1
|
Marasini S, Cole M, Curcuru A, Dyke LM, Gach HM, Flores R, Kim T. Characterization of real-time cine MR imaging distortion on 0.35 T MRgRT with concentric cine imaging QA phantom. Phys Med Biol 2024; 69:065009. [PMID: 38408387 DOI: 10.1088/1361-6560/ad2d33] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 02/26/2024] [Indexed: 02/28/2024]
Abstract
Objective. Real-time MRgRT uses 2D-cine imaging for target tracking and motion evaluation. Rotation of gantry inducedB0off-resonance, resulting in image artifacts and imaging isocenter-shift precluding MR-guided arc therapy. Standard MRI phantoms designed for higher resolution images face challenges when low-resolution cine imaging is needed to achieve high frame rates. This work aimed to examine the spatial accuracy including geometric distortion and isocenter shift in real-time during gantry rotation on a 0.35 T MR-Linac using the concentric Cine imaging quality assurance (QA) phantom and its associated image analysis software.Approach. The Cine imaging QA phantom consists of two concentric shells of low-T1mineral oil and a central alignment structure. The phantom was scanned on three different MRI systems; 0.55 T Siemens Free.Max, 1.5 T Philips Ingenia, and 0.35 T ViewRay MRIdian MR-Linac using 2D balanced steady-state free precession (bSSFP) imaging sequence. In addition, bSSFP cine MRI with the banding artifact correction was tested on 0.35 T ViewRay MR-Linac. Images from the MR-Linac were acquired with the Linac gantry stationary and rotating from gantry 300°→ 0° and vice versa. Three orthogonal image planes were scanned excluding the 1.5 T Philips Ingenia, where only the axial plane was scanned. The image analysis software calculated the distortion values as well as the isocenter position for each cine frame.Main results. The geometric distortion of cine imaging on MRIs and MR-Linac at gantry stationary are within 1 mm while the substantial geometric distortion of 2 and 2.2 mm were observed on 0.35 T MR-Linac while rotating the gantry clockwise (300°→ 0°) and counterclockwise 0°→ 300° respectively. The average imaging isocenter shift was 0.1 mm for both MRIs and the static gantry and imaging isocenter shift of ≤1.5 mm was observed during the gantry rotation. The imaging isocenter shift decreased by 1 ± 0.2 mm clockwise and counterclockwise withB0compensation.Significance. The concentric Cine imaging QA phantom and its associated software effectively demonstrate the image distortion on real-time cine imaging on regular MRIs and 0.35 T MR-Linac. The results of significant geometric distortion with a rotating gantry in the MR-Linac system require further investigation to alleviate the extent of the image distortion.
Collapse
Affiliation(s)
- Shanti Marasini
- Departments of Radiation Oncology, Washington University School of Medicine, St. Louis, MO,United States of America
| | | | - Austen Curcuru
- Departments of Radiation Oncology, Washington University School of Medicine, St. Louis, MO,United States of America
| | - Lara M Dyke
- Departments of Radiation Oncology, Washington University School of Medicine, St. Louis, MO,United States of America
| | - H Michael Gach
- Departments of Radiation Oncology, Washington University School of Medicine, St. Louis, MO,United States of America
- Department of Radiology, Washington University School of Medicine, St. Louis, MO, United States of America
- Departments of Biomedical Engineering, Washington University in St. Louis, MO, United States of America
| | | | - Taeho Kim
- Departments of Radiation Oncology, Washington University School of Medicine, St. Louis, MO,United States of America
| |
Collapse
|
2
|
Shan S, Gao Y, Liu PZY, Whelan B, Sun H, Dong B, Liu F, Waddington DEJ. Distortion-corrected image reconstruction with deep learning on an MRI-Linac. Magn Reson Med 2023; 90:963-977. [PMID: 37125656 PMCID: PMC10860740 DOI: 10.1002/mrm.29684] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Revised: 03/29/2023] [Accepted: 04/11/2023] [Indexed: 05/02/2023]
Abstract
PURPOSE MRI is increasingly utilized for image-guided radiotherapy due to its outstanding soft-tissue contrast and lack of ionizing radiation. However, geometric distortions caused by gradient nonlinearities (GNLs) limit anatomical accuracy, potentially compromising the quality of tumor treatments. In addition, slow MR acquisition and reconstruction limit the potential for effective image guidance. Here, we demonstrate a deep learning-based method that rapidly reconstructs distortion-corrected images from raw k-space data for MR-guided radiotherapy applications. METHODS We leverage recent advances in interpretable unrolling networks to develop a Distortion-Corrected Reconstruction Network (DCReconNet) that applies convolutional neural networks (CNNs) to learn effective regularizations and nonuniform fast Fourier transforms for GNL-encoding. DCReconNet was trained on a public MR brain dataset from 11 healthy volunteers for fully sampled and accelerated techniques, including parallel imaging (PI) and compressed sensing (CS). The performance of DCReconNet was tested on phantom, brain, pelvis, and lung images acquired on a 1.0T MRI-Linac. The DCReconNet, CS-, PI-and UNet-based reconstructed image quality was measured by structural similarity (SSIM) and RMS error (RMSE) for numerical comparisons. The computation time and residual distortion for each method were also reported. RESULTS Imaging results demonstrated that DCReconNet better preserves image structures compared to CS- and PI-based reconstruction methods. DCReconNet resulted in the highest SSIM (0.95 median value) and lowest RMSE (<0.04) on simulated brain images with four times acceleration. DCReconNet is over 10-times faster than iterative, regularized reconstruction methods. CONCLUSIONS DCReconNet provides fast and geometrically accurate image reconstruction and has the potential for MRI-guided radiotherapy applications.
Collapse
Affiliation(s)
- Shanshan Shan
- ACRF Image X Institute, Sydney School of Health Sciences, Faculty of Medicine and HealthThe University of SydneySydneyNew South WalesAustralia
- State Key Laboratory of Radiation Medicine and Protection, School for Radiological and Interdisciplinary Sciences (RAD‐X), Collaborative Innovation Center of Radiation Medicine of Jiangsu Higher Education InstitutionsSoochow UniversitySuzhouJiangsuChina
- Department of Medical PhysicsIngham Institute of Applied Medical ResearchLiverpoolNew South WalesAustralia
- School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneQueenslandAustralia
| | - Yang Gao
- School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneQueenslandAustralia
- School of Computer Science and EngineeringCentral South UniversityChangshaHunanChina
| | - Paul Z. Y. Liu
- ACRF Image X Institute, Sydney School of Health Sciences, Faculty of Medicine and HealthThe University of SydneySydneyNew South WalesAustralia
- Department of Medical PhysicsIngham Institute of Applied Medical ResearchLiverpoolNew South WalesAustralia
| | - Brendan Whelan
- ACRF Image X Institute, Sydney School of Health Sciences, Faculty of Medicine and HealthThe University of SydneySydneyNew South WalesAustralia
- Department of Medical PhysicsIngham Institute of Applied Medical ResearchLiverpoolNew South WalesAustralia
| | - Hongfu Sun
- School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneQueenslandAustralia
| | - Bin Dong
- Department of Medical PhysicsIngham Institute of Applied Medical ResearchLiverpoolNew South WalesAustralia
| | - Feng Liu
- School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneQueenslandAustralia
| | - David E. J. Waddington
- ACRF Image X Institute, Sydney School of Health Sciences, Faculty of Medicine and HealthThe University of SydneySydneyNew South WalesAustralia
- Department of Medical PhysicsIngham Institute of Applied Medical ResearchLiverpoolNew South WalesAustralia
| |
Collapse
|
3
|
Liu PZY, Shan S, Waddington D, Whelan B, Dong B, Liney G, Keall P. Rapid distortion correction enables accurate magnetic resonance imaging-guided real-time adaptive radiotherapy. Phys Imaging Radiat Oncol 2023; 25:100414. [PMID: 36713071 PMCID: PMC9880240 DOI: 10.1016/j.phro.2023.100414] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Revised: 01/11/2023] [Accepted: 01/17/2023] [Indexed: 01/22/2023] Open
Abstract
Background and purpose Magnetic resonance imaging (MRI)-Linac systems combine simultaneous MRI with radiation delivery, allowing treatments to be guided by anatomically detailed, real-time images. However, MRI can be degraded by geometric distortions that cause uncertainty between imaged and actual anatomy. In this work, we develop and integrate a real-time distortion correction method that enables accurate real-time adaptive radiotherapy. Materials and methods The method was based on the pre-treatment calculation of distortion and the rapid correction of intrafraction images. A motion phantom was set up in an MRI-Linac at isocentre (P0 ), the edge (P 1) and just outside (P 2) the imaging volume. The target was irradiated and tracked during real-time adaptive radiotherapy with and without the distortion correction. The geometric tracking error and latency were derived from the measurements of the beam and target positions in the EPID images. Results Without distortion correction, the mean geometric tracking error was 1.3 mm at P 1 and 3.1 mm at P 2. When distortion correction was applied, the error was reduced to 1.0 mm at P 1 and 1.1 mm at P 2. The corrected error was similar to an error of 0.9 mm at P0 where the target was unaffected by distortion indicating that this method has accurately accounted for distortion during tracking. The latency was 319 ± 12 ms without distortion correction and 335 ± 34 ms with distortion correction. Conclusions We have demonstrated a real-time distortion correction method that maintains accurate radiation delivery to the target, even at treatment locations with large distortion.
Collapse
Affiliation(s)
- Paul Z. Y Liu
- Image X Institute, University of Sydney Central Clinical School, Sydney, NSW, Australia,Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - Shanshan Shan
- Image X Institute, University of Sydney Central Clinical School, Sydney, NSW, Australia,Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - David Waddington
- Image X Institute, University of Sydney Central Clinical School, Sydney, NSW, Australia,Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - Brendan Whelan
- Image X Institute, University of Sydney Central Clinical School, Sydney, NSW, Australia,Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - Bin Dong
- Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - Gary Liney
- Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia,School of Medicine, University of New South Wales, Sydney, NSW, Australia,Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW, Australia
| | - Paul Keall
- Image X Institute, University of Sydney Central Clinical School, Sydney, NSW, Australia,Department of Medical Physics, Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia,Corresponding author at: Image X Institute, University of Sydney Central Clinical School, Sydney, NSW, Australia.
| |
Collapse
|
4
|
Goodburn RJ, Philippens MEP, Lefebvre TL, Khalifa A, Bruijnen T, Freedman JN, Waddington DEJ, Younus E, Aliotta E, Meliadò G, Stanescu T, Bano W, Fatemi‐Ardekani A, Wetscherek A, Oelfke U, van den Berg N, Mason RP, van Houdt PJ, Balter JM, Gurney‐Champion OJ. The future of MRI in radiation therapy: Challenges and opportunities for the MR community. Magn Reson Med 2022; 88:2592-2608. [PMID: 36128894 PMCID: PMC9529952 DOI: 10.1002/mrm.29450] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Revised: 08/17/2022] [Accepted: 08/22/2022] [Indexed: 01/11/2023]
Abstract
Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.
Collapse
Affiliation(s)
- Rosie J. Goodburn
- Joint Department of PhysicsInstitute of Cancer Research and Royal Marsden NHS Foundation TrustLondonUnited Kingdom
| | | | - Thierry L. Lefebvre
- Department of PhysicsUniversity of CambridgeCambridgeUnited Kingdom
- Cancer Research UK Cambridge Research InstituteUniversity of CambridgeCambridgeUnited Kingdom
| | - Aly Khalifa
- Department of Medical BiophysicsUniversity of TorontoTorontoOntarioCanada
| | - Tom Bruijnen
- Department of RadiotherapyUniversity Medical Center UtrechtUtrechtNetherlands
| | | | - David E. J. Waddington
- Faculty of Medicine and Health, Sydney School of Health Sciences, ACRF Image X InstituteThe University of SydneySydneyNew South WalesAustralia
| | - Eyesha Younus
- Department of Medical Physics, Odette Cancer CentreSunnybrook Health Sciences CentreTorontoOntarioCanada
| | - Eric Aliotta
- Department of Medical PhysicsMemorial Sloan Kettering Cancer CenterNew YorkNew YorkUSA
| | - Gabriele Meliadò
- Unità Operativa Complessa di Fisica SanitariaAzienda Ospedaliera Universitaria Integrata VeronaVeronaItaly
| | - Teo Stanescu
- Department of Radiation Oncology, University of Toronto and Medical Physics, Princess Margaret Cancer CentreUniversity Health NetworkTorontoOntarioCanada
| | - Wajiha Bano
- Joint Department of PhysicsInstitute of Cancer Research and Royal Marsden NHS Foundation TrustLondonUnited Kingdom
| | - Ali Fatemi‐Ardekani
- Department of PhysicsJackson State University (JSU)JacksonMississippiUSA
- SpinTecxJacksonMississippiUSA
- Department of Radiation OncologyCommunity Health Systems (CHS) Cancer NetworkJacksonMississippiUSA
| | - Andreas Wetscherek
- Joint Department of PhysicsInstitute of Cancer Research and Royal Marsden NHS Foundation TrustLondonUnited Kingdom
| | - Uwe Oelfke
- Joint Department of PhysicsInstitute of Cancer Research and Royal Marsden NHS Foundation TrustLondonUnited Kingdom
| | - Nico van den Berg
- Department of RadiotherapyUniversity Medical Center UtrechtUtrechtNetherlands
| | - Ralph P. Mason
- Department of RadiologyUniversity of Texas Southwestern Medical CenterDallasTexasUSA
| | - Petra J. van Houdt
- Department of Radiation OncologyNetherlands Cancer InstituteAmsterdamNetherlands
| | - James M. Balter
- Department of Radiation OncologyUniversity of MichiganAnn ArborMichiganUSA
| | - Oliver J. Gurney‐Champion
- Imaging and Biomarkers, Cancer Center Amsterdam, Amsterdam UMCUniversity of AmsterdamAmsterdamNetherlands
| |
Collapse
|
5
|
Keall PJ, Brighi C, Glide-Hurst C, Liney G, Liu PZY, Lydiard S, Paganelli C, Pham T, Shan S, Tree AC, van der Heide UA, Waddington DEJ, Whelan B. Integrated MRI-guided radiotherapy - opportunities and challenges. Nat Rev Clin Oncol 2022; 19:458-470. [PMID: 35440773 DOI: 10.1038/s41571-022-00631-3] [Citation(s) in RCA: 49] [Impact Index Per Article: 24.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/31/2022] [Indexed: 12/25/2022]
Abstract
MRI can help to categorize tissues as malignant or non-malignant both anatomically and functionally, with a high level of spatial and temporal resolution. This non-invasive imaging modality has been integrated with radiotherapy in devices that can differentially target the most aggressive and resistant regions of tumours. The past decade has seen the clinical deployment of treatment devices that combine imaging with targeted irradiation, making the aspiration of integrated MRI-guided radiotherapy (MRIgRT) a reality. The two main clinical drivers for the adoption of MRIgRT are the ability to image anatomical changes that occur before and during treatment in order to adapt the treatment approach, and to image and target the biological features of each tumour. Using motion management and biological targeting, the radiation dose delivered to the tumour can be adjusted during treatment to improve the probability of tumour control, while simultaneously reducing the radiation delivered to non-malignant tissues, thereby reducing the risk of treatment-related toxicities. The benefits of this approach are expected to increase survival and quality of life. In this Review, we describe the current state of MRIgRT, and the opportunities and challenges of this new radiotherapy approach.
Collapse
Affiliation(s)
- Paul J Keall
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia.
| | - Caterina Brighi
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia
| | - Carri Glide-Hurst
- Department of Human Oncology, University of Wisconsin, Madison, WI, USA
| | - Gary Liney
- Ingham Institute of Applied Medical Research, Sydney, New South Wales, Australia
| | - Paul Z Y Liu
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia
| | - Suzanne Lydiard
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia
| | - Chiara Paganelli
- Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy
| | - Trang Pham
- Faculty of Medicine and Health, The University of New South Wales, Sydney, New South Wales, Australia
| | - Shanshan Shan
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia
| | - Alison C Tree
- The Royal Marsden NHS Foundation Trust and the Institute of Cancer Research, London, UK
| | - Uulke A van der Heide
- Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, Netherlands
| | - David E J Waddington
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia
| | - Brendan Whelan
- ACRF Image X Institute, The University of Sydney, Sydney, New South Wales, Australia
| |
Collapse
|
6
|
Patterson E, Oborn BM, Cutajar D, Jelen U, Liney G, Rosenfeld AB, Metcalfe PE. Characterizing magnetically focused contamination electrons by off-axis irradiation on an inline MRI-Linac. J Appl Clin Med Phys 2022; 23:e13591. [PMID: 35333000 PMCID: PMC9195023 DOI: 10.1002/acm2.13591] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Revised: 12/10/2021] [Accepted: 03/02/2022] [Indexed: 11/18/2022] Open
Abstract
Purpose The aim of this study is to investigate off‐axis irradiation on the Australian MRI‐Linac using experiments and Monte Carlo simulations. Simulations are used to verify experimental measurements and to determine the minimum offset distance required to separate electron contamination from the photon field. Methods Dosimetric measurements were performed using a microDiamond detector, Gafchromic® EBT3 film, and MOSkinTM. Three field sizes were investigated including 1.9 × 1.9, 5.8 × 5.8, and 9.7 × 9.6 cm2. Each field was offset a maximum distance, approximately 10 cm, from the central magnetic axis (isocenter). Percentage depth doses (PDDs) were collected at a source‐to‐surface distance (SSD) of 1.8 m for fields collimated centrally and off‐axis. PDD measurements were also acquired at isocenter for each off‐axis field to measure electron contamination. Monte Carlo simulations were used to verify experimental measurements, determine the minimum field offset distance, and demonstrate the use of a spoiler to absorb electron contamination. Results Off‐axis irradiation separates the majority of electron contamination from an x‐ray beam and was found to significantly reduce in‐field surface dose. For the 1.9 × 1.9, 5.8 × 5.8, and 9.7 × 9.6 cm2 field, surface dose was reduced from 120.9% to 24.9%, 229.7% to 39.2%, and 355.3% to 47.3%, respectively. Monte Carlo simulations generally were within experimental error to MOSkinTM and microDiamond, and used to determine the minimum offset distance, 2.1 cm, from the field edge to isocenter. A water spoiler 2 cm thick was shown to reduce electron contamination dose to near zero. Conclusions Experimental and simulation data were acquired for a range of field sizes to investigate off‐axis irradiation on an inline MRI‐Linac. The skin sparing effect was observed with off‐axis irradiation, a feature that cannot be achieved to the same extent with other methods, such as bolusing, for beams at isocenter.
Collapse
Affiliation(s)
| | - Bradley M Oborn
- Centre for Medical Radiation Physics, Wollongong, NSW, Australia.,Illawarra Cancer Care Centre, Wollongong Hospital, Wollongong, NSW, Australia
| | - Dean Cutajar
- Centre for Medical Radiation Physics, Wollongong, NSW, Australia
| | - Urszula Jelen
- Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - Gary Liney
- Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| | - Anatoly B Rosenfeld
- Centre for Medical Radiation Physics, Wollongong, NSW, Australia.,Illawarra Health Medical Research Institute, University of Wollongong, Wollongong, NSW, Australia
| | - Peter E Metcalfe
- Centre for Medical Radiation Physics, Wollongong, NSW, Australia.,Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
| |
Collapse
|
7
|
Shan S, Li M, Li M, Tang F, Crozier S, Liu F. ReUINet: A fast GNL distortion correction approach on a 1.0 T MRI-Linac scanner. Med Phys 2021; 48:2991-3002. [PMID: 33763850 DOI: 10.1002/mp.14861] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2020] [Revised: 03/17/2021] [Accepted: 03/19/2021] [Indexed: 11/12/2022] Open
Abstract
PURPOSE The hybrid system combining a magnetic resonance imaging (MRI) scanner with a linear accelerator (Linac) has become increasingly desirable for tumor treatment because of excellent soft tissue contrast and nonionizing radiation. However, image distortions caused by gradient nonlinearity (GNL) can have detrimental impacts on real-time radiotherapy using MRI-Linac systems, where accurate geometric information of tumors is essential. METHODS In this work, we proposed a deep convolutional neural network-based method to efficiently recover undistorted images (ReUINet) for real-time image guidance. The ReUINet, based on the encoder-decoder structure, was created to learn the relationship between the undistorted images and distorted images. The ReUINet was pretrained and tested on a publically available brain MR image dataset acquired from 23 volunteers. Then, transfer learning was adopted to implement the pretrained model (i.e., network with optimal weights) on the experimental three-dimensional (3D) grid phantom and in-vivo pelvis image datasets acquired from the 1.0 T Australian MRI-Linac system. RESULTS Evaluations on the phantom (768 slices) and pelvis data (88 slices) showed that the ReUINet achieved improvement over 15 times and 45 times on computational efficiency in comparison with standard interpolation and GNL-encoding methods, respectively. Moreover, qualitative and quantitative results demonstrated that the ReUINet provided better correction results than the standard interpolation method, and comparable performance compared to the GNL-encoding approach. CONCLUSIONS Validated by simulation and experimental results, the proposed ReUINet showed promise in obtaining accurate MR images for the implementation of real-time MRI-guided radiotherapy.
Collapse
Affiliation(s)
- Shanshan Shan
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia.,ACRF Image X Institute, School of Health Sciences, University of Sydney, Sydney, Australia
| | - Mao Li
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Mingyan Li
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Fangfang Tang
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Stuart Crozier
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Feng Liu
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| |
Collapse
|
8
|
Buckley JG, Dong B, Liney GP. Imaging performance of a high-field in-line magnetic resonance imaging linear accelerator with a patient rotation system for fixed-gantry radiotherapy. PHYSICS & IMAGING IN RADIATION ONCOLOGY 2020; 16:130-133. [PMID: 33458355 PMCID: PMC7807630 DOI: 10.1016/j.phro.2020.11.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/10/2020] [Revised: 11/05/2020] [Accepted: 11/05/2020] [Indexed: 02/06/2023]
Abstract
This paper describes the imaging performance of a high-field in-line MRI linear accelerator with a patient rotation system in-situ. Signal quality was quantified using signal-to-noise ratio (SNR) and RF uniformity maps. B0-field inhomogeneity was assessed using magnetic field mapping. SNR was evaluated with various entries into the Faraday cage which were required for extended couch translations. SNR varied between 103 and 87 across PRS rotation angles. Maximum B0-field inhomogeneity corresponded to 0.7 mm of geometric distortion. A 45 × 55 cm2 aperture allowed PRS translation with no reduction in SNR. Imaging performance with the PRS in-situ was found to be acceptable.
Collapse
Affiliation(s)
- Jarryd G Buckley
- Centre for Medical Radiation Physics, University of Wollongong, Northfields Avenue, Wollongong, NSW 2522, Australia.,Ingham Institute for Applied Medical Research, 1 Campbell St, Liverpool, NSW 2170, Australia
| | - Bin Dong
- Ingham Institute for Applied Medical Research, 1 Campbell St, Liverpool, NSW 2170, Australia.,Liverpool and Macarthur Cancer Therapy Centre, Liverpool Hospital, 75 Elizabeth St, Liverpool, NSW 2170, Australia
| | - Gary P Liney
- Ingham Institute for Applied Medical Research, 1 Campbell St, Liverpool, NSW 2170, Australia.,Liverpool and Macarthur Cancer Therapy Centre, Liverpool Hospital, 75 Elizabeth St, Liverpool, NSW 2170, Australia
| |
Collapse
|
9
|
Liu PZY, Dong B, Nguyen DT, Ge Y, Hewson EA, Waddington DEJ, O'Brien R, Liney GP, Keall PJ. First experimental investigation of simultaneously tracking two independently moving targets on an MRI‐linac using real‐time MRI and MLC tracking. Med Phys 2020; 47:6440-6449. [DOI: 10.1002/mp.14536] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Revised: 09/16/2020] [Accepted: 10/01/2020] [Indexed: 12/25/2022] Open
Affiliation(s)
- Paul Z. Y. Liu
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
- Department of Medical Physics Ingham Institute for Applied Medical Research Liverpool NSW Australia
| | - Bing Dong
- Department of Medical Physics Ingham Institute for Applied Medical Research Liverpool NSW Australia
| | - Doan Trang Nguyen
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
- School of Biomedical Engineering Faculty of Engineering and IT University of Technology Sydney NSW Australia
| | - Yuanyuan Ge
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
- Nelune Comprehensive Cancer Centre Prince of Wales Hospital Randwick NSW Australia
| | - Emily A. Hewson
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
| | - David E. J. Waddington
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
- Department of Medical Physics Ingham Institute for Applied Medical Research Liverpool NSW Australia
| | - Ricky O'Brien
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
| | - Gary P. Liney
- Department of Medical Physics Ingham Institute for Applied Medical Research Liverpool NSW Australia
- Liverpool Cancer Therapy Centre, Radiation Physics Liverpool NSW Australia
- School of Medicine University of New South Wales Sydney NSW Australia
- Centre for Medical Radiation Physics University of Wollongong Wollongong NSW Australia
| | - Paul J. Keall
- ACRF Image X InstituteUniversity of Sydney Central Clinical School Sydney NSW Australia
- Department of Medical Physics Ingham Institute for Applied Medical Research Liverpool NSW Australia
| |
Collapse
|
10
|
Li M, Shan S, Chandra SS, Liu F, Crozier S. Fast geometric distortion correction using a deep neural network: Implementation for the 1 Tesla MRI‐Linac system. Med Phys 2020; 47:4303-4315. [DOI: 10.1002/mp.14382] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2020] [Revised: 06/18/2020] [Accepted: 07/04/2020] [Indexed: 11/08/2022] Open
Affiliation(s)
- Mao Li
- School of Information Technology and Electrical Engineering University of Queensland Brisbane QLD 4067 Australia
| | - Shanshan Shan
- School of Information Technology and Electrical Engineering University of Queensland Brisbane QLD 4067 Australia
| | - Shekhar S. Chandra
- School of Information Technology and Electrical Engineering University of Queensland Brisbane QLD 4067 Australia
| | - Feng Liu
- School of Information Technology and Electrical Engineering University of Queensland Brisbane QLD 4067 Australia
| | - Stuart Crozier
- School of Information Technology and Electrical Engineering University of Queensland Brisbane QLD 4067 Australia
| |
Collapse
|