Main Menu (Mobile)- Block

Main Menu - Block

custom | custom

Search Results

filters_region_cap | custom

Filter

facetapi-Q2b17qCsTdECvJIqZJgYMaGsr8vANl1n | block

Associated Lab

facetapi-W9JlIB1X0bjs93n1Alu3wHJQTTgDCBGe | block

Associated Project Team

facetapi-61yz1V0li8B1bixrCWxdAe2aYiEXdhd0 | block

Associated Support Team

facetapi-PV5lg7xuz68EAY8eakJzrcmwtdGEnxR0 | block
facetapi-aK0bSsPXQOqhYQEgonL2xGNrv4SPvFLb | block

Tool Types

general_search_page-panel_pane_1 | views_panes

1 Janelia Publications

Showing 1-1 of 1 results
Your Criteria:
    09/04/17 | Deep learning for isotropic super-resolution from non-isotropic 3D electron microscopy.
    Heinrich L, Bogovic JA, Saalfeld S
    International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2017. MICCAI 2017. Lecture Notes in Computer Science. 2017 Sept 4;10434:arXiv:1706.03142. doi: 10.1007/978-3-319-66185-8_16

    The most sophisticated existing methods to generate 3D isotropic super-resolution (SR) from non-isotropic electron microscopy (EM) are based on learned dictionaries. Unfortunately, none of the existing methods generate practically satisfying results. For 2D natural images, recently developed super-resolution methods that use deep learning have been shown to significantly outperform the previous state of the art. We have adapted one of the most successful architectures (FSRCNN) for 3D super-resolution, and compared its performance to a 3D U-Net architecture that has not been used previously to generate super-resolution. We trained both architectures on artificially downscaled isotropic ground truth from focused ion beam milling scanning EM (FIB-SEM) and tested the performance for various hyperparameter settings.

    Our results indicate that both architectures can successfully generate 3D isotropic super-resolution from non-isotropic EM, with the U-Net performing consistently better. We propose several promising directions for practical application.

    View Publication Page