3D light-sheet microscopy data for SELMA3D 2026 challenge - isolated structures - training patches with no annotations

ABSTRACT: This dataset is the training set containing large 3D LSM images of isolated structures without annotations annotations for SELMA3D 2026 challenge. The SELMA3D 2026 challenge focuses on self-supervised learning for 3D light-sheet microscopy (LSM) image segmentation. Its objective is to encourage the development of generalizable models capable of serving multiple 3D LSM image segmentation tasks. This dataset contains cropped 3D patches from large images of different isolated structures, including c-Fos labeled brain cells involved in neural activity, cell nuclei, Alzheimer's disease plaques, chondrocytes, astrocytes, dopaminergic neurons and chondrogenic cells.

SUBMITTER: Ying Chen 

PROVIDER: S-BIAD3281 | bioimages |

REPOSITORIES: bioimages