From Pixels to Patterns – Machine Learning for Advanced Image Analysis

From Pixels to Patterns: Applying Machine Learning Tools for Advanced Image Analysis

Introduction

Software Installation

Cellpose installation

Recommended Installation of Miniforge3 and Cellpose3

Alternative Miniconda3 and Cellpose3 installation (NOT recommended)

Ilastik Installation

Fiji Installation and Configuration

Example Image Download

Basics on Machine Learning for Image Segmentation

Introduction to Image Segmentation

Shallow vs. Deep Machine Learning

Important Considerations when using ML Tools

Good Scientific Practice in ML/DL

Pixel Classification (using ilastik)

RGB Image Segmentation and Analysis

RGB Image Segmentation

Batch Processing in ilastik

Analyzing Pixel-Classified Areas in Fiji

Ilastik Configuration in Fiji

Run Ilastik Workflow in Fiji

Combine Pixel and Object Classification

Semantic Object Segmentation (Cells)

Object Classification (including Instance Segmentation)

Batch Processing in Ilastik & Analysis in Fiji

Star-Convex Object Detection in Fiji (fluorescent and RGB)

Introduction to StarDist

Star-Convex Object Segmentation

Combining StarDist and ilastik

Extracting Positive Stain Area

Extracting Nuclei from a IHC-Staining

Analyzing Positive/Negative Ratio of Objects

Automation - StarDist and ilastik in Fiji

Quality Control Metrics

Introduction to Quality Control in Fiji

Cellpose - Deep Learning for Everybody

Introduction to Cellpose

Improving Cellpose with human-in-the-loop Training

Image Restoration in Cellpose (optional)

Combining Cellpose and ilastik

Object Detection and Batch Processing with Cellpose via Fiji

Ilastik Object Classification from Cellpose Instances

Combining Cellpose and Ilastik via Fiji

3D Image Segmentation

General Considerations for 3D Segmentation

3D Segmentation in Fiji (non-ML) and Ilastik

3D Cellpose

Tracking in Fiji using ML/DL Object Detection

Tracking in Fiji with ML/DL algorithms

Bonus - Cellpose 4

Cellpose 4 Installation

Cellpose 4.0.4 Overview

From Pixels to Patterns

Introduction

Course Overview

The Trainer

Dr. Jan Brocher - BioVoxxel

BioVoxxel was founded in 2012 by Dr. Jan Brocher and since then offers widely accepted individualized workshops in image proper image integrity and publication figure creation, image analysis and analysis automation for undergraduates, PhD students and PostDocs in life sciences worldwide.

These courses understandably transmit in-depth methodologies according to high scientific standards to enable researchers to successfully apply those to solve individual image analysis challenges and create publication figures efficiently.

Besides teaching, BioVoxxel offers customized trainings, 1:1-coaching sessions, automated solutions and customized programming of image processing and analyses tools challenges for customers as well as scientific illustration services.

Expertise

Bio-Image Analyst with expertise in scientific image analysis since 2010
Until 2025 over 400 live workshops for over 5000 students delivered
PhD in Molecular Biology
10 years experience in international academic science
Experience in very diverse light microscopy techniques
Professional teaching as freelance scientific trainer since 2012
Scientific image analysis software developer since 2013
Bio-Image analysis consultant for academia and industry since 2013
Programming experience: IJ Macro, Java, Groovy, Python

This courses teaches you the proper usage of open source scientific image analysis tools but it would not be possible without the tools themselfs and the great masterminds behind those tools that foster the constantly updated possibilities in the huge universe of scientific image analysis.

Further more, it is not for granted that those publically funded tools are handed for free to the community and to scientists, since a huge amount of money originating from different science funding grants and organizations are involved in the development of such software.

Please give something back by properly citing those tools if you use them for your image analysis to produce published results.

Fiji

Schindelin, J., Arganda-Carreras, I., Frise, E., Kaynig, V., Longair, M., Pietzsch, T., … Cardona, A. (2012). Fiji: an open-source platform for biological-image analysis. Nature Methods, 9(7), 676–682. doi:10.1038/nmeth.2019
Schneider, C. A., Rasband, W. S., & Eliceiri, K. W. (2012). NIH Image to ImageJ: 25 years of image analysis. Nature Methods, 9(7), 671–675. doi:10.1038/nmeth.2089

StarDist

Martin Weigert and Uwe Schmidt.
Nuclei Instance Segmentation and Classification in Histopathology Images with Stardist.
The IEEE International Symposium on Biomedical Imaging Challenges (ISBIC), Kolkata, India, March 2022.
Martin Weigert, Uwe Schmidt, Robert Haase, Ko Sugawara, and Gene Myers.
Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy.
The IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass Village, Colorado, March 2020.
Uwe Schmidt, Martin Weigert, Coleman Broaddus, and Gene Myers.
Cell Detection with Star-convex Polygons.
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Granada, Spain, September 2018.

ilastik

ilastik: interactive machine learning for (bio)image analysis
Stuart Berg, Dominik Kutra, Thorben Kroeger, Christoph N. Straehle, Bernhard X. Kausler, Carsten Haubold, Martin Schiegg, Janez Ales, Thorsten Beier, Markus Rudy, Kemal Eren, Jaime I Cervantes, Buote Xu, Fynn Beuttenmueller, Adrian Wolny, Chong Zhang, Ullrich Koethe, Fred A. Hamprecht & Anna Kreshuk
in: Nature Methods, (2019) Link at publisher

Cellpose

Stringer, C., Wang, T., Michaelos, M., & Pachitariu, M. (2021). Cellpose: a generalist algorithm for cellular segmentation. Nature methods, 18(1), 100-106.
Pachitariu, M. & Stringer, C. (2022). Cellpose 2.0: how to train your own model. Nature methods, 1-8.
Stringer, C. & Pachitariu, M. (2025). Cellpose3: one-click image restoration for improved segmentation. Nature Methods.
Pachitariu, M., Rariden, M., & Stringer, C. (2025). Cellpose-SAM: superhuman generalization for cellular segmentation. bioRxiv.

TrackMate

Ershov, D., Phan, M.-S., Pylvänäinen, J. W., Rigaud, S. U., Le Blanc, L., Charles-Orszag, A., … Tinevez, J.-Y. (2022). TrackMate 7: integrating state-of-the-art segmentation algorithms into tracking pipelines. Nature Methods, 19(7), 829–832. doi:10.1038/s41592-022-01507-1
Tinevez, J.-Y., Perry, N., Schindelin, J., Hoopes, G. M., Reynolds, G. D., Laplantine, E., … Eliceiri, K. W. (2017). TrackMate: An open and extensible platform for single-particle tracking. Methods, 115, 80–90. doi:10.1016/j.ymeth.2016.09.016

Mask instant Comparator (MiC)