Enhanced Optical Head Tracking for Cranial Radiation Therapy: Supporting Surface Registration by Cutaneous Structures

Wissel, Tobias; Stüber, Patrick; Wagner, Benjamin; Bruder, Ralf; Erdmann, Christian; Deutz, Christin-Sophie; Sack, Benjamin; Manit, Jirapong; Schweikard, Achim; Ernst, Floris

doi:10.1016/j.ijrobp.2016.01.041

Cited by 8 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate and compare the tissue thickness estimation accuracy of this CNN model, the dataset we used in this experiment was the same dataset that was acquired from the experiment in [3]. This dataset was collected by the laserbased head tracking system from 30 healthy subjects; 16 …”

Section: Data Acquisitionmentioning

confidence: 99%

“…Our previous research showed that with support vector machine regression (SVR) or Gaussian processes (GP) estimation by using combined features (image data, incident angle and neighbourhood features), it is possible to determine tissue thickness with RMSE of 0.217 mm and 0.1140 mm, respectively [3]. These previous learning methods, however, require the user, to manually define the learning features [3,4], which may not be good enough for this application.…”

Section: Introductionmentioning

confidence: 99%

“…These previous learning methods, however, require the user, to manually define the learning features [3,4], which may not be good enough for this application. Although the GP algorithm has shown good performance, its complexity of limited the training on training sets with a large size.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep convolutional neural network approach for forehead tissue thickness estimation

Manit

Schweikard

Ernst

2017

Current Directions in Biomedical Engineering

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper, we presented a deep convolutional neural network (CNN) approach for forehead tissue thickness estimation. We use down sampled NIR laser backscattering images acquired from a novel marker-less near-infrared laserbased head tracking system, combined with the beam's incident angle parameter. These two-channel augmented images were constructed for the CNN input, while a single node output layer represents the estimated value of the forehead tissue thickness. The models were -separately for each subject -trained and tested on datasets acquired from 30 subjects (high resolution MRI data is used as ground truth). To speed up training, we used a pre-trained network from the first subject to bootstrap training for each of the other subjects. We could show a clear improvement for the tissue thickness estimation (mean RMSE of 0.096 mm). This proposed CNN model outperformed previous support vector regression (mean RMSE of 0.155 mm) or Gaussian processes learning approaches (mean RMSE of 0.114 mm) and eliminated their restrictions for future research.

show abstract

Section: Data Acquisitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep convolutional neural network approach for forehead tissue thickness estimation

Manit

Schweikard

Ernst

2017

Current Directions in Biomedical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Markerless approaches to this task employ, for example, structured light [3] or time-of-flight cameras [4]. Extending point cloud models with additional information, such as tissue thickness estimation, has been proposed [5]. Another application for head tracking in medicine is robotic transcranial magnetic stimulation (rTMS).…”

Section: Introductionmentioning

confidence: 99%

Concept for Markerless 6D Tracking Employing Volumetric Optical Coherence Tomography

Schlüter

Glandorf

Gromniak

et al. 2020

Sensors

View full text Add to dashboard Cite

Optical tracking systems are widely used, for example, to navigate medical interventions. Typically, they require the presence of known geometrical structures, the placement of artificial markers, or a prominent texture on the target’s surface. In this work, we propose a 6D tracking approach employing volumetric optical coherence tomography (OCT) images. OCT has a micrometer-scale resolution and employs near-infrared light to penetrate few millimeters into, for example, tissue. Thereby, it provides sub-surface information which we use to track arbitrary targets, even with poorly structured surfaces, without requiring markers. Our proposed system can shift the OCT’s field-of-view in space and uses an adaptive correlation filter to estimate the motion at multiple locations on the target. This allows one to estimate the target’s position and orientation. We show that our approach is able to track translational motion with root-mean-squared errors below 0.25 mm and in-plane rotations with errors below 0.3°. For out-of-plane rotations, our prototypical system can achieve errors around 0.6°.

show abstract

“…These images are utilized for registration of bony or soft tissue landmarks, implanted fiducials, or surrogates such as bite blocks or reflective markers. Other imaging systems used in humans, such as enhanced optical surface tracking, surface guided radiation therapy, and four‐dimensional CT, or MRI‐based intensity‐modulated radiation therapy have yet to be reported in veterinary radiation therapy. The popularity of onboard imaging and image‐guided radiotherapy, along with the introduction of advanced six‐degrees‐of‐freedom image registration technique, has seen increased registration accuracy in not only the translational planes x , y , and z but also in the rotational planes of pitch, roll, and yaw (Figure ).…”

Section: Introductionmentioning

confidence: 99%

The Elekta Fraxion™ system is not suitable for maxillary fixation in canine conformal radiation therapy techniques

Yu¹,

Morrow

Moutrie

et al. 2019

Vet Radiology Ultrasound

View full text Add to dashboard Cite

In this prospective, exploratory study, we evaluated the positioning accuracy in a group of 15 dogs undergoing fractionated stereotactic radiotherapy for tumors affecting the head, using a modified human maxillary fixation device (Elekta Fraxion TM system). Positioning was assessed using on-board volumetric imaging, with a six-degrees-of-freedom image registration technique. Prior to treatment delivery, CBCT images were obtained and patient alignment was corrected, in both translational and rotational planes, using a six-degrees-of-freedom robotic patient positioning system (HexaPOD Evo RT System). The maximum angular inter-fraction motions observed were 6.1 • (yaw), 10.9 • (pitch), and 4.5 • (roll). The mean systematic translational errors were 4.7, 2.6, and 2.3 mm, mean random translational errors were 3.0, 2.2, and 2.5 mm, and mean overall translational errors were 2.4, 0.7, and 2.3 mm in the cranial-caudal, lateral, and dorsal-ventral directions, respectively. The mean systematic rotational errors were 1.17 • , 0.77 • , and 1.43 • , the mean rotational random errors were 1.65 • , 1.46 • , and 1.34 • and the mean overall rotational errors were 0.56 • , 0.22 • , and 0.29 • in the yaw, pitch, and roll directions, respectively. The mean error of the three-dimensional vector was 6.9 mm with a standard deviation of 3.8 mm. Ninety-five percent of the three-dimensional vectors were <14.8 mm. This study demonstrates that this maxillary fixation device relies on six-degrees-of-freedom registration and an ability to apply corrections using a six-degrees-of-freedom couch for accurate patient positioning and tumor targeting. Its use in conformal radiation therapy in dogs is not recommended. K E Y W O R D Sbrain tumor, nasal tumor, oncology, oral tumor, radiation therapy

show abstract

Enhanced Optical Head Tracking for Cranial Radiation Therapy: Supporting Surface Registration by Cutaneous Structures

Cited by 8 publications

References 19 publications

Deep convolutional neural network approach for forehead tissue thickness estimation

Deep convolutional neural network approach for forehead tissue thickness estimation

Concept for Markerless 6D Tracking Employing Volumetric Optical Coherence Tomography

The Elekta Fraxion™ system is not suitable for maxillary fixation in canine conformal radiation therapy techniques

Contact Info

Product

Resources

About