CODA: shorthand for calling functions | HuBMAP | JHU-TMC v2

Le résumé fourni par la source

To downsample ndpi or svs images to 10x, 5x, and 1x tifs, use this function: create_downsampled_tif_imagesor try Openslide in python To calculate registration on the low resolution (1x) images 1. calculate the tissue area and background pixels using this function: calculate_tissue_ws 2. calculate the registration transforms: calculate_image_registration To build a 3D tissue volume using sematic segmentation: 1. generate manual annotations in Aperio imagescope 2. apply the deep learning function to train a model and segment the high resolution (5x or 10x) images: train_image_segmentation To apply the registration to segmented images: apply_image_registration To build a 3D tissue matrix from registered, classified images: build_tissue_volume To build a 3D cell volume containing nuclear coordinates: 1. Build a mosaic image containing regions of many whole-slide images for cell detection optimization: make_cell_detection_mosaic 2. Manually annotate the mosaic image to get the ‘ground-truth’ number of cell nuclei: manual_cell_count 3. Determine cell detection parameters using the manual annotations on the mosaic image: get_nuclear_detection_parameters 4. Deconvolve the high-resolution (5x or 10x) H&E images before applying the cell detection algorithm: deconvolve_histological_images 5. Detect cells on the hematoxylin channel of the high-resolution images: cell_detection 6. Apply the registration to the cell coordinates: register_cell_coordinates 7. Build a 3D cell coordinate matrix corresponding to the 3D tissue matrix: build_cell_volume

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.