An Approach to Improve Accuracy of Optical Tracking Systems in Cranial Radiation Therapy

Stüber, Patrick; Wagner, Benjamin; Wissel, Tobias; Bruder, Ralf; Schweikard, Achim; Ernst, Floris

doi:10.7759/cureus.239

Cited by 2 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stüber et al . [22] introduced the NIR laser‐based forehead scanning device to minimise the risks by precisely tracking a patient's head position during the treatment and output the motion vectors, as feedback information to the radiotherapy device to synchronously adjust the radiation beam trajectory.…”

Section: Methodsmentioning

confidence: 99%

“…Patient head motion is a very critical issue in cranial radiotherapy because a small head position drift may cause the treatment target to be missed, which could lead to undesired side effects on the patient. Stüber et al [22] introduced the NIR laser-based forehead scanning device to minimise the risks by precisely tracking a patient's head position during the treatment and output the motion vectors, as feedback information to the radiotherapy device to synchronously adjust the radiation beam trajectory.…”

Section: Forehead Scanning Systemmentioning

confidence: 99%

See 1 more Smart Citation

Human forehead recognition: a novel biometric modality based on near‐infrared laser backscattering feature image using deep transfer learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

Human recognition systems are an essential tool for identity verification. Though various parts of the human body have been widely used as input data for decades, developing new biometric technology is still necessary to enhance the security system complexity. This article presents a novel biometric modality based on forehead feature images acquired from a specially designed near-infrared laser scanning system. The authors selected state-of-the-art deep convolutional neural networks (CNN), including VGGNet, ResNet, and Inception-v3, to demonstrate the human forehead recognition task. Though large-scale training data is generally required for learning a promising CNN model, they showed the feasibility to transfer the feature representation knowledge of the networks that were pre-trained on the data from a different domain and fine-tuned the target network on the limited dataset of forehead feature images. This transfer learning approach establishes the usability of human forehead recognition and allows us to implement this biometric modality for real-world application.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Forehead Scanning Systemmentioning

confidence: 99%

Human forehead recognition: a novel biometric modality based on near‐infrared laser backscattering feature image using deep transfer learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Instead of prohibiting the patient from moving, we have proposed a novel marker-less near-infrared laser base system to tack the patient's head [2]. This tracking system utilises an 850nm laser beam to obtain the 3D forehead geometry, and uses a machine learning algorithm to estimate the underlying tissue thickness (see Figure ).…”

Section: Introductionmentioning

confidence: 99%

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

An Approach to Improve Accuracy of Optical Tracking Systems in Cranial Radiation Therapy

Cited by 2 publications

References 7 publications

Human forehead recognition: a novel biometric modality based on near‐infrared laser backscattering feature image using deep transfer learning

Human forehead recognition: a novel biometric modality based on near‐infrared laser backscattering feature image using deep transfer learning

Deep convolutional neural network approach for forehead tissue thickness estimation

Contact Info

Product

Resources

About