AI Rad Companion webinar headerimage

Deep learning-based autocontouring

Organs-at-risk contouring in radiation therapy for various clinical environments

Accurate contouring of organs-at-risk (OAR) is one of the major bottlenecks of radiation therapy planning, but still the necessary first step in the process. Therefore, the increase in the number of patients puts significant pressure on radiation therapy staff responsible for consistent OAR contouring results. Advances in technology and artificial intelligence can help automate repetitive tasks such as OAR contouring, thus reduce workload, and standardize key CT simulation steps.

Learn more about automated organs-at-risk contouring solutions in radiation therapy for various clinical environments.

With AI-Rad Companion Trial Light1 you can easily experience the quality of our algorithms – directly via your browser and without any installation effort.

Clinical Use

Our deep learning-based autocontouring solutions enable precise organs-at-risk contouring in radiation therapy. They provide consistent results as a starting point for treatment: 

>95% of the contouring results are clinically usable or require minor edits2.

The value of AI-based autocontouring

deep learning-based autocontouring


Deep learning-trained organs-at-risk contouring for increased quality and consistency in radiation oncology.

Courtesy of Universitätsklinikum Erlangen, Germany

autocontouring radiotherapy


Improve workflow efficiency to free up resources from routine delineating tasks in radiation oncology.

Courtesy of Radiologische Allianz Hamburg, Germany

artificial intelligence in radiotherapy


Seamless integration into the daily radiation oncology treatment planning workflow.

Eclipse version 17.0 was used to display the autocontouring results.

AI-based autocontouring: Efficiency and automation throughout the radiation therapy planning process.

With AI-based autocontouring and EclipseTM we enable you to reach efficiency and automation throughout the planning process. The contouring of the organs at risk is done automatically with the support of deep learning algorithms. It may reduce unwarranted variations with high-quality contours that approach the level of consensus-based contours.9

Features & Benefits


We follow international and RTOG guidelines to train our deep learning algorithms for organs-at-risk contouring: