Package index • segmantR

All functions

example_images: Example segmantR images
example_masks: Example segmantR masks
new_sg_image(): Create a new sg_image object
new_sg_mask(): Create a new sg_mask object
new_sg_trained_model(): Create a new sg_trained_model object
sg_active_learning_loop(): Run an active learning loop for iterative segmentation refinement
sg_apply_corrections(): Apply manual corrections to a segmentation mask
sg_create_annotation_task(): Create an annotation task for human review
sg_evaluate_segmentation(): Evaluate segmentation quality
sg_example_image(): Load a bundled example image
sg_example_mask(): Load a bundled example mask
sg_export_mask(): Export mask to file
sg_extract_features(): Extract per-cell features from an image and mask
sg_filter_cells(): Filter cells by morphological criteria
sg_load_model(): Load a packaged segmantR model
sg_mask_to_polygons(): Convert mask to polygon geometries
sg_merge_masks(): Merge nuclear and cell body masks
sg_model_card(): Display a formatted model card
sg_package_model(): Package a trained model for sharing
sg_plot_comparison(): Side-by-side comparison of two masks
sg_plot_features(): Scatter plot of cell features
sg_plot_mask(): Render a mask as a coloured image
sg_plot_metrics(): Bar chart of evaluation metrics
sg_plot_overlay(): Overlay cell boundaries on an image
sg_preprocess(): Preprocess an image
sg_read_image(): Read an image file
sg_run_app(): Launch the segmantR Shiny application
sg_segment_cellpose(): Cellpose cell segmentation
sg_segment_mesmer(): Mesmer (DeepCell) cell segmentation
sg_segment_propagate(): Voronoi propagation from nuclear seeds
sg_segment_stardist(): StarDist cell segmentation
sg_segment_threshold(): Threshold-based cell segmentation
sg_segment_watershed(): Marker-controlled watershed segmentation
sg_setup_python(): Set up a Python environment for deep learning backends
sg_stain_deconvolve(): Separate H&E stain channels by colour deconvolution
sg_train_cellpose(): Fine-tune a Cellpose model on user-corrected masks