A5091643028- Advanced Radiotherapy Techniques
- Lung Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Radiation Therapy and Dosimetry
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Radiation Dose and Imaging
- Head and Neck Cancer Studies
- Esophageal Cancer Research and Treatment
- Prostate Cancer Diagnosis and Treatment
- Effects of Radiation Exposure
- Gastric Cancer Management and Outcomes
- Management of metastatic bone disease
- Endometrial and Cervical Cancer Treatments
- Esophageal and GI Pathology
- Brain Metastases and Treatment
- Lung Cancer Treatments and Mutations
- Ultrasound and Hyperthermia Applications
- Advanced MRI Techniques and Applications
- Radiation Effects and Dosimetry
- Radiation Detection and Scintillator Technologies
- Chemotherapy-induced cardiotoxicity and mitigation
- Medical Imaging and Analysis
- Nuclear Physics and Applications
- Prostate Cancer Treatment and Research
Tohoku University Hospital
2011-2025
Tohoku University
2016-2025
Japanese Society of Medical Oncology
2024
Dana-Farber Cancer Institute
2020
Tata Medical Center
2016
The University of Sydney
2015
Stanford University
2013-2015
Philips (Germany)
2015
National Center for Global Health and Medicine
2015
National Cancer Center Hospital East
2015
Purpose Patient‐specific quality assurance ( QA ) measurement is conducted to confirm the accuracy of dose delivery. However, time‐consuming and places a heavy workload on medical physicists radiological technologists. In this study, we proposed prediction model for gamma evaluation, based deep learning. We applied dataset prostate cancer cases evaluate its practicality. Methods Sixty pretreatment verification plans from patients treated using intensity modulated radiation therapy were...
We evaluated the accuracy of one commercially available and three publicly deformable image registration (DIR) algorithms for thoracic four-dimensional (4D) computed tomography (CT) images. Five patients with esophagus cancer were studied. Datasets five provided by DIR-lab (dir-lab.com) consisted 4D CT images a coordinate list anatomical landmarks that had been manually identified. Expert landmark correspondence was used evaluating DIR spatial accuracy. First, measured displacement vector...
Purpose CT ventilation imaging (CTVI) is being used to achieve functional avoidance lung cancer radiation therapy in three clinical trials (NCT02528942, NCT02308709, NCT02843568). To address the need for common CTVI validation tools, we have built Ventilation And Medical Pulmonary Image Registration Evaluation (VAMPIRE) Dataset, and present results of first VAMPIRE Challenge compare relative distributions between different algorithms other established modalities. Methods The Dataset includes...
The purpose of the study was to compare a 3D convolutional neural network (CNN) with conventional machine learning method for predicting intensity-modulated radiation therapy (IMRT) dose distribution using only contours in prostate cancer. In this study, which included 95 IMRT-treated cancer patients available distributions and planning target volume (PTVs) organs at risk (OARs), supervised-learning approach used training, where voxel set dataset defined as label. adaptive moment estimation...
Early regression-the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)-is a common occurrence radiotherapy. This rapid radiation-induced may alter target coordinates, necessitating adaptive (ART). We developed deep learning-based radiomics (DLR) approach to predict early head and neck thereby facilitate ART. Primary gross (GTVp) was monitored 96 patients nodal GTV (GTVn) 79 treatment. All underwent two computed tomography...
Purpose This study aimed to investigate changes in target coverage using magnetic resonance–guided online adaptive radiotherapy (MRgoART) for kidney tumors and evaluate the suitable timing of treatment. Materials Methods Among patients treated with 3-fraction MRgoART cancer, 18 located within 1 cm gastrointestinal tract were selected. Stereotactic radiosurgery planning a prescription dose 26 Gy was performed pretreatment simulation three timings an adapt-to-shape method. The best plan...
Deformable image registration (DIR) is fundamental technique for adaptive radiotherapy and image-guided radiotherapy. However, further improvement of DIR still needed. We evaluated the accuracy B-spline transformation-based implemented in elastix. This package largely based on Insight Segmentation Registration Toolkit (ITK), several new functions were to achieve high accuracy. The purpose this study was clarify whether elastix are useful improving Thoracic 4D computed tomography images ten...
In this study, we developed a 3D-printed deformable pelvis phantom for evaluating spatial DIR accuracy. We then evaluated the accuracies of various settings cervical cancer.A female was created based on patient CT data using 3D printing. To create uterus phantom, first printed both model and internal cavities vagina uterus. made mold phantom. Finally, urethane poured into with in place, creating cavity which an applicator could be inserted. bladder models same scaled down by 2 mm. larger...
Purpose This study aimed to develop and evaluate a novel strategy for establishing deep learning‐based gamma passing rate (GPR) prediction model volumetric modulated arc therapy (VMAT) using dummy target plan data, one measurement process, multicriteria method. Methods A total of 147 VMAT plans were used the training set (two sets 48 plans) test (51 clinical plans). The measured diode array detector. We developed an original convolutional neural network that accepts coronal sagittal dose...
Abstract Purpose In patient‐specific quality assurance (QA) for static beam intensity‐modulated radiation therapy (IMRT), machine‐learning‐based dose analysis methods have been developed to identify the cause of an error as alternative gamma analysis. Although these new revealed that can be identified by analyzing distribution obtained from two‐dimensional detector, they not extended volumetric‐modulated arc (VMAT) QA. this study, we propose a deep learning approach detect various types...
The irradiation field of boron neutron capture therapy (BNCT) consists multiple dose components including thermal, epithermal and fast neutron, gamma. objective this work was to establish a methodology dosimetric quality assurance (QA), using the most standard reliable measurement methods, determine tolerance level for each QA commercially available accelerator-based BNCT system. In order system suitable BNCT, following steps were taken. First, points based on tissue-administered doses in...
This study aimed to evaluate the performance of hybrid deformable image registration (DIR) method in comparison with intensity-based DIR for pelvic cone-beam computed tomography (CBCT) images, using intensity and anatomical information. Ten prostate cancer patients treated intensity-modulated radiation therapy (IMRT) were studied. Nine or ten CBCT scans performed each patient. First, rigid was between planning CT all images gold fiducial markers, then performed. The Dice similarity...
Purpose To assess changes in left ventricular function and tissue composition by using MRI after chemotherapy–radiation therapy participants with esophageal cancer. Materials Methods Between January 2013 April 2015, this prospective study enrolled 24 (42% women; mean age, 63 years; range, 49–73 years) scheduled for therapy. 3.0-T examinations were performed before, at 0.5 year, 1.5 years Myocardial native T1, postcontrast extracellular volume measured basal septum (as irradiated areas)...