System for annotating X-ray images and generating pathologies

Developing software in the field of medicine is a complex task, as the sector is heavily regulated by various laws and is highly formalized in nature. However, there is a large number of annotation software tools available for healthcare professionals that they use on a daily basis. Nevertheless, a significant part of such software may not always comply with legislation, for example, in terms of refusing to store patient data on servers located on the territory of a particular country. Some software also fails to meet specific functional requirements. Such software can be less intuitive for both young professionals, older specialists, and students. Consequently, valuable time has to be spent on learning the interface, which could have been used more efficiently.

The main goal of the project was the development of a cloud-based web platform with multi-user access, enabling healthcare professionals to work with X-ray studies within a unified environment. The platform allows users to work with original, annotated, and artificially generated studies.

The functionality available to a physician depends on their role in the system. The development had two stages:

1. Development of an annotation module, which allows physicians to collaborate on studies.
2. Development of a synthetic study generator, enabling the creation of synthetic (artificial) studies that can be used for training future doctors and for creating datasets for training specialized neural networks.

What we did

1. Cloud-based web platform with multi-user access
2. Toolset for X-ray image annotation
3. Capability to upload, store, and download data
4. Functionality for collaborative user work
5. Pathology generator, which uses neural networks to create pathologies on an image of a healthy lung based on specified parameters.