Albert Cardona

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: imagej.net/plugins/labkit/

* BigDataViewer: imagej.net/plugins/bdv/

* ImgLib2: imagej.net/libs/imglib2/

* Fiji: fiji.sc

Labkit - Intuitive Pixel Classification in Fiji

The ImageJ wiki is a community-edited knowledge base…

imagej.net
Albert Cardona

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.

deepimagej.github.io/

#DeepImageJ #PyTorch #TensorFlow #ImageJ #ImageProcessing

deepImageJ • Home

deepimagej.github.io
Albert Cardona

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

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

And the examples of my own tutorial syn.mrc-lmb.cam.ac.uk/acardona 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 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 forum.image.sc/t/plugin-mainta

#ImageProcessing

SciJava Javadoc

javadoc.scijava.org
Albert Cardona

@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!

Mark Kittisopikul

#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 .

Mark Kittisopikul

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:
forum.image.sc/t/bigdataviewer

Albert Cardona

Now onto #FijiSc: Fiji is a recursive acronym meaning "Fiji is just ImageJ" fji.sc (and the paper nature.com/articles/nmeth.2019 ) –and #ImageJ is a #java open source software for image processing 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 imagej.net/scripting/script-ed 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 imagej.net/plugins/labkit/
- #WEKA Trainable Segmentation imagej.net/plugins/tws/index

3D/4D/ND Visualization:
- 3D/4D Viewer #3DViewer imagej.net/plugins/3d-viewer/i with ray-tracing, orthoslices, volume rendering, and more
- #BigDataViewer #BDV 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 imagej.net/plugins/bigstitcher
- #TrakEM2 for montaging in 2D and alinging in 3D collections of serial sections, typically from #vEM (volume electron microscopy) syn.mrc-lmb.cam.ac.uk/acardona
- #mpicbg libraries for extracting #SIFT and #MOPS features, then finding feature correspondences and estimating rigid and elastic transformation models 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 forum.image.sc/