#ImgLib2

Why would one want to run machine learning inference from #java?

To do so on 3D, 4D, ND datasets, trivially accessible from image processing and visualization libraries such as #ImgLib2, the #BigDataViewer, #LabKit and more, all integral parts of #FijiSc.

* LabKit: https://imagej.net/plugins/labkit/

* BigDataViewer: https://imagej.net/plugins/bdv/

* ImgLib2: https://imagej.net/libs/imglib2/

* Fiji: https://fiji.sc

@christianp

Unrelated – yet reminds me of the time we implemented unsigned integer division for 128-bit numbers ... in the end we delegated it to java's BigInteger: https://github.com/imglib/imglib2/blob/master/src/main/java/net/imglib2/type/numeric/integer/Unsigned128BitType.java

#ImgLib2

DeepImageJ 3.0 released—a user-friendly #FijiSc plugin that enables the use of a variety of pre-trained neural networks from the #BioimageModelZoo. Works with small and also very large images thanks to #ImgLib2.

https://deepimagej.github.io/

#DeepImageJ #PyTorch #TensorFlow #ImageJ #ImageProcessing

Every time I need to run an image processing task, the open source software #FijiSc delivers.

The javadocs are up to date https://javadoc.scijava.org/ , the libraries just work – particularly #ImgLib2 https://imagej.net/libs/imglib2/

And the examples of my own tutorial https://syn.mrc-lmb.cam.ac.uk/acardona/fiji-tutorial/ written in python 2.7 for the #JVM (#jython), despite some being a decade old, they all just work. Grateful every day for the outstanding backwards compatibility plus the new plugins and libraries that continue to grow https://fiji.sc

Many thanks to the many, many developers and maintainers, particularly Curtis Rueden, who is presently cutting out a new release: 2.11.0 https://forum.image.sc/t/plugin-maintainers-can-you-test-fiji-2-11-0/78852/18

#ImageProcessing

@b0rk For fast integer modulo computation in #java programs. For example, in the #ImgLib2:

// Same as (i * 4) % 64
final long shift = ( j << 2 ) & 63;

... in the Unsigned4BitType class: https://github.com/imglib/imglib2/blob/master/src/main/java/net/imglib2/type/numeric/integer/Unsigned4BitType.java#L105

@benoitmandelbot How nice–love the colors, looks tropical.

There is an example using the #ImgLib2 library implementing the computation and rendering at arbitrary depth of the #Mandelbrot set.

The main class to run it: https://github.com/imglib/imglib2-tutorials/blob/master/src/test/java/interactive/fractals/MandelbrotDemo.java

The viewer implementation:
https://github.com/imglib/imglib2-tutorials/blob/master/src/main/java/interactive/MandelbrotRealViewer2DExample.java

The Mandelbrot math bits, in a separate #java class: https://github.com/imglib/imglib2-tutorials/blob/master/src/main/java/interactive/fractals/MandelbrotRealRandomAccessible.java

@markkitti @HHMI Great to hear about the support for developing #imglib2 from #HHMI and #CZI! Tobias Pietzsch has made outstanding contributions to #imglib2 and #FijiSc in general, and now this support means he will have the means to continue to so. Excellent!

#FIJI development is mainly concentrated at #LOCI based at #UWMadison.

#imglib2 development is currently focused at @HHMI Janelia where I work.

Tobias Pietzsch, an independent developer, is now picking up of #imglib2 and #BigDataViewer development with support from #CZI and @HHMI .

One of the open source projects I work on is #FIJI (is just #ImageJ).

At the heart of #FIJI is #imglib2, a n-dimensional numerical processing library for #Java.

Yesterday, we had a Chan Zuckberg Initiative Essential Open Source Software sponsored community meeting:
https://forum.image.sc/t/bigdataviewer-imglib2-developer-community-activities/73836

Now onto #FijiSc: Fiji is a recursive acronym meaning "Fiji is just ImageJ" https://fji.sc (and the paper https://www.nature.com/articles/nmeth.2019 ) –and #ImageJ is a #java open source software for image processing https://imagej.nih.gov/ij/index.html written by Wayne Rasband from the #NIH Research Branch.

An analogy: think of ImageJ as the kernel and Fiji as the rest of the operating system.

#FijiSc brings to #ImageJ:
(1) a package manager to install and update plugins, and that crucially enables reproducible science by exporting the whole set of plugins and libraries as an executable;
(2) a Script Editor https://imagej.net/scripting/script-editor supporting many languages (#python, #groovy #ruby #scala #clojure and more), all with access to a huge collection of #JVM libraries;
(3) huge amount of libraries such as #ImgLib2, #JFreeChart for plotting, for GUIs, etc.

There are many, many plugins. A tiny sample:

Machine learning-based image segmentation:
- #LabKit https://imagej.net/plugins/labkit/
- #WEKA Trainable Segmentation https://imagej.net/plugins/tws/index

3D/4D/ND Visualization:
- 3D/4D Viewer #3DViewer https://imagej.net/plugins/3d-viewer/index with ray-tracing, orthoslices, volume rendering, and more
- #BigDataViewer #BDV https://imagej.net/plugins/bdv/index for interactively navigate N-dimensional image volumes larger than RAM

Image registration and serial section alignment:
- #BigStitcher for registering 3D/4D tiled datasets, with multiview deconvolution and more https://imagej.net/plugins/bigstitcher/index
- #TrakEM2 for montaging in 2D and alinging in 3D collections of serial sections, typically from #vEM (volume electron microscopy) https://syn.mrc-lmb.cam.ac.uk/acardona/INI-2008-2011/trakem2.html
- #mpicbg libraries for extracting #SIFT and #MOPS features, then finding feature correspondences and estimating rigid and elastic transformation models https://www.nature.com/articles/nmeth.2072

Summarizing #FijiSc is impossible. See the online forum where questions find answers by the hand of the broader community of users and developers https://forum.image.sc/