: The smallest expected distance between two distinct nuclei. Threshold : The sensitivity level for peak detection.
: ITCN can automatically count nuclei within an image or a selected region of interest. This feature significantly speeds up the analysis process compared to manual counting.
We benchmarked ITCN against manual counting across 50 fluorescence micrographs (40x, 1024x1024 pixels, DAPI-stained HeLa cells, ~80–200 nuclei per field). itcn imagej plugin
– If using ITCN in published work, cite: “Image-based Tool for Counting Nuclei (ITCN)” – available via ImageJ.net, and reference the ImageJ software (Schneider et al., 2012, Nat Methods).
: Open ITCN and input the following estimations: Width (Diameter) : The average size of a nucleus in pixels. : The smallest expected distance between two distinct nuclei
| Tool | Strengths | Weaknesses | Best for | |------|-----------|------------|----------| | | No training, fast, interpretable | Fails on irregular shapes, intensity gradients | Routine, well-stained spherical nuclei | | StarDist (QuPath/ImageJ) | Handles any shape, excellent accuracy | Requires training data (~50–100 annotated images) | Complex tissues, variable morphology | | Cellpose | Outstanding on heterogeneous data | Heavy GPU requirements, overkill for simple assays | Unusual cell types, phase-contrast images | | Trainable Weka Segmentation | Good for texture-based separation | Slow, manual feature selection | Images with texture but poor contrast |
: Close and reopen ImageJ. The tool will appear under the Plugins menu (often specifically Plugins > Filters > ITCN ). Step-by-Step Usage Guide This feature significantly speeds up the analysis process
ITCN remains the best first-line tool for standard DAPI/Hoechst-stained monolayers or sections with round/oval nuclei. If ITCN fails after 15 minutes of parameter tuning, then invest time in deep-learning tools.
Download ITCN.class from the ImageJ plugin repository (or via Fiji’s update manager under “ITCN”). Place it in plugins/ and restart ImageJ.
While ImageJ’s built-in Analyze Particles works for well-separated objects, it fails when nuclei touch, cluster, or vary in intensity. Enter the —originally developed by the Center for Bio-Image Informatics at UC Santa Barbara. It implements an intelligent, Laplacian-of-Gaussian (LoG)-based spot detection algorithm specifically optimized for round, sub-cellular features.
: Obtain the ITCN_.jar file from ImageJ's plugin page or BioImage UCSB .