Publications by authors named "Akihiro Haga"

73 Publications

Deep Learning Analysis of Echocardiographic Images to Predict Positive Genotype in Patients With Hypertrophic Cardiomyopathy.

Front Cardiovasc Med 2021 27;8:669860. Epub 2021 Aug 27.

Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, United States.

Genetic testing provides valuable insights into family screening strategies, diagnosis, and prognosis in patients with hypertrophic cardiomyopathy (HCM). On the other hand, genetic testing carries socio-economical and psychological burdens. It is therefore important to identify patients with HCM who are more likely to have positive genotype. However, conventional prediction models based on clinical and echocardiographic parameters offer only modest accuracy and are subject to intra- and inter-observer variability. We therefore hypothesized that deep convolutional neural network (DCNN, a type of deep learning) analysis of echocardiographic images improves the predictive accuracy of positive genotype in patients with HCM. In each case, we obtained parasternal short- and long-axis as well as apical 2-, 3-, 4-, and 5-chamber views. We employed DCNN algorithm to predict positive genotype based on the input echocardiographic images. We performed 5-fold cross-validations. We used 2 reference models-the Mayo HCM Genotype Predictor score (Mayo score) and the Toronto HCM Genotype score (Toronto score). We compared the area under the receiver-operating-characteristic curve (AUC) between a combined model using the reference model plus DCNN-derived probability and the reference model. We calculated the -value by performing 1,000 bootstrapping. We calculated sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In addition, we examined the net reclassification improvement. We included 99 adults with HCM who underwent genetic testing. Overall, 45 patients (45%) had positive genotype. The new model combining Mayo score and DCNN-derived probability significantly outperformed Mayo score (AUC 0.86 [95% CI 0.79-0.93] vs. 0.72 [0.61-0.82]; < 0.001). Similarly, the new model combining Toronto score and DCNN-derived probability exhibited a higher AUC compared to Toronto score alone (AUC 0.84 [0.76-0.92] vs. 0.75 [0.65-0.85]; = 0.03). An improvement in the sensitivity, specificity, PPV, and NPV was also achieved, along with significant net reclassification improvement. In conclusion, compared to the conventional models, our new model combining the conventional and DCNN-derived models demonstrated superior accuracy to predict positive genotype in patients with HCM.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fcvm.2021.669860DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8429777PMC
August 2021

Automatic contour segmentation of cervical cancer using artificial intelligence.

J Radiat Res 2021 Sep;62(5):934-944

Department of Medical Image Informatics, Institute of Biomedical Sciences, Tokushima University Graduate School, 3-18-15 Kuramoto-Cho, Tokushima, Tokushima 770-8503, Japan.

In cervical cancer treatment, radiation therapy is selected based on the degree of tumor progression, and radiation oncologists are required to delineate tumor contours. To reduce the burden on radiation oncologists, an automatic segmentation of the tumor contours would prove useful. To the best of our knowledge, automatic tumor contour segmentation has rarely been applied to cervical cancer treatment. In this study, diffusion-weighted images (DWI) of 98 patients with cervical cancer were acquired. We trained an automatic tumor contour segmentation model using 2D U-Net and 3D U-Net to investigate the possibility of applying such a model to clinical practice. A total of 98 cases were employed for the training, and they were then predicted by swapping the training and test images. To predict tumor contours, six prediction images were obtained after six training sessions for one case. The six images were then summed and binarized to output a final image through automatic contour segmentation. For the evaluation, the Dice similarity coefficient (DSC) and Hausdorff distance (HD) was applied to analyze the difference between tumor contour delineation by radiation oncologists and the output image. The DSC ranged from 0.13 to 0.93 (median 0.83, mean 0.77). The cases with DSC <0.65 included tumors with a maximum diameter < 40 mm and heterogeneous intracavitary concentration due to necrosis. The HD ranged from 2.7 to 9.6 mm (median 4.7 mm). Thus, the study confirmed that the tumor contours of cervical cancer can be automatically segmented with high accuracy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/jrr/rrab070DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8438257PMC
September 2021

kV-kV and kV-MV DECT based estimation of proton stopping power ratio - a simulation study.

Phys Med 2021 Aug 12;89:182-192. Epub 2021 Aug 12.

Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology, Beijing 100191, China; School of Physics, Beihang University, Beijing 102206, China; Beijing Key Laboratory of Advanced Nuclear Materials and Physics, Beihang University, Beijing 102206, China; School of Physics and Microelectronics, Zhengzhou University, Zhengzhou, Henan 450001, China.

Purpose: This study aims to estimate the proton stopping power ratio (SPR) by using 80-120 kV and 120 kV-6 MV dual-energy CT (DECT) in a fully simulation-based approach for proton therapy dose calculations.

Methods: Based on a virtual CT system, a two-step approach is applied to obtain the reference attenuation coefficient for image reconstruction. The effective atomic number (EAN) and electron density ratio (EDR) are estimated from two CT scans. The SPR is estimated using a calibration based on known materials to obtain a piecewise linear relationship between the EAN and the logarithm of the mean excitation energy, lnI. The calibration phantoms are constructed from reference tissue materials taken from ICRU Report 44. Our approach is evaluated through using the ICRP110 human phantom. The respective influences of noise and beam hardening effects are studied.

Results: With the beam hardening correction applied, the results of 120 kV-6 MV DECT are comparable to those of 80-120 kV DECT in predicting the EAN, but the former demonstrated a clear improvement in predicting the EDR and SPR. The 120 kV-6 MV DECT is able to predict the SPR within an accuracy of 10% for lung tissue and 5% for pelvis tissue, thereby outperforming the 80-120 kV DECT.

Conclusions: The 120 kV-6 MV DECT is less sensitive to noise but more susceptible to beam hardening effects. By applying beam hardening correction, the 120 kV-6 MV DECT can predict the SPR more accurately than the 80-120 kV DECT. To utilize our DECT approach most effectively, high-quality reconstructed images are required.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2021.07.038DOI Listing
August 2021

Computed tomography image representation using the Legendre polynomial and spherical harmonics functions.

Radiol Phys Technol 2021 Mar 11;14(1):113-121. Epub 2021 Jan 11.

Graduate School of Biomedical Sciences, Tokushima University, 3-18-15 Kuramoto-cho, Tokushima city, Tokushima, 770-8503, Japan.

The representation of computed tomography (CT) images using the Legendre polynomial (LPF) and spherical harmonics (SHF) functions was investigated. We selected 100 two-dimensional (2D) CT images of 10 lung cancer patients and 33 three-dimensional (3D) CT images of head and neck cancer patients. The reproducibility of these special functions was evaluated in terms of the normalized cross-correlation (NCC). For the 2D images, the NCC was 0.990 ± 0.002 (1sd) with an LPF of order 70, whereas for the 3D images, the NCC was 0.971 ± 0.004 (1sd) with an SHF of degree 70. The results showed that the LPF was more efficient than the Fourier series. As the thoracic and head areas are cylindrical and spherical, respectively, expansions with the LPF and SHF achieved an efficient representation of the human body. CT image representation with analytical functions can be potentially beneficial, such as in X-ray scattering estimation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12194-020-00604-0DOI Listing
March 2021

Causal relations of health indices inferred statistically using the DirectLiNGAM algorithm from big data of Osaka prefecture health checkups.

PLoS One 2020 23;15(12):e0243229. Epub 2020 Dec 23.

Health Care Division, Health and Counseling Center, Osaka University, Osaka, Japan.

Causal relations among many statistical variables have been assessed using a Linear non-Gaussian Acyclic Model (LiNGAM). Using access to large amounts of health checkup data from Osaka prefecture obtained during the six fiscal years of years 2012-2017, we applied the DirectLiNGAM algorithm as a trial to extract causal relations among health indices for age groups and genders. Results show that LiNGAM yields interesting and reasonable results, suggesting causal relations and correlation among the statistical indices used for these analyses.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0243229PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7757823PMC
January 2021

Retrospective dose reconstruction of prostate stereotactic body radiotherapy using cone-beam CT and a log file during VMAT delivery with flattening-filter-free mode.

Radiol Phys Technol 2020 Sep 12;13(3):238-248. Epub 2020 Jul 12.

Department of Radiology, University of Tokyo Hospital, 3-7-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.

This study aimed to reconstruct the dose distribution of single fraction of stereotactic body radiotherapy for patients with prostate cancer using cone-beam computed tomography (CBCT) and a log file during volumetric-modulated arc therapy (VMAT) delivery with flattening-filter-free (FFF) mode. Twenty patients with clinically localized prostate cancer were treated with FFF-VMAT, and projection images for in-treatment CBCT (iCBCT) imaging were concomitantly acquired with a log file. A D dose of 36.25 Gy in five fractions was prescribed to each planning target volume (PTV) on each treatment planning CT (pCT). Deformed pCT (dCT) was obtained from the iCBCT using a hybrid deformable image registration algorithm. Dose distributions on the dCT were calculated using Pinnacle v9.10 by converting the log file data to Pinnacle data format using an in-house software. Dose warping was performed by referring to deformation vector fields calculated from pCT and dCT. Reconstructed dose distribution was compared with that of the original plan. Dose differences between the original and reconstructed dose distributions were within 3% at the isocenter and observed in PTV and organ-at-risk (OAR) regions. Differences in OAR regions were relatively larger than those in the PTV, presumably because OARs were more deformed than the PTV. Therefore, our method can be used successfully to reconstruct the dose distributions of one fraction using iCBCT and a log file during FFF-VMAT delivery.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12194-020-00574-3DOI Listing
September 2020

Fast Statistical Iterative Reconstruction for Mega-voltage Computed Tomography.

J Med Invest 2020 ;67(1.2):30-39

Department of Radiology, The University of Tokyo Hospital, Japan.

Statistical iterative reconstruction is expected to improve the image quality of computed tomography (CT). However, one of the challenges of iterative reconstruction is its large computational cost. The purpose of this review is to summarize a fast iterative reconstruction algorithm by optimizing reconstruction parameters. Megavolt projection data was acquired from a TomoTherapy system and reconstructed using in-house statistical iterative reconstruction algorithm. Total variation was used as the regularization term and the weight of the regularization term was determined by evaluating signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and visual assessment of spatial resolution using Gammex and Cheese phantoms. Gradient decent with an adaptive convergence parameter, ordered subset expectation maximization (OSEM), and CPU/GPU parallelization were applied in order to accelerate the present reconstruction algorithm. The SNR and CNR of the iterative reconstruction were several times better than that of filtered back projection (FBP). The GPU parallelization code combined with the OSEM algorithm reconstructed an image several hundred times faster than a CPU calculation. With 500 iterations, which provided good convergence, our method produced a 512 × 512 pixel image within a few seconds. The image quality of the present algorithm was much better than that of FBP for patient data. J. Med. Invest. 67 : 30-39, February, 2020.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2152/jmi.67.30DOI Listing
June 2021

Clinically Feasible and Accurate View Classification of Echocardiographic Images Using Deep Learning.

Biomolecules 2020 04 25;10(5). Epub 2020 Apr 25.

Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima 770-8503, Japan.

A proper echocardiographic study requires several video clips recorded from different acquisition angles for observation of the complex cardiac anatomy. However, these video clips are not necessarily labeled in a database. Identification of the acquired view becomes the first step of analyzing an echocardiogram. Currently, there is no consensus whether the mislabeled samples can be used to create a feasible clinical prediction model of ejection fraction (EF). The aim of this study was to test two types of input methods for the classification of images, and to test the accuracy of the prediction model for EF in a learning database containing mislabeled images that were not checked by observers. We enrolled 340 patients with five standard views (long axis, short axis, 3-chamber view, 4-chamber view and 2-chamber view) and 10 images in a cycle, used for training a convolutional neural network to classify views (total 17,000 labeled images). All DICOM images were rigidly registered and rescaled into a reference image to fit the size of echocardiographic images. We employed 5-fold cross validation to examine model performance. We tested models trained by two types of data, averaged images and 10 selected images. Our best model (from 10 selected images) classified video views with 98.1% overall test accuracy in the independent cohort. In our view classification model, 1.9% of the images were mislabeled. To determine if this 98.1% accuracy was acceptable for creating the clinical prediction model using echocardiographic data, we tested the prediction model for EF using learning data with a 1.9% error rate. The accuracy of the prediction model for EF was warranted, even with training data containing 1.9% mislabeled images. The CNN algorithm can classify images into five standard views in a clinical setting. Our results suggest that this approach may provide a clinically feasible accuracy level of view classification for the analysis of echocardiographic data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/biom10050665DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7277840PMC
April 2020

Deep Learning for Assessment of Left Ventricular Ejection Fraction from Echocardiographic Images.

J Am Soc Echocardiogr 2020 05 25;33(5):632-635.e1. Epub 2020 Feb 25.

Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.echo.2020.01.009DOI Listing
May 2020

Publisher Correction: Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis.

Sci Rep 2020 Feb 17;10(1):3073. Epub 2020 Feb 17.

Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-60086-3DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7026034PMC
February 2020

Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis.

Sci Rep 2019 12 19;9(1):19411. Epub 2019 Dec 19.

Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.

We conducted a feasibility study to predict malignant glioma grades via radiomic analysis using contrast-enhanced T1-weighted magnetic resonance images (CE-T1WIs) and T2-weighted magnetic resonance images (T2WIs). We proposed a framework and applied it to CE-T1WIs and T2WIs (with tumor region data) acquired preoperatively from 157 patients with malignant glioma (grade III: 55, grade IV: 102) as the primary dataset and 67 patients with malignant glioma (grade III: 22, grade IV: 45) as the validation dataset. Radiomic features such as size/shape, intensity, histogram, and texture features were extracted from the tumor regions on the CE-T1WIs and T2WIs. The Wilcoxon-Mann-Whitney (WMW) test and least absolute shrinkage and selection operator logistic regression (LASSO-LR) were employed to select the radiomic features. Various machine learning (ML) algorithms were used to construct prediction models for the malignant glioma grades using the selected radiomic features. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the prediction models in the primary dataset. The selected radiomic features for all folds in the LOOCV of the primary dataset were used to perform an independent validation. As evaluation indices, accuracies, sensitivities, specificities, and values for the area under receiver operating characteristic curve (or simply the area under the curve (AUC)) for all prediction models were calculated. The mean AUC value for all prediction models constructed by the ML algorithms in the LOOCV of the primary dataset was 0.902 ± 0.024 (95% CI (confidence interval), 0.873-0.932). In the independent validation, the mean AUC value for all prediction models was 0.747 ± 0.034 (95% CI, 0.705-0.790). The results of this study suggest that the malignant glioma grades could be sufficiently and easily predicted by preparing the CE-T1WIs, T2WIs, and tumor delineations for each patient. Our proposed framework may be an effective tool for preoperatively grading malignant gliomas.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-019-55922-0DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6923390PMC
December 2019

Acceptable fetal dose using flattening filter-free volumetric arc therapy (FFF VMAT) in postoperative chemoradiotherapy of tongue cancer during pregnancy.

Clin Transl Radiat Oncol 2020 Jan 14;20:9-12. Epub 2019 Oct 14.

Department of Radiology, The University of Tokyo Hospital, Tokyo, Japan.

Optimizing irradiation protocols for pregnant women is challenging, because there are few cases and a dearth of fetal dosimetry data. We cared for a 36-year-old pregnant woman with tongue cancer. Prior to treatment, we compared three intensity-modulated radiation therapy (IMRT) techniques, including helical tomotherapy, volumetric arc therapy (VMAT), and flattening-filter free VMAT (FFF-VMAT) using treatment planning software. FFF-VMAT achieved the minimum fetal exposure and was selected as the optimal modality. We prescribed 66 Gy to the involved nodes, 60 Gy to the tumor bed and ipsilateral neck, and 54 Gy to the contralateral neck over 33 fractions. To confirm the out-of-field exposure per fraction, surface doses and the rectal dose were measured during FFF-VMAT delivery. Postoperative chemoradiotherapy was delivered using IMRT and a cisplatin regimen. Without any shielding, the total fetal dose was 0.03 Gy, within the limits established by the ICRP. A healthy girl was born vaginally at 37 weeks' gestation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ctro.2019.10.002DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6833340PMC
January 2020

Optimization of treatment strategy by using a machine learning model to predict survival time of patients with malignant glioma after radiotherapy.

J Radiat Res 2019 Nov;60(6):818-824

Department of Radiology, The University of Tokyo Hospital, Tokyo, Japan.

The purpose of this study was to predict the survival time of patients with malignant glioma after radiotherapy with high accuracy by considering additional clinical factors and optimize the prescription dose and treatment duration for individual patient by using a machine learning model. A total of 35 patients with malignant glioma were included in this study. The candidate features included 12 clinical features and 192 dose-volume histogram (DVH) features. The appropriate input features and parameters of the support vector machine (SVM) were selected using the genetic algorithm based on Akaike's information criterion, i.e. clinical, DVH, and both clinical and DVH features. The prediction accuracy of the SVM models was evaluated through a leave-one-out cross-validation test with residual error, which was defined as the absolute difference between the actual and predicted survival times after radiotherapy. Moreover, the influences of various values of prescription dose and treatment duration on the predicted survival time were evaluated. The prediction accuracy was significantly improved with the combined use of clinical and DVH features compared with the separate use of both features (P < 0.01, Wilcoxon signed rank test). Mean ± standard deviation of the leave-one-out cross-validation using the combined clinical and DVH features, only clinical features and only DVH features were 104.7 ± 96.5, 144.2 ± 126.1 and 204.5 ± 186.0 days, respectively. The prediction accuracy could be improved with the combination of clinical and DVH features, and our results show the potential to optimize the treatment strategy for individual patients based on a machine learning model.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/jrr/rrz066DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7357235PMC
November 2019

Improvement of the robustness to set up error by a virtual bolus in total scalp irradiation with Helical TomoTherapy.

Radiol Phys Technol 2019 Dec 23;12(4):433-437. Epub 2019 Oct 23.

Department of Radiology, University of Tokyo Hospital, 7-3-1Bunkyo-ku, HongoTokyo, 113-8655, Japan.

Intensity-modulated radiation therapy has recently been used for total scalp irradiation. In inverse planning, the treatment planning system increases the fluence of tangential beam near the skin surface to counter the build-up region. Consequently, the dose to the skin surface increases even with small setup errors. Replacing the electron density of the surrounding air of some thickness with a virtual bolus during optimization could suppress the extremely high fluence near the skin. We confirmed the usefulness of a virtual bolus in total scalp irradiation. For each patient, two beams were planned, one with and the other without a virtual bolus. The dose distribution was calculated using computed tomography images that were shifted to simulate setup errors. The hot spot dose was suppressed in the plans using a virtual bolus. In conclusion, using a virtual bolus improved the robustness to setup errors.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12194-019-00539-1DOI Listing
December 2019

Radiomics Analysis for Glioma Malignancy Evaluation Using Diffusion Kurtosis and Tensor Imaging.

Int J Radiat Oncol Biol Phys 2019 11 22;105(4):784-791. Epub 2019 Jul 22.

Department of Neurosurgery, University of Tokyo, Tokyo.

Purpose: A noninvasive diagnostic method to predict the degree of malignancy accurately would be of great help in glioma management. This study aimed to create a highly accurate machine learning model to perform glioma grading.

Methods And Materials: Preoperative magnetic resonance imaging acquired for cases of glioma operated on at our institution from October 2014 through January 2018 were obtained retrospectively. Six types of magnetic resonance imaging sequences (T-weighted image, diffusion-weighted image, apparent diffusion coefficient [ADC], fractional anisotropy, and mean kurtosis [MK]) were chosen for analysis; 476 features were extracted semiautomatically for each sequence (2856 features in total). Recursive feature elimination was used to select significant features for a machine learning model that distinguishes glioblastoma from lower-grade glioma (grades 2 and 3).

Results: Fifty-five data sets from 54 cases were obtained (14 grade 2 gliomas, 12 grade 3 gliomas, and 29 glioblastomas), of which 44 and 11 data sets were used for machine learning and independent testing, respectively. We detected 504 features with significant differences (false discovery rate <0.05) between glioblastoma and lower-grade glioma. The most accurate machine learning model was created using 6 features extracted from the ADC and MK images. In the logistic regression, the area under the curve was 0.90 ± 0.05, and the accuracy of the test data set was 0.91 (10 out of 11); using a support vector machine, they were 0.93 ± 0.03 and 0.91 (10 out of 11), respectively (kernel, radial basis function; c = 1.0).

Conclusions: Our machine learning model accurately predicted glioma tumor grade. The ADC and MK sequences produced particularly useful features.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijrobp.2019.07.011DOI Listing
November 2019

Utilization of Artificial Intelligence in Echocardiography.

Circ J 2019 07 29;83(8):1623-1629. Epub 2019 Jun 29.

Department of Cardiovascular Medicine, Tokushima University Hospital.

Echocardiography has a central role in the diagnosis and management of cardiovascular disease. Precise and reliable echocardiographic assessment is required for clinical decision-making. Even if the development of new technologies (3-dimentional echocardiography, speckle-tracking, semi-automated analysis, etc.), the final decision on analysis is strongly dependent on operator experience. Diagnostic errors are a major unresolved problem. Moreover, not only can cardiologists differ from one another in image interpretation, but also the same observer may come to different findings when a reading is repeated. Daily high workloads in clinical practice may lead to this error, and all cardiologists require precise perception in this field. Artificial intelligence (AI) has the potential to improve analysis and interpretation of medical images to a new stage compared with previous algorithms. From our comprehensive review, we believe AI has the potential to improve accuracy of diagnosis, clinical management, and patient care. Although there are several concerns about the required large dataset and "black box" algorithm, AI can provide satisfactory results in this field. In the future, it will be necessary for cardiologists to adapt their daily practice to incorporate AI in this new stage of echocardiography.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1253/circj.CJ-19-0420DOI Listing
July 2019

A Deep Learning Approach for Assessment of Regional Wall Motion Abnormality From Echocardiographic Images.

JACC Cardiovasc Imaging 2020 02 15;13(2 Pt 1):374-381. Epub 2019 May 15.

Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan.

Objectives: This study investigated whether a deep convolutional neural network (DCNN) could provide improved detection of regional wall motion abnormalities (RWMAs) and differentiate among groups of coronary infarction territories from conventional 2-dimensional echocardiographic images compared with that of cardiologists, sonographers, and resident readers.

Background: An effective intervention for reduction of misreading of RWMAs is needed. The hypothesis was that a DCNN trained using echocardiographic images would provide improved detection of RWMAs in the clinical setting.

Methods: A total of 300 patients with a history of myocardial infarction were enrolled. From this cohort, 3 groups of 100 patients each had infarctions of the left anterior descending (LAD) artery, the left circumflex (LCX) branch, and the right coronary artery (RCA). A total of 100 age-matched control patients with normal wall motion were selected from a database. Each case contained cardiac ultrasonographs from short-axis views at end-diastolic, mid-systolic, and end-systolic phases. After the DCNN underwent 100 steps of training, diagnostic accuracies were calculated from the test set. Independently, 10 versions of the same model were trained, and ensemble predictions were performed using those versions.

Results: For detection of the presence of WMAs, the area under the receiver-operating characteristic curve (AUC) produced by the deep learning algorithm was similar to that produced by the cardiologists and sonographer readers (0.99 vs. 0.98, respectively; p = 0.15) and significantly higher than the AUC result of the resident readers (0.99 vs. 0.90, respectively; p = 0.002). For detection of territories of WMAs, the AUC by the deep learning algorithm was similar to the AUC by the cardiologist and sonographer readers (0.97 vs. 0.95, respectively; p = 0.61) and significantly higher than the AUC by resident readers (0.97 vs. 0.83, respectively; p = 0.003). From a validation group at an independent site (n = 40), the AUC by the deep learning algorithm was 0.90.

Conclusions: The present results support the possibility of using DCNN for automated diagnosis of RWMAs in the field of echocardiography.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jcmg.2019.02.024DOI Listing
February 2020

Standardization of imaging features for radiomics analysis.

J Med Invest 2019 ;66(1.2):35-37

Department of Radiology, The University of TokyoHospital, Tokyo, Japan.

Radiomics has the potential to provide tumor characteristics with noninvasive and repeatable way. The purpose of this paper is to evaluate the standardization effect of imaging features for radiomics analysis. For this purpose, we prepared two CT databases ; one includes 40 non-small cell lung cancer (NSCLC) patients for whom tumor biopsies was performed before stereotactic body radiation therapy in The University of Tokyo Hospital, and the other includes 29 early-stage NSCLC datasets from the Cancer Imaging Archive. The former was used as the training data, whereas the later was used as the test data in the evaluation of the prediction model. In total, 476 imaging features were extracted from each data. Then, both training and test data were standardized as the min-max normalization, the z-score normalization, and the whitening from the principle component analysis. All of standardization strategies improved the accuracy for the histology prediction. The area under the receiver observed characteristics curve was 0.725, 0.789, and 0.785 in above standardizations, respectively. Radiomics analysis has shown that robust features have a high prognostic power in predicting early-stage NSCLC histology subtypes. The performance was able to be improved by standardizing the data in the feature space. J. Med. Invest. 66 : 35-37, February, 2019.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2152/jmi.66.35DOI Listing
December 2019

[An Introduction to Radiomics: Toward a New Era of Precision Medicine].

Igaku Butsuri 2018;38(3):129-134

The University of Tokyo Hospital.

Recently, in a medical field, quantitative data mining is a hot topic for performing a precision (or personalized) medicine. Although a molecular biological data has been mainly utilized for data mining in this field, medical images are also important minable data. Radiomics is a comprehensive analysis methodology for describing tumor phenotypes or molecular biological expressions (e.g. genotypes) using minable feature extracted from a large number of medical images. In this review paper, we introduce to a framework of the radiomics.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.11323/jjmp.38.3_129DOI Listing
April 2019

[Visualization of Organ Motion Using Four Dimensional Cone-beam CT and Its Applications].

Authors:
Akihiro Haga

Nihon Hoshasen Gijutsu Gakkai Zasshi 2018;74(11):1337-1342

Department of Medical Image Informatics, Tokushima University.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.6009/jjrt.2018_JSRT_74.11.1337DOI Listing
March 2019

Development of a markerless tumor-tracking algorithm using prior four-dimensional cone-beam computed tomography.

J Radiat Res 2019 Jan;60(1):109-115

Department of Radiology, The University of Tokyo hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan.

Respiratory motion management is a huge challenge in radiation therapy. Respiratory motion induces temporal anatomic changes that distort the tumor volume and its position. In this study, a markerless tumor-tracking algorithm was investigated by performing phase recognition during stereotactic body radiation therapy (SBRT) using four-dimensional cone-beam computer tomography (4D-CBCT) obtained at patient registration, and in-treatment cone-beam projection images. The data for 20 treatment sessions (five lung cancer patients) were selected for this study. Three of the patients were treated with conventional flattening filter (FF) beams, and the other two were treated with flattening filter-free (FFF) beams. Prior to treatment, 4D-CBCT was acquired to create the template projection images for 10 phases. In-treatment images were obtained at near real time during treatment. Template-based phase recognition was performed for 4D-CBCT re-projected templates using prior 4D-CBCT based phase recognition algorithm and was compared with the results generated by the Amsterdam Shroud (AS) technique. Visual verification technique was used for the verification of the phase recognition and AS technique at certain tumor-visible angles. Offline template matching analysis using the cross-correlation indicated that phase recognition performed using the prior 4D-CBCT and visual verification matched up to 97.5% in the case of FFF, and 95% in the case of FF, whereas the AS technique matched 83.5% with visual verification for FFF and 93% for FF. Markerless tumor tracking based on phase recognition using prior 4D-CBCT has been developed successfully. This is the first study that reports on the use of prior 4D-CBCT based on normalized cross-correlation technique for phase recognition.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/jrr/rry085DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6373695PMC
January 2019

Stereotactic body radiotherapy for centrally-located lung tumors with 56 Gy in seven fractions: A retrospective study.

Oncol Lett 2018 Oct 23;16(4):4498-4506. Epub 2018 Jul 23.

Department of Radiology, University of Tokyo Hospital, Tokyo 113-8655, Japan.

Stereotactic body radiotherapy (SBRT) for centrally-located lung tumors remains a challenge because of the increased risk of treatment-related adverse events (AEs), and uncertainty around prescribing the optimal dose. The present study reported the results of central tumor SBRT with 56 Gy in 7 fractions (fr) at the University of Tokyo Hospital. A total of 35 cases that underwent SBRT with or without volumetric-modulated arc therapy consisting of 56 Gy/7 fr for central lung lesions between 2010 and 2016 at the University of Tokyo Hospital were reveiwed. A central lesion was defined as a tumor within 2 cm of the proximal bronchial tree (RTOG 0236 definition) or within 2 cm in all directions of any critical mediastinal structure. Local control (LC), overall survival (OS), and AEs were investigated. The Kaplan-Meier method was used to estimate LC and OS. AEs were scored per the Common Terminology Criteria for Adverse Events Version 4.0. Thirty-five patients with 36 central lung lesions were included. Fifteen lesions were primary non-small cell lung cancer (NSCLC), 13 were recurrences of NSCLC, and 8 had oligo-recurrences from other primaries. Median tumor diameter was 29 mm. Eighteen patients had had prior surgery. At a median follow-up of 13.1 months for all patients and 18.3 months in surviving patients, 22 patients had died, ten due to primary disease (4 NSCLC), while three were treatment-related. The 1- and 2-year OS were 57.3 and 40.4%, respectively, and median OS was 15.7 months. Local recurrence occurred in only two lesions. 1- and 2-year LC rates were both 96%. Nine patients experienced grade ≥3 toxicity, representing 26% of the cohort. Two of these were grade 5, one pneumonitis and one hemoptysis. Considering the background of the subject, tumor control of our central SBRT is promising, especially in primary NSCLC. However, the safety of SBRT to central lung cancer remains controversial.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3892/ol.2018.9188DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6126178PMC
October 2018

Cone Beam Computed Tomography Image Quality Improvement Using a Deep Convolutional Neural Network.

Cureus 2018 Apr 29;10(4):e2548. Epub 2018 Apr 29.

Radiology, The University of Tokyo Hospital.

Introduction Cone beam computed tomography (CBCT) plays an important role in image-guided radiation therapy (IGRT), while having disadvantages of severe shading artifact caused by the reconstruction using scatter contaminated and truncated projections. The purpose of this study is to develop a deep convolutional neural network (DCNN) method for improving CBCT image quality. Methods CBCT and planning computed tomography (pCT) image pairs from 20 prostate cancer patients were selected. Subsequently, each pCT volume was pre-aligned to the corresponding CBCT volume by image registration, thereby leading to registered pCT data (pCT). Next, a 39-layer DCNN model was trained to learn a direct mapping from the CBCT to the corresponding pCTimages. The trained model was applied to a new CBCT data set to obtain improved CBCT (i-CBCT) images. The resulting i-CBCT images were compared to pCT using the spatial non-uniformity (SNU), the peak-signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM). Results The image quality of the i-CBCT has shown a substantial improvement on spatial uniformity compared to that of the original CBCT, and a significant improvement on the PSNR and the SSIM compared to that of the original CBCT and the enhanced CBCT by the existing pCT-based correction method. Conclusion We have developed a DCNN method for improving CBCT image quality. The proposed method may be directly applicable to CBCT images acquired by any commercial CBCT scanner.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.7759/cureus.2548DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6021187PMC
April 2018

Flattening filter-free technique in volumetric modulated arc therapy for lung stereotactic body radiotherapy: A clinical comparison with the flattening filter technique.

Oncol Lett 2018 Mar 16;15(3):3928-3936. Epub 2018 Jan 16.

Department of Radiology, University of Tokyo Hospital, Tokyo 113-8655, Japan.

The present study sought to evaluate the impact of the flattening filter-free (FFF) technique in volumetric modulated arc therapy for lung stereotactic body radiotherapy. Its clinical safety and availability were compared with the flattening filter (FF) method. The cases of 65 patients who underwent lung volumetric modulated arc therapy-stereotactic body radiotherapy (VMAT-SBRT) using FF or FFF techniques were reviewed. A total of 55 Gy/4 fractions (fr) was prescribed for peripheral lesions or 56 Gy/7 fr for central lesions. The total monitor units (MU), treatment time, dose to tumors, dose to organs at risk, tumor control (local control rate, overall survival, progression-free survival) and adverse events between cases treated with FF and cases treated with the FFF technique were compared. A total of 35 patients were treated with conventional FF techniques prior to November 2014 and 30 patients were treated with FFF techniques after this date. It was revealed that the beam-on time was significantly shortened by the FFF technique (P<0.01). Other factors were similar for FFF and FF plans in respect to conformity (P=0.95), homogeneity (P=0.20) and other dosimetric values, including total MU and planning target volume/internal target volume coverage. The median follow-up period was 18 months (range, 2-35). One-year local control rates were 97.1 and 90.0% in the FF group and FFF groups, respectively (P=0.33). Grade 3 pneumonitis was observed in 5.8% of FF patients and 3.4% of FFF patients (P=1.00). No other adverse events ≥grade 3 were observed. The results of the study suggest that VMAT-SBRT using the FFF technique shortens the treatment time for lung SBRT while maintaining a high local control rate with low toxicity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3892/ol.2018.7809DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5854932PMC
March 2018

Classification of early stage non-small cell lung cancers on computed tomographic images into histological types using radiomic features: interobserver delineation variability analysis.

Radiol Phys Technol 2018 Mar 5;11(1):27-35. Epub 2017 Dec 5.

Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo, Tokyo, 113-8655, Japan.

Radiomics, which involves the extraction of large numbers of quantitative features from medical images, has attracted attention in cancer research. In radiomics analysis, tumor segmentation is a crucial step. In this study, we evaluated the potential application of radiomics for predicting the histology of early stage non-small cell lung cancer (NSCLC) by analyzing interobserver variability in tumor delineation. Forty patient datasets were included in this study, 21 involving adenocarcinomas and 19 involving squamous cell carcinomas. All patients underwent stereotactic body radiotherapy treatment. In total, 476 features were extracted from each dataset, representing treatment planning, computed tomography images, and gross tumor volume (GTV). The definition of GTV can significantly affect the histology prediction. Therefore, in the present study, the effect of interobserver tumor delineation variability on radiomic features was evaluated by preparing 4 volumes of interest (VOIs) for each patient, as follows: the original GTV (which was delineated at treatment planning); two GTVs delineated retrospectively by radiation oncologists; and a semi-automatic GTV contoured by a medical physicist. Radiomic features extracted from each VOI were then analyzed using a naïve Bayesian model. Area-under-the-curve (AUC) analysis showed that interobserver variability in delineation is a significant factor in radiomics performance. Nevertheless, with 8 selected features, AUC values averaged over the VOIs were high (0.725 ± 0.070). The present study indicated that radiomics has potential for predicting early stage NSCLC histology despite variability in delineation. The high prediction accuracy implies that noninvasive histology evaluation by radiomics is a promising clinical application.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12194-017-0433-2DOI Listing
March 2018

Cone-beam CT reconstruction for non-periodic organ motion using time-ordered chain graph model.

Radiat Oncol 2017 Sep 4;12(1):145. Epub 2017 Sep 4.

Department of Radiology, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, 113-8655, Japan.

Purpose: The purpose of this study is to introduce the new concept of a four-dimensional (4D) cone-beam computed tomography (CBCT) reconstruction approach for non-periodic organ motion in cooperation with the time-ordered chain graph model (TCGM) and to compare it with previously developed methods such as total variation-based compressed sensing (TVCS) and prior-image constrained compressed sensing (PICCS).

Materials And Methods: Our proposed reconstruction is based on a model including the constraint originating from the images of neighboring time phases. Namely, the reconstructed time-series images depend on each other in this TCGM scheme, and the time-ordered images are concurrently reconstructed in the iterative reconstruction approach. In this study, iterative reconstruction with the TCGM was carried out with 90° projection ranges. The images reconstructed by the TCGM were compared with the images reconstructed by TVCS (200° projection ranges) and PICCS (90° projection ranges). Two kinds of projection data sets-an elliptic-cylindrical digital phantom and two clinical patients' data-were used. For the digital phantom, an air sphere was contained and virtually moved along the longitudinal axis by 3 cm/30 s and 3 cm/60 s; the temporal resolution was evaluated by measuring the penumbral width of the air sphere. The clinical feasibility of the non-periodic time-ordered 4D CBCT image reconstruction was examined with the patient data in the pelvic region.

Results: In the evaluation of the digital-phantom reconstruction, the penumbral widths of the TCGM yielded the narrowest result; the results obtained by PICCS and TCGM using 90° projection ranges were 2.8% and 18.2% for 3 cm/30 s, and 5.0% and 23.1% for 3 cm/60 s narrower than that of TVCS using 200° projection ranges. This suggests that the TCGM has a better temporal resolution, whereas PICCS seems similar to TVCS. These reconstruction methods were also compared using patients' projection data sets. Although all three reconstruction results showed motion related to rectal gas or stool, the result obtained by the TCGM was visibly clearer with less blurring.

Conclusion: The TCGM is a feasible approach to visualize non-periodic organ motion. The digital-phantom results demonstrated that the proposed method provides 4D image series with a better temporal resolution compared to TVCS and PICCS. The clinical patients' results also showed that the present method enables us to visualize motion related to rectal gas and flatus in the rectum.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s13014-017-0879-8DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5584034PMC
September 2017

Effective atomic number estimation using kV-MV dual-energy source in LINAC.

Phys Med 2017 Jul 20;39:9-15. Epub 2017 Jun 20.

Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo, Tokyo 113-8655, Japan.

Dual-energy computed tomography (DECT) imaging can measure the effective atomic number (EAN) as well as the electron density, and thus its adoption may improve dose calculations in brachytherapy and external photon/particle therapy. An expanded energy gap in dual-energy sources is expected to yield more accurate EAN estimations than conventional DECT systems, which typically span less than 100kV. The aim of this paper is to assess a larger energy gap DECT by using a linear accelerator (LINAC) radiotherapy system with a kV X-ray imaging device, which are combined to provide X-rays in both the kV- and MV-energy ranges. Traditionally, the EAN is determined by parameterising the Hounsfield Unit; however, this is difficult in a kV-MV DECT due to different uncertainties in the reconstructed attenuation coefficient at each end of the energy spectrum. To overcome this problem, we included a new calibration step to produce the most likely linear attenuation coefficients, based upon the X-ray spectrum. To determine the X-ray spectrum, Monte Carlo calculations using GEANT4 were performed. Then the images were calibrated using information from eight inserts of known materials in a CIRS phantom (CIRS Inc., Norfolk, VA). Agreement between the estimated and empirical EANs in these inserts was within 11%. Validation was subsequently performed with the CatPhan500 phantom (The Phantom Laboratory, Salem). The estimated EAN for seven inserts agreed with the empirical values to within 3%. Accordingly, it can be concluded that, given properly reconstructed images based upon a well-determined X-ray spectrum, kV-MV DECT provides an excellent prediction for the EAN.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2017.06.010DOI Listing
July 2017

Evaluation of a commercial automatic treatment planning system for prostate cancers.

Med Dosim 2017 Autumn;42(3):203-209. Epub 2017 May 23.

Department of Radiology, University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan.

Recent developments in Radiation Oncology treatment planning have led to the development of software packages that facilitate automated intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT) planning. Such solutions include site-specific modules, plan library methods, and algorithm-based methods. In this study, the plan quality for prostate cancer generated by the Auto-Planning module of the Pinnacle radiation therapy treatment planning system (v9.10, Fitchburg, WI) is retrospectively evaluated. The Auto-Planning module of Pinnacle uses a progressive optimization algorithm. Twenty-three prostate cancer cases, which had previously been planned and treated without lymph node irradiation, were replanned using the Auto-Planning module. Dose distributions were statistically compared with those of manual planning by the paired t-test at 5% significance level. Auto-Planning was performed without any manual intervention. Planning target volume (PTV) dose and dose to rectum were comparable between Auto-Planning and manual planning. The former, however, significantly reduced the dose to the bladder and femurs. Regression analysis was performed to examine the correlation between volume overlap between bladder and PTV divided by the total bladder volume and resultant V70. The findings showed that manual planning typically exhibits a logistic way for dose constraint, whereas Auto-Planning shows a more linear tendency. By calculating the Akaike information criterion (AIC) to validate the statistical model, a reduction of interoperator variation in Auto-Planning was shown. We showed that, for prostate cancer, the Auto-Planning module provided plans that are better than or comparable with those of manual planning. By comparing our results with those previously reported for head and neck cancer treatment, we recommend the homogeneous plan quality generated by the Auto-Planning module, which exhibits less dependence on anatomic complexity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.meddos.2017.03.004DOI Listing
May 2018

Adequate target volume in total-body irradiation by intensity-modulated radiation therapy using helical tomotherapy: a simulation study.

J Radiat Res 2017 Mar;58(2):210-216

Department of Radiology, University of Tokyo Hospital, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.

Recently, intensity-modulated radiation therapy (IMRT) has been used for total-body irradiation (TBI). Since the planning target volume (PTV) for TBI includes the surrounding air, a dose prescription to the PTV provides high fluence to the body surface. Thus with just a small set-up error, the body might be exposed to a high-fluence beam. This study aims to assess which target volume should be prescribed the dose, such as a clinical target volume (CTV) with a margin, or a CTV that excludes the surface area of the skin. Three treatment plans were created for each patient: the 5-mm clipped plan (Plan A), the 0-mm margin plan (Plan B) and the 5-mm margin plan (Plan C). The CTV was the whole body. PTVs were the CTV with the exception of 5 mm from the skin surface in Plan A, equal to the CTV in Plan B, and the CTV with a 5 mm margin in Plan C. The prescribed dose was 12 Gy in six fractions. To assess the influence of the set-up error, dose distributions were simulated on computed tomography (CT) images shifted 2 pixels (= 4.296 mm), 5 pixels (= 10.74 mm) and 10 pixels (= 21.48 mm) in the lateral direction from the original CT. With a set-up error of 10.74 mm, V110% was 8.8%, 11.1% and 23.3% in Plans A, B and C, respectively. The prescription to the PTV containing the surrounding air can be paradoxically vulnerable to a high-dose as a consequence of a small set-up error.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/jrr/rrw115DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5439372PMC
March 2017

Evaluation of In Vivo Volumetric Dosimetry for Prostate Cancer Using Electronic Portal Imaging Device.

Nihon Hoshasen Gijutsu Gakkai Zasshi 2016 ;72(11):1128-1136

Department of Radiology, University of Tokyo Hospital.

Purpose: Volumetric modulated arc therapy (VMAT) is capable of acquiring projection images using electronic portal imaging device (EPID). Commercial EPID-based dosimetry software, dosimetry check (DC), allows in vivo dosimetry using projection images. The purpose of this study was to evaluate in vivo dosimetry for prostate cancer using VMAT.

Method: VMAT plans were generated for eight patients with prostate cancer using treatment planning system (TPS), and patient quality assurances (QAs) were carried out with phantom. We analyzed five plans as phantom study and five plans as patient study. Projection images were acquired during VMAT delivery. DC converted acquired images into fluence images and used a pencil beam algorithm to calculate dose distributions delivered on the CT images of the phantom and the patients. We evaluated isocenter point doses and gamma analysis in both studies and dose indexes of planning target volume (PTV), bladder and rectum in patient study.

Results And Discussion: Dose differences at the isocenter were less than a criterion in both studies. Pass rates of the gamma analysis were less than a criterion by two plans in the phantom study. Dose indexes of reconstructed distribution were lower than original plans and standard deviations of PTV in reconstructed distribution were larger than original plans. The errors were caused by some issues, such as the commissioning of DC, variations in patient anatomy, and patient positioning.

Conclusion: The method was feasible to non-invasively perform in vivo dose evaluation for prostate cancer using VMAT.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.6009/jjrt.2016_JSRT_72.11.1128DOI Listing
April 2017
-->