Temporal regularization of ultrasound-based liver motion estimation for image-guided radiation therapy

O’Shea, Tuathan; Bamber, Jeffrey C.; Harris, Emma

doi:10.1118/1.4938582

Cited by 19 publications

(26 citation statements)

References 23 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultrasound guided radiation therapy of the liver and pancreas are also currently under investigation. 25 Further work will investigate the dosimetric effect of the probe if it is positioned on the abdomen during radiotherapy.…”

Section: Discussionmentioning

confidence: 99%

Monte Carlo investigation of the dosimetric effect of the Autoscan ultrasound probe for guidance in radiotherapy

Martyn

O’Shea²,

Harris³

et al. 2016

Medical Imaging 2016: Ultrasonic Imaging and Tomography

Self Cite

View full text Add to dashboard Cite

The aim of this study was to quantify the dosimetric effect of the Autoscan TM ultrasound probe, which is a 3D transperineal probe used for real-time tissue tracking during the delivery of radiotherapy. CT images of an anthropomorphic phantom, with and without the probe placed in contact with its surface, were obtained (0.75 mm slice width, 140 kVp). CT datasets were used for relative dose calculation in Monte Carlo simulations of a 7-field plan delivered to the phantom. The Monte Carlo software packages BEAMnrc and DOSXYZnrc were used for this purpose. A number of simulations, which varied the distance of the radiation field edge from the probe face (0 mm to 5 mm), were performed. Perineal surface doses as a function of distance from the radiation field edge, with and without the probe in place, were compared. The presence of the probe was found to result in an increase in perineal surface dose, relative to the maximum dose. The maximum increase in surface dose was 18.15%, at a probe face to field edge distance of 0 mm. However increases in surface dose fall-off rapidly as this distance increases, agreeing within Monte Carlo simulation uncertainty at distances ≥ 5 mm. Using data from three patient volunteers, a typical probe face to field edge distance was calculated to be ≈20 mm. Our results therefore indicate that the presence of the probe is unlikely to adversely affect a typical patient treatment, since the dosimetric effect of the probe is minimal at these distances.

show abstract

Section: Discussionmentioning

confidence: 99%

Monte Carlo investigation of the dosimetric effect of the Autoscan ultrasound probe for guidance in radiotherapy

Martyn

O’Shea²,

Harris³

et al. 2016

Medical Imaging 2016: Ultrasonic Imaging and Tomography

Self Cite

View full text Add to dashboard Cite

show abstract

“…As was evaluated in work by O'Shea et al ,. 2.0 mm was used as tracking accuracy threshold, successful tracking was observed for all of the tracking landmarks, with 1.94 mm being the worst tracking error observed.…”

Section: Resultsmentioning

confidence: 99%

Attention‐aware fully convolutional neural network with convolutional long short‐term memory network for ultrasound‐based motion tracking

Huang

Lü

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Purpose One of the promising options for motion management in radiation therapy (RT) is the use of LINAC‐compatible robotic‐arm‐mounted ultrasound imaging system due to its high soft tissue contrast, real‐time capability, absence of ionizing radiation, and low cost. The purpose of this work is to develop a novel deep learning‐based real‐time motion tracking strategy for ultrasound image‐guided RT. Methods The proposed tracker combined the attention‐aware fully convolutional neural network (FCNN) and the convolutional long short‐term memory network (CLSTM) that is end‐to‐end trainable. The glimpse sensor module was built inside the attention‐aware FCNN to discard majority of background by focusing on a region containing the object of interest. FCNN extracted discriminating spatial features of glimpse to facilitate temporal modeling for CLSTM. The saliency mask computed from CLSTM refined the features particular to the tracked landmarks. Moreover, the multitask loss strategy including bounding box loss, localization loss, saliency loss, and adaptive loss weighting term was utilized to facilitate training convergence and avoid over/underfitting. The tracker was tested on the databases provided by MICCAI 2015 challenges, and the ground truth data were obtained with the help of brute force‐based template matching technology. Results The mean tracking error of 0.97 ± 0.52 mm and maximum tracking error of 1.94 mm were observed for 85 point landmarks across 39 ultrasound cases compared to the ground truth annotations. The tracking speed per frame per landmark with the GPU implementation ranged from 66 and 101 frames per second, which largely exceeded the ultrasound imaging rate. Conclusion The results demonstrated the robustness and accuracy of the proposed deep learning‐based motion estimation, despite the existence of some known shortcomings of ultrasound imaging such as speckle noise. The tracking speed of the system was found to be remarkable, sufficiently fast for real‐time applications in RT environment. The approach provides a valuable tool to guide RT treatment with beam gating or multileaf collimator (MLC) tracking in real time.

show abstract

“…Currently, US‐guided IMRT is mainly used in clinics to treat prostate and breast cancer . US‐guided targeting of the liver in RT has been recently investigated . However, during therapy fractions, liver tumors are not necessarily visible in US images.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of 2D and 3D ultrasound tracking algorithms and impact on ultrasound‐guided liver radiotherapy margins

et al. 2018

View full text Add to dashboard Cite

Liver motion estimation and prediction during free-breathing from 2D ultrasound images can substantially reduce the in-plane motion uncertainty and hence treatment margins. Employing an accurate tracking method while avoiding non-linear temporal prediction would be favorable. This approach has the potential to shorten treatment time compared to breath-hold and gated approaches, and increase treatment efficiency and safety.

show abstract

Temporal regularization of ultrasound-based liver motion estimation for image-guided radiation therapy

Cited by 19 publications

References 23 publications

Monte Carlo investigation of the dosimetric effect of the Autoscan ultrasound probe for guidance in radiotherapy

Monte Carlo investigation of the dosimetric effect of the Autoscan ultrasound probe for guidance in radiotherapy

Attention‐aware fully convolutional neural network with convolutional long short‐term memory network for ultrasound‐based motion tracking

Evaluation of 2D and 3D ultrasound tracking algorithms and impact on ultrasound‐guided liver radiotherapy margins

Contact Info

Product

Resources

About