Overview

ImFusion Labels is a software designed to ease the workflow of medical image annotation for further algorithm development. In particular, it provides a user-friendly way of

• managing a database of images coming from multiple sources,

• annotating or segmenting images, volumes or even sequences in a few clicks,

• exporting all annotations in a standardized way (for instance to train a machine learning model),

• running your own experiments and easily visualizing the results on the whole database.

The key advantages of ImFusion Labels over other solutions include

• its genericity since it is not restricted to a particular modality of clinical applications,

• the support of a large variety of data format, including DICOM images,

• a toolset of segmentation algorithms that have been designed to be fast and powerful,

• Python integration, enabling users to write their own algorithms to label data

• powerful and customizable visualization of data and their annotation,

• the possibility to easily define post-processing (resampling, orientation normalization, data augmentation, etc.) before exporting the database,

• the access to the ImFusion Suite algorithms within the ImFusion Python module