![]() |
Compensating for patient motion constitutes a challenging as well as important problem for high precision cranial radiotherapy. Common approaches rely on patient immobilization using stereotactic frames, masks or bite bars, or employ X-ray based monitoring and motion compensation such as the 6D skull tracking used by the CyberKnife®. These techniques entail several drawbacks: First, the mask systems are rather inconvenient and also not tolerated by all patients. They further provide no motion monitoring during the treatment - the patient is assumed to be fixed. This is indeed only true up to errors in millimeter range. Second, X-ray based imaging exposes the subject to an unnecessary amount of additional radiation. This exposure also limits the head-tracking speed to about 1 Hz.
Therefore, marker-less optical head-tracking provides a promising alternative, where a laser constantly scans the patient's forehead. This approach requires only light patient fixation and provides a basis for fast real-time monitoring. While promising results have already been achieved using commercial systems such as the Microsoft Kinect®, the accuracy still lags behind the desirable standard of sub-millimeter accuracy. One major drawback of marker-less tracking is given by the lack of point-to-point correspondences. Finding these, for objects which are not strictly rigid, is challenging and prone to registration errors. Point cloud matching algorithms are used which rely, if at all, on a few spatial landmarks. The surface geometry very often introduces further ambiguities which lead to a convergence into local error minima and hence poor robustness.
Figure (1) Laser scanning optics, (2) Laser scan of the forehead, (3) MRI segmented tissue ground truth.
By combining expertise from the fields of computer science, electronics, applied mathematics, machine learning and biomedical optics our research group works on laser triangulation, dedicated electronic and optical hardware, as well as enhanced tracking approaches. Specifically the feasibility of optically detecting subcutaneous as well as cutaneous structures is evaluated. The structures serve as supportive landmarks and can be used to localize rigid cranial bone. To uncover these landmarks the developed system extracts optical backscatter features. These are obtained from near-infrared (NIR) laser scans of the forehead. Finally, machine learning algorithms such as Gaussian Processes or Support Vector regression are used to obtain the tissue thickness. In cooperation with Varian Medical, Inc., the world-leading manufacturer for LINACs, we develop a novel prototype for high-accuracy head-tracking in radiotherapy.
Figure (1) Triangulated 3D surface point cloud, (2) feature-labeled point cloud, (3) reconstructed tissue-labeled point cloud.
Relationship between NIR laser power and the human forehead tissue backscattering image features, in: Biophotonics: Photonic Solutions for Better Health Care VI, Strasbourg (France), pages 136, SPIE, 2018 | , and ,
![]() [DOI] [Bib|RIS] [URL] |
Deep Convolutional Neural Network Approach for Forehead Tissue Thickness Estimation from NIR Laser Backscattering Images, in: Proceedings of the 51st DGBMT Annual Conference, Dresden, Germany, pages submitted, 2017 | , and ,
[Bib|RIS] |
Patient identification using a near-infrared laser scanner, in: Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling, SPIE, Orlando, FL, pages 101352L, SPIE, 2017 | , , and ,
![]() [DOI] [Bib|RIS] |
Enhanced Optical Head Tracking for Cranial Radiotherapy: Supporting Surface Registration by Cutaneous Structures (2016), in: International Journal of Radiation Oncology, Biology, Physics, 95:2(810-817) | , , , , , , , , and ,
![]() [DOI] [Bib|RIS] |
A Study of Gaussian Noise Effects on Skin Thickness Measurement, in: Proceedings of the 49th DGBMT Annual Conference, Lübeck, Germany, pages S190, 2015 | , , , and ,
![]() [DOI] [Bib|RIS] |
An Approach to Improve Accuracy of Optical Tracking Systems in Cranial Radiation Therapy (2015), in: Cureus, 7:1(e239) | , , , , and ,
![]() [DOI] [Bib|RIS] |
Analysis of feature stability for laser-based determination of tissue thickness, in: Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XIII, San Francisco, CA, pages 93130Q, 2015 | , , , , and ,
![]() [DOI] [Bib|RIS] |
Calibration of galvanometric laser scanners using statistical learning methods, in: Bildverarbeitung für die Medizin, Berlin, Heidelberg, New York, pages 467-472, Springer, 2015 | , , , , , and ,
![]() [DOI] [Bib|RIS] |
Data-driven Learning for Calibrating Galvanometric Laser Scanners (2015), in: IEEE Sensors Journal, 15:10(5709-5717) | , , , and ,
![]() [DOI] [Bib|RIS] |
Efficient Estimation of Tissue Thicknesses using Sparse Approximation for Gaussian Processes, in: 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC '15), EMBS, Milano, Italy, pages 7015-7018, IEEE, 2015 | , , , and ,
![]() [DOI] [Bib|RIS] |
Enhanced Tissue Thickness Computation by Exploiting Local Neighborhoods, in: Proceedings of the 29th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS'15), Barcelona, Spain, 2015 | , , , , and ,
![]() [Bib|RIS] |
Enriching 3D optical surface scans with prior knowledge: tissue thickness computation by exploiting local neighborhoods (2015), in: International Journal of Computer Assisted Radiology and Surgery, 11:4(569-579) | , , , , and ,
![]() [DOI] [Bib|RIS] |
Optical localization of the human skull for cranial radiation therapy, in: Varian Research Partnership Symposium, Varian Medical, 2015 | , , , , and ,
[Bib|RIS] |
Ray Interpolation for Generic Triangulation Based on a Galvanometric Laser Scanning System, in: 2015 IEEE International Symposium on Biomedical Imaging, New York, pages 1419-1422, IEEE, 2015 | , , , , and ,
![]() [DOI] [Bib|RIS] |
Tissue Segmentation from Head MRI: A Ground Truth Validation for Feature-Enhanced Tracking, in: Proceedings of the 49th DGBMT Annual Conference, Lübeck, Germany, pages S184, 2015 | , , , and ,
![]() [DOI] [Bib|RIS] |
Tissue segmentation from head MRI: a ground truth validation for feature-enhanced tracking (2015), in: Current Directions in Biomedical Engineering, 1:1(228-231) | , , , and ,
![]() [DOI] [Bib|RIS] |
A comparison of different hardware design approaches for feature-supported optical tracking with respect to angular dependencies, in: 56th Annual Meeting of the AAPM, pages 204, 2014 | , , , , and ,
![]() [DOI] [Bib|RIS] |
Accuracy analysis for triangulation and tracking based on time-multiplexed structured light (2014), in: Medical Physics, 41:8(082701) | , , , , and ,
[DOI] [Bib|RIS] |
Angle influence and compensation for marker-less head tracking based on laser scanners, in: Proceedings of the 28th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS'14), Fukuoka, Japan, pages 62-63, 2014 | , , , , and ,
![]() [Bib|RIS] |
Kalman Filter based Head Tracking for Cranial Radiation Therapy with low-cost Range-Imaging Cameras, in: Bildverarbeitung für die Medizin 2014, Aachen, Germany, pages 324-329, Springer, 2014 | , , and ,
![]() [DOI] [Bib|RIS] |
Measuring cranial soft tissue thickness with MRI or pressure-compensated tracked ultrasound (2014), in: British Journal of Medicine and Medical Research, 4:4(937-948) | , , , , and ,
![]() [Bib|RIS] |
Tissue Thickness Estimation for High Precision Head-Tracking using a Galvanometric Laser Scanner - A Case Study, in: 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC '14), EMBS, Chicago, IL, pages 3106-3109, IEEE, 2014 | , , , , , and ,
![]() [Bib|RIS] |
Accuracy of object tracking based on time-multiplexed structured light, in: 12. Jahrestagung der Deutschen Gesellschaft für Computer- und Roboterassistierte Chirurgie (CURAC), CURAC, Innsbruck, Austria, pages 139-142, 2013 | , , , , and ,
![]() [Bib|RIS] |
An improvement for the scanning process in high accuracy head tracking, in: 12. Jahrestagung der Deutschen Gesellschaft für Computer- und Roboterassistierte Chirurgie (CURAC), CURAC, Innsbruck, Austria, pages 179-182, 2013 | , , , , and ,
![]() [Bib|RIS] |
Design and evaluation of a highly accurate optical setup for backscatter analysis, in: 44. Jahrestagung der DGMP, DGMP, Cologne, Germany, pages 181-186, 2013 | , , , , and ,
![]() [Bib|RIS] |
Estimating soft tissue thickness from light-tissue interactions\textemdash a simulation study (2013), in: Biomedical Optics Express, 4:7(1176-1187) | , , and ,
![]() [DOI] [Bib|RIS] |
Für mehr Präzision in der Tumorbestrahlung (2013), in: Lübecker Nachrichten | ,
![]() [Bib|RIS] [URL] |
Preliminary Study on Optical Feature Detection for Head Tracking in Radiation Therapy, in: 13th IEEE International Conference on BioInformatics and BioEngineering (BIBE), IEEE, Chania, Greece, pages 1-5, 2013 | , , , , and ,
![]() [DOI] [Bib|RIS] |
Real time contact-free and non-invasive tracking of the human skull\textemdash first light and initial validation, in: Applications of Digital Image Processing XXXVI, San Diego, CA, pages 88561G-1 - 88561G-8, 2013 | , , , , and ,
[DOI] [Bib|RIS] |
Skin measurements improve motion tracking, medicalphysicsweb.org, 2013 | ,
![]() [Bib|RIS] [URL] |
Skin thickness estimation for high precision optical head tracking during cranial radiation therapy\textemdash a simulation study, in: Proceedings of the 55th Annual Meeting of the {ASTRO}, ASTRO, Atlanta, GA, USA, pages S669, 2013 | , and ,
![]() [DOI] [Bib|RIS] |
Time-multiplexed structured light for head tracking, in: 44. Jahrestagung der DGMP, DGMP, Cologne, Germany, pages 199-202, 2013 | , , , , and ,
![]() [Bib|RIS] |
Estimation of error sources for optical head tracking in cranial radiation therapy, in: 11. Jahrestagung der Deutschen Gesellschaft für Computer- und Roboterassistierte Chirurgie (CURAC), CURAC, 2012 | , , , , and ,
![]() [Bib|RIS] |