DeepCERES
DeepCERES is a pipeline to automatically analyze cerebellum at ultra-high-resolution MRI (0.125 mm3). It gets an anonymized standard resolution T1w MRI brain volume in NIFTI format and produces a pdf report. DeepCERES provides the volumes/asymmetries of the cerebellum lobules and the cerebellum tissues.
Labelling protocol
Cerebellum white matter and lobules were manually segmented by experts in a set of 75 high resolution T1w and T2w MRI subjects. All structures were outlined using a modified version of the Park et al., 2014. protocol to avoid white matter sub estimation.
Report
Once the process is finished, you will be notified by e-mail, so you will be able to download a package including some image files and two reports (CSV and PDF) providing all the volumes estimated from the segmentations. As you can see in the figure below, the PDF includes patient information, volume of cerebellum tissues and cerebellum lobules, cerebellum pseudo-cortical thickness as well as asymmetry indexes. Finally, it also includes several snapshots from the different labeling steps as a quality control.
References
Morell-Ortega, S., Ruiz-Perez, M., Gadea, M., Vivo-Hernando, R., Rubio, G., Aparici, F., de la Iglesia-Vaya, M., Catheline, G., Coupé, P., & Manjón, J. v. (2024). DeepCERES: A Deep learning method for cerebellar lobule segmentation using ultra-high resolution multimodal MRI. arXiv Preprint arXiv:2401.12074. PDF