Deep Atlas is a suite of tools created by the Blue Brain Project to manipulate brain atlas images.
Among different sources of data, Allen Brain Institute hosts a rich database of gene expression images, Nissl volumes, and annotation atlases. The Atlas-Download-Tools library can help you to download single section images and entire datasets, as well as the corresponding metadata. It can further pre-process the image data to place it in the standard reference space.
Over the years the Allen Brain institute has constantly improved and updated their brain region annotation atlases. Unfortunately the old annotation atlases are not always aligned with the new ones. For example, the CCFv2 annotations and the Nissl volume are not compatible with the CCFv3 annotation and the corresponding average brain volume. This package proposes a number of methods for deforming the Nissl volume and the CCFv2 annotations in order to re-align them to CCFv3.
Atlas Alignment is a Blue Brain toolbox to perform multi-modal image registration and alignment. It includes both traditional and supervised deep learning models. It is also used to fix any misalignment between ISH stains and Nissl stains within the Blue Brain Cell Atlas
The Allen Brain Institute hosts a rich database of mouse brain imagery. It contains a large number of gene expression datasets obtained through the in situ hybridization (ISH) staining. While for a given gene a number of datasets corresponding to different specimen can be found, each of these datasets only contains sparse section images that do not form a continuous volume. This package explores techniques that allow to interpolate the missing slices and thus reconstruct whole gene expression volumes.