A practical demonstration of DeepMIB – a user-friendly and open-source software for training of deep learning network for biological image segmentation

Electrons – Problem Solver Session 15:35 – 16:15 (Sydney Time) | Wednesday 17 Feb 2020


Deep learning approaches are highly sought after solutions for coping with large amounts of collected datasets and are expected to become an essential part of imaging workflows. However, in most cases, deep learning is still considered as a complex task that only image analysis experts can master. Here, I present DeepMIB, a new software package that is capable of training convolutional neural networks for segmentation of multidimensional microscopy datasets on any workstation.

In my presentation, I will demonstrate practical application of DeepMIB for segmentation of 2D and 3D electron microscopy datasets. DeepMIB is distributed as both an open-source multi-platform Matlab code and as compiled standalone application for Windows and MacOS. It comes in a single package that is simple to install and use as it does not require knowledge of programming. DeepMIB is suitable for everyone interested of bringing a power of deep learning into own image segmentation workflows.


Dr Ilya Belevich

Dr Ilya Belevich

Senior Researcher Electron Microscopy Unit (EMBI) Institute of Biotechnology University of Helsinki, Finland

Dr. Ilya Belevich is a senior researcher at the Electron Microscopy Unit, Institute of Biotechnology at the University of Helsinki, Finland. He graduated in biophysics at the Biological Department, Lomonosov’s Moscow State University, Russia (1999) and obtained a PhD from the University of Helsinki in the lab of Prof. Mårten Wikström studying molecular mechanisms of cytochorome c oxidase functioning. As a postdoctoral researcher, he first continued studies of cytochrome oxidase with Michael Verkhovsky at the University of Helsinki until in 2010 joined the lab of Eija Jokitalo at the Electron Microscopy Unit. His current research is focused on various aspects of 3D imaging by serial block face scanning electron microscopy and development of open-source tools (as an example, Microscopy Image Browser) and methods for efficient segmentation and analysis of multidimensional dataset from both light and electron microscopy.