Smoothing

This workflow segments glands from H&E stained histopathological images
from the Gland Segmentation Challenge (GlaS2015) using deep learning (UNet).
UNet implementation largely inspired from PyTorch-UNet by Milesial. 

This workflow processes images of cells with discernible nuclei and outputs a binary mask containing where nuclei are detected.

The macro will segment nuclei and separate clustered nuclei in a 3D image using a distance transform watershed. As a result an index-mask image is written for each input image.

Performs 3D Gaussian blurring.

CLIJ2 is a GPU-accelerated image processing library for ImageJ/Fiji, Icy, Matlab and Java. It comes with hundreds of operations for filtering, binarizing, labeling, measuring in images, projections, transformations and mathematical operations for images. While most of these are classical image processing operations, CLIJ2 also allows performing operations on matrices potentially representing neighborhood relationships between cells and pixels.

CLIJ2 was developed to process images from fluorescence microscopy data of developing cells, tissues, organoids and organisms.

The MIPAV (Medical Image Processing, Analysis, and Visualization) application enables quantitative analysis and visualization of medical images of numerous modalities such as PET, MRI, CT, or microscopy. Using MIPAV's standard user-interface and analysis tools, researchers at remote sites (via the internet) can easily share research data and analyses, thereby enhancing their ability to research, diagnose, monitor, and treat medical disorders.

"The plugin analyzes fluorescence microscopy images of neurites and nuclei of dissociated cultured neurons. Given user-defined thresholds, the plugin counts neuronal nuclei, and traces and measures neurite length."[...]" NeuriteTracer is a fast simple-to-use ImageJ plugin for the analysis of outgrowth in two-dimensional fluorescence microscopy images of neuronal cultures. The plugin performed well on images from three different types of neurons with distinct morphologies."

This plugin requires parameter setting: Threshold levels and scale (see more details on the related publication)

Provides a selection of spatial, separable and customizable filters in 1D and 2D, with OpenCL implementation if supported.

This CellProfiler module allows smoothen the image with a choice from various algorithms: - Fit Polynomial - Gaussian Filter - Median Filter - Bilateral Filter - Circular averaging - "Smooth to Average" filter.

The smoothing is applied by the way of a bi-exponential filter, itself realized by a pair of one-tap recursions. It is therefore very fast; moreover, its computational cost is truly independent of the amount of smoothing. Meanwhile, the preservation of edges is obtained by a range filter akin to the range filter found in a bilateral filter. More technical details are available here.

The plugin allows one to control the amount of smoothing, the type of range filter, its broadness, and to iterate the filter several times if desired. We illustrate in Figure 2 a possible outcome of this filter. Here, we iterated the BEEPS 10 times with a Gaussian range filter, σ = 10, and the spatial decay λ = 0.1.

Anisotropic filters are a class of filter that reduces noise in an image while trying to preserve sharp edges

There are two implementations of Tschumperle/ R. Deriche filter ("anisotropic diffusion") for ImageJ Plugin

1. in the "imaging book" codes: see the javadoc here.

2. in Xlib

The Graph Cut plugin provides a way to obtain a globally smooth binary segmentation. As input, you have to provide a gray-scale image that represents the pixel affinities for belonging to the foreground. Via a single parameter you can adjust the smoothness of the segmentation.