Do you want to experience the power of AI?
With AI-Rad Companion Trial Light1 you can easily experience the quality of our algorithms – directly via your browser and without any installation effort.
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.
Clinical Use
Why AI-based autocontouring?
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.
Challenges of manual organs-at-risk contouring
Organs-at-risk (OAR) contouring creates a substantial amount of effort and is a major source of variability in radiation therapy planning. Modern treatment techniques rely on consistent OAR contours as a starting point. The time spent on OAR contouring keeps staff from focusing on clinical tasks like devising an optimal treatment plan.
/
Courtesy of University Hospital Groningen, Netherlands
The quality of autocontouring depends on the quality of the CT images
- Suboptimal image quality leads to suboptimal autocontouring3,4 that needs to be modified or re-done
- Radiation oncology professionals have no consistent starting point for RT planning
/
The value of AI-based autocontouring
Consistency
Deep learning-trained organs-at-risk contouring for increased quality and consistency in radiation oncology.
Courtesy of Universitätsklinikum Erlangen, Germany
Efficiency8
Improve workflow efficiency to free up resources from routine delineating tasks in radiation oncology.
Courtesy of Radiologische Allianz Hamburg, Germany
Accessibility
Seamless integration into the daily radiation oncology treatment planning workflow.
Eclipse version 17.0 was used to display the autocontouring results.
Autocontouring solutions for various clinical environments
Features & Benefits
Clinical outcomes
Guidelines
We follow international and RTOG guidelines to train our deep learning algorithms for organs-at-risk contouring:
- Head & neck OAR: International consensus, Brouwer et al., 2015
- Head & neck lymph nodes: International consensus, Gregoire et al., 2014
- Thoracic OAR: RTOG guideline, Kong et al., 2011
- Pelvic OAR: RTOG guideline, Gay et al., 2012
- Pelvic lymph nodes: RTOG guideline, Lawton et al., 2009
Testimonials
Hear what our customers say11:
Automatic contouring helps to increase precision which is highly beneficial for patients.
Centre de Cancérologie du Grand Montpellier (CCGM), France
The term autocontouring in this context means automated contouring of organs-at-risk structures.
The products/features (mentioned herein) are not commercially available in all countries. Their future availability cannot be guaranteed.
1
For demo purposes only. Please note that AI-Rad Companion Trial Light may not provide the full functionality of the released medical device.
2
The case evaluation was conducted with AI-Rad Companion Organs RT. Clinical data provided by Hopsital Montpellier. The results by Siemens Healthineers' customer described herein are based on results that were achieved in the customers' unique setting. Since there is no "typical" hospital and many variables exist (e.g., hospital size, case mix, level of IT adoption) there can be no guarantee that other customers will achieve the same results.
3
Wu X, Udupa JK, Odhner D et al. Knowledge-Based Auto Contouring for Radiation Therapy: Object Definitions, Ground Truth Delineations, Object Quality, and Image Quality. Int J Radiat Oncol Biol Phys. 2017; 99 (2): E740
4
Cheung CW, Leung KY, Lam WW et al. Application of Model-based Iterative Reconstruction in Auto-contouring of Head and Neck Cases. Scientific Informal (Poster) Presentation at: LL-ROS-TH Radiation Oncology and Radiobiology Lunch Hour CME Posters; 2012 Nov 29; Chicago, IL
5
Radiation Oncology Incident Learning System, Aggregate Report Patient, Safety Work Product, Q4, 2017
6
IAEA, Radiotherapy in Cancer Care: Facing the Global Challenge, 2017
7
J Van der Veen, A Gulyban, S Willems, F Maes, S Nuyts, Interobserver variability in organ at risk delineation in head and neck cancer, 2021
8
Rendering is based on research results that are not commercially available. Future availability cannot be guaranteed.
9
AI-Rad Companion Organs RT and Eclipse are two independent medical devices having individual intended purposes and must/should not considered as a system.
10
The case evaluation was conducted with Organs RT on syngo.via RT Image Suite.
11
The statements by Siemens Healthineers’ customers described herein are based on results that were achieved in the customer's unique setting. Because there is no “typical” hospital or laboratory and many variables exist (e.g., hospital size, samples mix, case mix, level of IT and/or automation adoption) there can be no guarantee that other customers will achieve the same results.
Dr. Mourtada, Dr. Alexandros Papchristofilou, Dr. Manuel Algara López, Stephane Muraro, Dr. Olivier Lauche, Prof. Dr. Oliver Ott, and Dr. Christian Grehn are employed by institutions that receive financial support from Siemens Healthineers for collaborations.
Dr. Mourtada, Dr. Alexandros Papchristofilou, Dr. Manuel Algara López, Stephane Muraro, Dr. Olivier Lauche, Prof. Dr. Oliver Ott, and Dr. Christian Grehn are employed by institutions that receive financial support from Siemens Healthineers for collaborations.
