Package: segmantR 0.2.0

R. Heller

segmantR: Cell Segmentation for Histology with Human-in-the-Loop Training

Cell segmentation for histology and multiplexed tissue imaging. Provides classical segmentation methods (adaptive thresholding, watershed, Voronoi propagation), wrappers through 'reticulate' for the deep learning models 'Cellpose' (Stringer et al. (2021) <doi:10.1038/s41592-020-01018-x>), 'StarDist' (Schmidt et al. (2018) <doi:10.1007/978-3-030-00934-2_30>) and 'Mesmer' (Greenwald et al. (2022) <doi:10.1038/s41587-021-01094-0>), and a human-in-the-loop iterative refinement workflow. A 'shiny' application lets researchers annotate, correct, train, evaluate and download custom segmentation models without leaving R. Versioned declarative segmentation protocols, a neutral interchange format (JSON manifests, integer label TIFF, GeoJSON, measurement tables with SHA-256 inventories), training dataset manifests with grouped splits, and readable 'QuPath' script templates with a 'StarDist' parameter adapter support reproducible exchange with 'QuPath' and partner packages.

Authors:R. Heller [aut, cre, cph]

segmantR_0.2.0.tar.gz
segmantR_0.2.0.zip(r-4.7-any)segmantR_0.2.0.zip(r-4.6-any)segmantR_0.2.0.zip(r-4.5-any)
segmantR_0.2.0.tgz(r-4.6-any)segmantR_0.2.0.tgz(r-4.5-any)
segmantR_0.2.0.tar.gz(r-4.7-any)segmantR_0.2.0.tar.gz(r-4.6-any)
segmantR_0.2.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
segmantR/json (API)

# Install 'segmantR' in R:

install.packages('segmantR', repos = c('https://cttir.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/cttir/segmantr/issues

Pkgdown/docs site:https://cttir.github.io

On CRAN:

4.26 score 1 packages 4 scripts 136 exports 60 dependencies

Last updated from:882c2fb7fe. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel	OK	258
source / vignettes	OK	290
linux-release	OK	274
macos-release	OK	207
macos-oldrel	OK	219
windows-devel	OK	219
windows-release	OK	223
windows-oldrel	OK	208
wasm-release	OK	142

Exports:new_sg_image new_sg_mask new_sg_trained_model renderSgCanvas sg_active_learning_loop sg_app sg_apply_corrections sg_canvas sg_canvas_correct sg_cleanup_labels sg_control_capabilities sg_create_annotation_task sg_dataset_manifest sg_display_levels sg_display_range sg_envi_info sg_evaluate_segmentation sg_example_image sg_example_mask sg_export_interchange sg_export_mask sg_export_qupath sg_extract_features sg_filter_cells sg_hash_assets sg_image_channels sg_import_interchange sg_import_qupath sg_interchange_capabilities sg_interchange_manifest sg_load_model sg_mask_legend sg_mask_revision sg_mask_status sg_mask_to_polygons sg_merge_masks sg_model_card sg_package_model sg_plot_comparison sg_plot_features sg_plot_mask sg_plot_metrics sg_plot_overlay sg_predict_model sg_prepare_training_data sg_preprocess sg_protocol_get sg_protocol_list sg_protocol_run sg_protocol_schema sg_protocol_validate sg_read_envi sg_read_field sg_read_fields sg_read_image sg_read_window sg_replace_mask sg_review_mask sg_roi_add_layer sg_roi_add_roi sg_roi_area sg_roi_bbox sg_roi_buffer sg_roi_centroid sg_roi_check_containment sg_roi_check_geometry sg_roi_circle sg_roi_clamp sg_roi_contains sg_roi_difference sg_roi_dims sg_roi_distance sg_roi_ellipse sg_roi_fix_geometry sg_roi_flip_y sg_roi_frame sg_roi_freehand sg_roi_from_geojson sg_roi_from_sf sg_roi_intersect sg_roi_layer sg_roi_layer_add sg_roi_layer_n sg_roi_layer_remove sg_roi_layer_rois sg_roi_layers sg_roi_mask sg_roi_mask_boundary sg_roi_mask_derive sg_roi_mask_legend sg_roi_mask_preview sg_roi_mask_stack sg_roi_mask_stats sg_roi_overlaps sg_roi_point sg_roi_polygon sg_roi_project sg_roi_read_geojson sg_roi_read_qupath sg_roi_rect sg_roi_remove_layer sg_roi_remove_roi sg_roi_rescale sg_roi_ring sg_roi_rois sg_roi_rois_overlap sg_roi_simplify sg_roi_snap sg_roi_style sg_roi_summary sg_roi_symdiff sg_roi_transform sg_roi_union sg_roi_validate sg_roi_write_geojson sg_roi_write_qupath sg_run_app sg_segment_cellpose sg_segment_mesmer sg_segment_propagate sg_segment_stardist sg_segment_threshold sg_segment_watershed sg_select_channel sg_setup_python sg_slide_display_ranges sg_stage_mask sg_stain_deconvolve sg_stardist_capabilities sg_stardist_manifest sg_stardist_parameter_map sg_train_cellpose sg_train_stardist sg_validate_interchange sg_validate_training_manifest sgCanvasOutput

Dependencies:abind base64enc bslib cachem class classInt cli commonmark cpp11 DBI digest dplyr e1071 farver fastmap fontawesome fs generics ggplot2 glue gtable htmltools httpuv isoband jquerylib jsonlite KernSmooth labeling later lifecycle magrittr memoise mime otel pillar pkgconfig promises proxy R6 rappdirs RColorBrewer Rcpp rlang s2 S7 sass scales sf shiny sourcetools stars tibble tidyselect units utf8 vctrs viridisLite withr wk xtable

Standard protocols, DNN training and QuPath/StarDist exchange

Rendered fromprotocols-and-interop.Rmdusingknitr::rmarkdown

Last update: 2026-10-28
Started: 2026-09-15

Help page	Topics
Create a new sg_image object	new_sg_image
Create a new sg_mask object	new_sg_mask
Create a new sg_trained_model object	new_sg_trained_model
Run an active learning loop for iterative segmentation refinement	sg_active_learning_loop
Build the segmantR Shiny application	sg_app
Apply manual corrections to a segmentation mask	sg_apply_corrections
Draw cell boundaries on a microscopy image	sg_canvas
Apply a cell canvas correction	sg_canvas_correct
Clean up a label mask	sg_cleanup_labels
Control service capabilities (segmantR-control-v1)	sg_control_capabilities
Create an annotation task for human review	sg_create_annotation_task
Describe a training dataset	sg_dataset_manifest
Display levels from positive and negative reference cells	sg_display_levels
Display range of fluorescence values	sg_display_range
Read and validate an ENVI header without reading pixel data	sg_envi_info
Evaluate segmentation quality	sg_evaluate_segmentation
Load a bundled example image	sg_example_image
Load a bundled example mask	sg_example_mask
Export to the neutral interchange format	sg_export_interchange
Export mask to file	sg_export_mask
Export segmantR objects or a StarDist protocol for QuPath	sg_export_qupath
Extract per-cell features from an image and mask	sg_extract_features
Filter cells by morphological criteria	sg_filter_cells
Hash, write or verify a bundle inventory	sg_hash_assets
List the channels of a multi-page microscopy TIFF	sg_image_channels
Import interchange data	sg_import_interchange
Import QuPath results into segmantR	sg_import_qupath
Interchange capability report	sg_interchange_capabilities
Build an interchange manifest	sg_interchange_manifest
Load a packaged segmantR model	sg_load_model
Effective legend of a mask	sg_mask_legend
Stage, review or replace masks	sg_mask_review sg_replace_mask sg_review_mask sg_stage_mask
Content revision of a mask	sg_mask_revision
Review state of a mask	sg_mask_status
Convert mask to polygon geometries	sg_mask_to_polygons
Merge nuclear and cell body masks	sg_merge_masks
Display a formatted model card	sg_model_card
Package a trained model for sharing	sg_package_model
Side-by-side comparison of two masks	sg_plot_comparison
Scatter plot of cell features	sg_plot_features
Render a mask as a coloured image	sg_plot_mask
Bar chart of evaluation metrics	sg_plot_metrics
Overlay cell boundaries on an image	sg_plot_overlay
Predict with a trained model	sg_predict_model
Prepare training data tiles	sg_prepare_training_data
Preprocess an image	sg_preprocess
Get a registered protocol	sg_protocol_get
List registered segmentation protocols	sg_protocol_list
Run a declarative segmentation protocol	sg_protocol_run
Protocol schema and parameter specifications	sg_protocol_schema
Validate a protocol, optionally against an image and parameters	sg_protocol_validate
Read an ENVI cube window into an sg_image	sg_read_envi
Read a square multichannel field around a point	sg_read_field
Read many square fields, for example cell galleries	sg_read_fields
Read an image file	sg_read_image
Read a rectangular pixel window of one channel	sg_read_window
Histology ROI objects	sg_roi
Add a layer to a project	sg_roi_add_layer
Add an ROI to a project layer	sg_roi_add_roi
ROI area	sg_roi_area
ROI bounding box	sg_roi_bbox
Buffer an ROI	sg_roi_buffer
ROI centroid	sg_roi_centroid
Check cross-layer containment	sg_roi_check_containment
Check the geometry of every ROI in a project	sg_roi_check_geometry
Create a circular ROI	sg_roi_circle
Clip an ROI to image bounds	sg_roi_clamp
Test whether points fall inside an ROI	sg_roi_contains
Image dimensions at a pyramid level	sg_roi_dims
Distance between two ROIs	sg_roi_distance
Create an elliptical ROI	sg_roi_ellipse
Repair the geometry of a project	sg_roi_fix_geometry
Flip an ROI's y-axis	sg_roi_flip_y
Declare the coordinate frame for histology ROIs	sg_roi_frame
Create a freehand ROI	sg_roi_freehand
Convert a GeoJSON feature to an ROI	sg_roi_from_geojson
Create an ROI from an existing sf geometry	sg_roi_from_sf
Create a layer	sg_roi_layer
Add an ROI to a layer	sg_roi_layer_add
Number of ROIs in a layer	sg_roi_layer_n
Remove an ROI from a layer	sg_roi_layer_remove
Layer ROI table	sg_roi_layer_rois
Layer summary table	sg_roi_layers
Rasterise ROIs to a mask	sg_roi_mask
Object boundaries of a mask	sg_roi_mask_boundary
Derive a training mask from layer masks	sg_roi_mask_derive
Legend of a mask	sg_roi_mask_legend
Downsampled preview of a mask	sg_roi_mask_preview
Stack per-layer masks into a 3D array	sg_roi_mask_stack
Per-value statistics of a mask	sg_roi_mask_stats
Test whether two ROIs intersect	sg_roi_overlaps
Create a point ROI	sg_roi_point
Create a polygon ROI	sg_roi_polygon
Create an annotation project	sg_roi_project
Read ROIs from a GeoJSON file	sg_roi_read_geojson
Read ROIs from a QuPath GeoJSON file	sg_roi_read_qupath
Create a rectangular ROI	sg_roi_rect
Remove a layer from a project	sg_roi_remove_layer
Remove an ROI from a project	sg_roi_remove_roi
Rescale an ROI between pyramid levels	sg_roi_rescale
Ring (annulus) along an ROI margin	sg_roi_ring
Query the ROIs of a project	sg_roi_rois
Pairwise ROI overlaps within a layer	sg_roi_rois_overlap
Set operations on ROIs	sg_roi_difference sg_roi_intersect sg_roi_setops sg_roi_symdiff sg_roi_union
Simplify an ROI	sg_roi_simplify
Snap ROI vertices to a grid	sg_roi_snap
Layer style	sg_roi_style
Summarise a project	sg_roi_summary
Transform an ROI between pyramid levels using real image dimensions	sg_roi_transform
Validate a project's invariants	sg_roi_validate
Write a project's ROIs to GeoJSON	sg_roi_write_geojson
Write a project's ROIs as QuPath GeoJSON	sg_roi_write_qupath
Launch the segmantR Shiny application	sg_run_app
Cellpose cell segmentation	sg_segment_cellpose
Mesmer (DeepCell) cell segmentation	sg_segment_mesmer
Voronoi propagation from nuclear seeds	sg_segment_propagate
StarDist cell segmentation	sg_segment_stardist
Threshold-based cell segmentation	sg_segment_threshold
Marker-controlled watershed segmentation	sg_segment_watershed
Select one analysis channel from an image	sg_select_channel
Set up a Python environment for deep learning backends	sg_setup_python
Slide-wide display ranges from sampled image blocks	sg_slide_display_ranges
Separate H&E stain channels by colour deconvolution	sg_stain_deconvolve
StarDist adapter capabilities	sg_stardist_capabilities
Describe a StarDist model for exchange	sg_stardist_manifest
Map StarDist protocol parameters to Python or QuPath	sg_stardist_parameter_map
Fine-tune a Cellpose model on user-corrected masks	sg_train_cellpose
Train a StarDist 2D model	sg_train_stardist
Validate interchange data	sg_validate_interchange
Validate a training dataset manifest	sg_validate_training_manifest
Shiny bindings for the cell canvas	renderSgCanvas sgCanvasOutput

Package: segmantR 0.2.0

segmantR: Cell Segmentation for Histology with Human-in-the-Loop Training

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)