Skip to content
Snippets Groups Projects
README.md 1.32 KiB
Newer Older
  • Learn to ignore specific revisions
  • monj's avatar
    monj committed
    ### Modeling of local structure with a dictionary of image patches 
    ### - applied to the study of Lung ECM proteins
    
    monj's avatar
    monj committed
    
    
    monj's avatar
    monj committed
    To reproduce the results from our paper (link to come), you will need to clone this repository or download it as a .zip file. Then, download the input_data and results_justDictionaries folders from DTU Data at XX. Place both within the Lung_ECM folder, besides the code folder. Rename 'results_justDictionaries' to 'results' so as to reproduce the exact results from our paper. Under the same DTU Data link you will also find the complete set of results under 'results_complete'.
    
    monj's avatar
    monj committed
    
    The following figure is a schematic view of the code, results and input_data folders. The table below describes further the content of the code folder found in this repository.
    
    monj's avatar
    monj committed
    
    
    monj's avatar
    monj committed
    Code contains:
    
    | File name | Description | Input | Output |
    | --------- | ----------- | ----- | ------ |
    
    monj's avatar
    monj committed
    | lung_lif_to_png.py | Transforms Leica microscope format into a png | .lif file pr. sample | input_data/raw | 
    | microscopy_analysis.py | Helper functions 
    | image_preprocessing.py | Equalises contrast across images and channels, and computes max. projections | input_data/raw | input_data/maximum_projections and postprocessed_maxProjs
    
    
    monj's avatar
    monj committed
    
    
    
    monj's avatar
    monj committed
    nogenerate data_corrected_bis, where each 3D scan is stored as a sequence of .png files under a folder with 'frame' as prefix.