# DeepMIB: User-friendly and open-source software for training of deep learning network for biological image segmentation

## TL;DR

DeepMIB is a user-friendly, open-source tool that simplifies training deep learning models for segmenting biological images in 2D and 3D.

## Contribution

DeepMIB introduces a multi-platform, standalone application for training deep learning models without programming knowledge.

## Key findings

- DeepMIB successfully segments 2D and 3D electron and multicolor light microscopy datasets.
- The software is distributed as open-source code and a standalone application for multiple operating systems.
- It enables non-experts to use deep learning for image segmentation workflows.

## Abstract

We present DeepMIB, a new software package that is capable of training convolutional neural networks for segmentation of multidimensional microscopy datasets on any workstation. We demonstrate its successful application for segmentation of 2D and 3D electron and multicolor light microscopy datasets with isotropic and anisotropic voxels. We distribute DeepMIB as both an open-source multi-platform Matlab code and as compiled standalone application for Windows, MacOS and Linux. 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.

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. With DeepMIB we address this problem and provide the community with a user-friendly and open-source tool to train convolutional neural networks and apply them to segment 2D and 3D grayscale or multi-color datasets.