
- Open-source tools have been developed for 3D analysis of brain slice photographs, which are often underutilized for quantitative research.
- These tools can 3D reconstruct brain volumes and segment them into 22 regions, independent of slice thickness, serving as a viable alternative to costly MRI scans.
- Tests on data from Alzheimer's Disease Research Centers show that the tools provide accurate reconstructions and detect differences related to Alzheimer's, with results comparable to those obtained from MRI.