Prospective Clinical Feasibility Study for MRI-Only Brain Radiotherapy

ObjectivesMRI-only radiotherapy (RT) provides a workflow to decrease the geometric uncertainty introduced by the image registration process between MRI and CT data and to streamline the RT planning. Despite the recent availability of validated synthetic CT (sCT) methods for the head region, there are no clinical implementations reported for brain tumors. Based on a preceding validation study of sCT, this study aims to investigate MRI-only brain RT through a prospective clinical feasibility study with endpoints for dosimetry and patient setup.Material and MethodsTwenty-one glioma patients were included. MRI Dixon images were used to generate sCT images using a CE-marked deep learning-based software. RT treatment plans were generated based on MRI delineated anatomical structures and sCT for absorbed dose calculations. CT scans were acquired but strictly used for sCT quality assurance (QA). Prospective QA was performed prior to MRI-only treatment approval, comparing sCT and CT image characteristics and calculated dose distributions. Additional retrospective analysis of patient positioning and dose distribution gamma evaluation was performed.ResultsTwenty out of 21 patients were treated using the MRI-only workflow. A single patient was excluded due to an MRI artifact caused by a hemostatic substance injected near the target during surgery preceding radiotherapy. All other patients fulfilled the acceptance criteria. Dose deviations in target were within ±1% for all patients in the prospective analysis. Retrospective analysis yielded gamma pass rates (2%, 2 mm) above 99%. Patient positioning using CBCT images was within ± 1 mm for registrations with sCT compared to CT.ConclusionWe report a successful clinical study of MRI-only brain radiotherapy, conducted using both prospective and retrospective analysis. Synthetic CT images generated using the CE-marked deep learning-based software were clinically robust based on endpoints for dosimetry and patient positioning.

Download Full-text

MRI-only brain radiotherapy: Assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approach

Radiotherapy and Oncology ◽

10.1016/j.radonc.2019.03.026 ◽

2019 ◽

Vol 136 ◽

pp. 56-63 ◽

Cited By ~ 23

Author(s):

Samaneh Kazemifar ◽

Sarah McGuire ◽

Robert Timmerman ◽

Zabi Wardak ◽

Dan Nguyen ◽

...

Keyword(s):

Deep Learning ◽

Ct Images ◽

Learning Approach ◽

Brain Radiotherapy ◽

Dosimetric Accuracy ◽

Synthetic Ct

Download Full-text

PO-1738: Dosimetric evaluation of deep learning generated synthetic CT data for H&N MRI only radiotherapy

Radiotherapy and Oncology ◽

10.1016/s0167-8140(21)01756-4 ◽

2020 ◽

Vol 152 ◽

pp. S963-S964

Author(s):

E. Palmér ◽

A. Karlsson ◽

F. Nordström ◽

C. Siversson ◽

K. Petruson ◽

...

Keyword(s):

Deep Learning ◽

Ct Data ◽

Synthetic Ct

Download Full-text

OC-0293: Dosimetric evaluation of deep learning based synthetic-CT generation for MR-only brain radiotherapy

Radiotherapy and Oncology ◽

10.1016/s0167-8140(18)30603-0 ◽

2018 ◽

Vol 127 ◽

pp. S151 ◽

Cited By ~ 1

Author(s):

A.M. Dinkla ◽

J.M. Wolterink ◽

M. Maspero ◽

M.H.F. Savenije ◽

J.J.C. Verhoeff ◽

...

Keyword(s):

Deep Learning ◽

Brain Radiotherapy ◽

Synthetic Ct

Download Full-text

Deep learning‐based synthetic CT generation for MR‐only radiotherapy of prostate cancer patients with 0.35T MRI linear accelerator

Journal of Applied Clinical Medical Physics ◽

10.1002/acm2.13327 ◽

2021 ◽

Author(s):

Reza Farjam ◽

Himanshu Nagar ◽

Xi Kathy Zhou ◽

David Ouellette ◽

Silvia Chiara Formenti ◽

...

Keyword(s):

Prostate Cancer ◽

Deep Learning ◽

Cancer Patients ◽

Linear Accelerator ◽

Synthetic Ct

Download Full-text

An automatic deep learning-based workflow for glioblastoma survival prediction using pre-operative multimodal MR images: a feasibility study

Advances in Radiation Oncology ◽

10.1016/j.adro.2021.100746 ◽

2021 ◽

pp. 100746

Author(s):

Jie Fu ◽

Kamal Singhrao ◽

Xinran Zhong ◽

Yu Gao ◽

Sharon X. Qi ◽

...

Keyword(s):

Deep Learning ◽

Feasibility Study ◽

Survival Prediction ◽

Mr Images

Download Full-text

Dosimetric evaluation of synthetic CT image generated using a neural network for MR‐only brain radiotherapy

Journal of Applied Clinical Medical Physics ◽

10.1002/acm2.13176 ◽

2021 ◽

Vol 22 (3) ◽

pp. 55-62

Author(s):

Bin Tang ◽

Fan Wu ◽

Yuchuan Fu ◽

Xianliang Wang ◽

Pei Wang ◽

...

Keyword(s):

Neural Network ◽

Ct Image ◽

Brain Radiotherapy ◽

Synthetic Ct

Download Full-text

Performance evaluation of a deep learning image reconstruction (DLIR) algorithm in “double low” chest CTA in children: a feasibility study

La radiologia medica ◽

10.1007/s11547-021-01384-2 ◽

2021 ◽

Author(s):

Jihang Sun ◽

Haoyan Li ◽

Jun Gao ◽

Jianying Li ◽

Michelle Li ◽

...

Keyword(s):

Performance Evaluation ◽

Deep Learning ◽

Image Reconstruction ◽

Feasibility Study

Download Full-text

Use of a Head-Tilting Baseplate During Tomotherapy to Shorten the Irradiation Time and Protect the Hippocampus and Lens in Hippocampal Sparing-Whole Brain Radiotherapy

Technology in Cancer Research & Treatment ◽

10.1177/1533033820986824 ◽

2021 ◽

Vol 20 ◽

pp. 153303382098682

Author(s):

Kosei Miura ◽

Hiromasa Kurosaki ◽

Nobuko Utsumi ◽

Hideyuki Sakurai

Keyword(s):

At Risk ◽

Planning Target Volume ◽

Irradiation Time ◽

Organs At Risk ◽

Absorbed Dose ◽

Whole Brain Radiotherapy ◽

Target Volume ◽

Whole Brain ◽

Brain Radiotherapy ◽

Hippocampal Sparing

Purpose: The aim of this study is to comparatively examine the possibility of reducing the exposure dose to organs at risk, such as the hippocampus and lens, and improving the dose distribution of the planned target volume with and without the use of a head-tilting base plate in hippocampal-sparing whole-brain radiotherapy using tomotherapy. Methods: Five paired images of planned head computed tomography without and with tilt were analyzed. The hippocampus and planning target volume were contoured according to the RTOG 0933 contouring atlas protocol. The hippocampal zone to be avoided was delineated using a 5-mm margin. The prescribed radiation dose was 30 Gy in 10 fractions. The absorbed dose to planning target volume dose, absorbed dose to the organ at risk, and irradiation time were evaluated. The paired t-test was used to analyze the differences between hippocampal-sparing whole-brain radiotherapy with head tilts and without head tilts. Results: Hippocampal-sparing whole-brain radiotherapy with tilt was not superior in planning target volume doses using the homogeneity index than that without tilt; however, it showed better values, and for Dmean and D2%, the values were closer to 30 Gy. Regarding the hippocampus, dose reduction with tilt was significantly greater at Dmax, Dmean, and Dmin, whereas regarding the lens, it was significantly greater at Dmax and Dmin. The irradiation time was also predominantly shorter. Conclusion: In our study, a tilted hippocampal-sparing whole-brain radiotherapy reduced the irradiation time by >10%. Therefore, our study indicated that hippocampal-sparing whole-brain radiotherapy with tomotherapy should be performed with a tilt. The head-tilting technique might be useful during hippocampal-sparing whole-brain radiotherapy. This method could decrease the radiation exposure time, while sparing healthy organs, including the hippocampus and lens.

Download Full-text

NIMG-08. PREDICTION OF LOWER-GRADE GLIOMA MOLECULAR SUBTYPES USING DEEP LEARNING

Neuro-Oncology ◽

10.1093/neuonc/noaa215.621 ◽

2020 ◽

Vol 22 (Supplement_2) ◽

pp. ii148-ii148

Author(s):

Yoshihiro Muragaki ◽

Yutaka Matsui ◽

Takashi Maruyama ◽

Masayuki Nitta ◽

Taiichi Saito ◽

...

Keyword(s):

Deep Learning ◽

Cross Validation ◽

Molecular Subtype ◽

Learning Model ◽

Group Classification ◽

Training Dataset ◽

Lower Grade ◽

Test Dataset ◽

Ct Data ◽

Deep Learning Model

Abstract INTRODUCTION It is useful to know the molecular subtype of lower-grade gliomas (LGG) when deciding on a treatment strategy. This study aims to diagnose this preoperatively. METHODS A deep learning model was developed to predict the 3-group molecular subtype using multimodal data including magnetic resonance imaging (MRI), positron emission tomography (PET), and computed tomography (CT). The performance was evaluated using leave-one-out cross validation with a dataset containing information from 217 LGG patients. RESULTS The model performed best when the dataset contained MRI, PET, and CT data. The model could predict the molecular subtype with an accuracy of 96.6% for the training dataset and 68.7% for the test dataset. The model achieved test accuracies of 58.5%, 60.4%, and 59.4% when the dataset contained only MRI, MRI and PET, and MRI and CT data, respectively. The conventional method used to predict mutations in the isocitrate dehydrogenase (IDH) gene and the codeletion of chromosome arms 1p and 19q (1p/19q) sequentially had an overall accuracy of 65.9%. This is 2.8 percent point lower than the proposed method, which predicts the 3-group molecular subtype directly. CONCLUSIONS AND FUTURE PERSPECTIVE A deep learning model was developed to diagnose the molecular subtype preoperatively based on multi-modality data in order to predict the 3-group classification directly. Cross-validation showed that the proposed model had an overall accuracy of 68.7% for the test dataset. This is the first model to double the expected value for a 3-group classification problem, when predicting the LGG molecular subtype. We plan to apply the techniques of heat map and/or segmentation for an increase in prediction accuracy.

Download Full-text