Search

Catheterization for structural heart disease (SHD) requires fluoroscopic guidance, which exposes health care professionals to radiation exposure risk. Nevertheless, existing freestanding radiation shields for anesthesiologists are typically simple, uncomfortable rectangles. Therefore, we devised a new perforated radiation shield that allows anesthesiologists and echocardiographers to access a patient through its apertures during SHD catheterization. No report of the relevant literature has described the degree to which the anesthesiologist’s radiation dose can be reduced by installing radiation shields. For estimating whole-body doses to anesthesiologists and air dose distributions in the operating room, we used a Monte Carlo system for a rapid dose-estimation system used with interventional radiology. The simulations were performed under four conditions: no radiation shield, large apertures, small apertures and without apertures. With small apertures, the doses to the lens, waist and neck surfaces were found to be comparable to those of a protective plate without an aperture, indicating that our new radiation shield copes with radiation protection and work efficiency. To simulate the air-absorbed dose distribution, results indicated that a fan-shaped area of the dose rate decrease was generated in the area behind the shield, as seen from the tube sphere. For the aperture, radiation was found to wrap around the backside of the shield, even at a height that did not match the aperture height. The data presented herein are expected to be of interest to all anesthesiologists who might be involved in SHD catheterization. The data are also expected to enhance their understanding of radiation exposure protection.

The questionnaire survey was conducted in 2020 to investigate the working conditions of qualified medical physicists in Japan. We developed a web-based system for administering the questionnaire and surveyed 1,228 qualified medical physicists. The number of received responses was 405. We summarized the results of the survey by job category. The obtained results showed that most of the people working as certified medical physicists met the following conditions: (1) position of healthcare occupation, (2) direct supervisor is a medical doctor or a medical physicist, (3) licensed or passed an examination for a Class I Radiation Protection Supervisor, (4) without the license of professional radiotherapy technologist, (5) master's or doctor's degree, (6) being assigned to the section that is different from the radiological technologist section. The average annual salary was approximately 600,000 yen higher for those employed as medical physicists than for those employed as radiotherapy technologists. The percentage of work performed by a certified medical physicist in radiation therapy greatly varies depending on whether the physicist is dedicated to treatment planning and equipment quality control. Alternatively, the proportion of the true duties of medical physicists in charge of radiation therapy, as considered by qualified medical physicists in radiation therapy, was the same regardless of whether they were working full-time or not. The results of this survey updated the working status of certified medical physicists in Japan. We will continue to conduct the survey periodically and update the information to contribute to the improvement of the working conditions of medical physicists and policy recommendations.

Background To accurately diagnose and control heart failure (HF), it is important to carry out a simple assessment of elevated pulmonary arterial wedge pressure (PAWP). The aim of this study was to develop and validate an objective method for detecting elevated PAWP by applying deep learning (DL) to a chest x-ray (CXR). Methods We enrolled 1013 consecutive patients with a right-heart catheter between October 2009 and February 2020. We developed a convolutional neural network to identify patients with elevated PAWP (> 18 mm Hg) as the actual value of PAWP to be used in the dataset for training. In the prospective validation dataset used to detect elevated PAWP, the area under the receiver operating characteristic curve (AUC) was calculated using the DL model that evaluated the CXR. Results In the prospective validation dataset, the AUC of the DL model with CXR was not significantly different from the AUC produced by brain natriuretic peptide (BNP) and the echocardiographic left-ventricular diastolic dysfunction (DD) algorithm (DL model: 0.77 vs BNP: 0.77 vs DD algorithm: 0.70; respectively; P = NS for all comparisons); it was, however, significantly higher than the AUC of the cardiothoracic ratio (DL model vs cardiothoracic ratio [CTR]: 0.66, P = 0.044). The model based on 3 parameters (BNP, DD algorithm, and CTR) was improved by adding the DL model (AUC: from 0.80 to 0.86; P = 0.041). Conclusions Applying the DL model based on a CXR (a classical, universal, and low-cost test) is useful for screening for elevated PAWP.

Stem cell‐based products have clinical and industrial applications. Thus, there is a need to develop quality control methods to standardize stem cell manufacturing. Here, we report a deep learning‐based automated cell tracking (DeepACT) technology for noninvasive quality control and identification of cultured human stem cells. The combination of deep learning‐based cascading cell detection and Kalman filter algorithm‐based tracking successfully tracked the individual cells within the densely packed human epidermal keratinocyte colonies in the phase‐contrast images of the culture. DeepACT rapidly analyzed the motion of individual keratinocytes, which enabled the quantitative evaluation of keratinocyte dynamics in response to changes in culture conditions. Furthermore, DeepACT can distinguish keratinocyte stem cell colonies from non‐stem cell‐derived colonies by analyzing the spatial and velocity information of cells. This system can be widely applied to stem cell cultures used in regenerative medicine and provides a platform for developing reliable and noninvasive quality control technology., A deep learning‐based automated cell tracking (DeepACT) technology enables the evaluation of keratinocyte culture quality and the identification of keratinocyte stem cells using quantitative cell motion analysis. DeepACT comprises two main modules: identifying human keratinocytes at single‐cell resolution from phase‐contrast images of cultures through deep learning and tracking keratinocyte motion in the colony using a state‐space model.

Objective The accuracy of identifying a CRT-response by a pre-operative radiological examination is limited, and another approach is necessary. We constructed endoscopic image-based radiomics classifiers to predict the response of locally advanced rectal cancers (LARCs) to neoadjuvant chemotherapy (NA-CRT). Design: We enrolled 90 patients who had undergone NA-CRT followed by surgery. We selected 5,255 pre- and post-CRT endoscopic images of the tumors and extracted 860 texture features from each image. Using the extracted texture features, we applied 12 machine learning models to construct radiomics classifiers. The performances of the radiomics classifiers to predict a pathological complete response (pCR) and a CRT-response (good or not) were evaluated with a double cross-validation technique by calculating the area under the receiver operating characteristics curve (AUROC). Results In the prediction of pCR using pre-CRT images, the cubic support vector machine (SVM) model showed the highest AUROC of 0.816 in the image-basis analysis, and the AUROC of 0.904 in the patient-basis analysis. In the prediction of pCR using post-CRT images, the quadratic SVM model showed the highest AUROC (0.839) in the image-basis analysis, and the AUROC of 0.958 in the patient-basis analysis. The Gaussian SVM model demonstrated the best performances to predict a CRT-response in both pre- and post-CRT images with AUROCs of 0.792 and 0.841 in the image-basis analysis and 0.857 and 0.950 in the patient-basis analysis, respectively. Conclusion Our endoscopic image-based radiomics classifiers demonstrated robust performances to predict the CRT-response of LARCs and may contribute to the patients' management.

Accurate diagnosis of pulmonary hypertension (PH) is crucial to ensure that patients receive timely treatment. We hypothesized that application of artificial intelligence (AI) to the chest X-ray (CXR) could identify elevated pulmonary artery pressure (PAP) and stratify the risk of heart failure hospitalization with PH. We retrospectively enrolled a total of 900 consecutive patients with suspected PH. We trained a convolutional neural network to identify patients with elevated PAP (> 20 mmHg) as the actual value of PAP. The endpoints in this study were admission or occurrence of heart failure with elevated PAP. In an independent evaluation set for detection of elevated PAP, the area under curve (AUC) by the AI algorithm was significantly higher than the AUC by measurements of CXR images and human observers (0.71 vs. 0.60 and vs. 0.63, all p

The purpose of this study was to evaluate the accuracy of the convolutional neural network (CNN) model in glaucoma identification with three primary colors (red, green, blue; RGB) and split color channels using fundus photographs with a small sample size. The dataset was prepared using color fundus photographs captured with a fundus camera (VX-10i, Kowa Co., Ltd., Tokyo, Japan). The training dataset consisted of 200 images, and the validation dataset contained 60 images. In the preprocessing stage, the color channels for the fundus images were separated into red (red model), green (green model), and blue (blue model) using OpenCV on Windows. All images were resized to squares with a size of 512 × 512 pixels for preprocessing before input into the model, and the model was fine-tuned with VGG16. The diagnostic performance was significantly higher in the green model [area under the curve (AUC) 0.946; 95% confidence interval (CI) 0.851–0.982] than in the RGB model (AUC 0.800; 95% CI 0.658–0.893; P = 0.006), red model (AUC 0.746; 95% CI 0.601–0.851; P = 0.002), and blue model (AUC 0.558; 95% CI 0.405–0.700; P

Background Classification of optical coherence tomography (OCT) images can be achieved with high accuracy using classical convolution neural networks (CNN), a commonly used deep learning network for computer-aided diagnosis. Classical CNN has often been criticized for suppressing positional relations in a pooling layer. Therefore, because capsule networks can learn positional information from images, we attempted application of a capsule network to OCT images to overcome that shortcoming. This study is our attempt to improve classification accuracy by replacing CNN with a capsule network. Methods From an OCT dataset, we produced a training dataset of 83,484 images and a test dataset of 1000 images. For training, the dataset comprises 37,205 images with choroidal neovascularization (CNV), 11,348 with diabetic macular edema (DME), 8616 with drusen, and 26,315 normal images. The test dataset has 250 images from each category. The proposed model was constructed based on a capsule network for improving classification accuracy. It was trained using the training dataset. Subsequently, the test dataset was used to evaluate the trained model. Results Classification of OCT images using our method achieved accuracy of 99.6%, which is 3.2 percentage points higher than that of other methods described in the literature. Conclusion The proposed method achieved classification accuracy results equivalent to those reported for other methods for CNV, DME, drusen, and normal images.

Purpose To share the experience of an iridium-192 (192Ir) source stuck event during high-dose-rate (HDR) brachytherapy for cervical cancer. Material and methods In 2014, we experienced the first source stuck event in Japan when treating cervical cancer with HDR brachytherapy. The cause of the event was a loose screw in the treatment device that interfered with the gear reeling the source. This event had minimal clinical effects on the patient and staff; however, after the event, we created a normal treatment process and an emergency process. In the emergency processes, each staff member is given an appropriate role. The dose rate distribution calculated by the new Monte Carlo simulation system was used as a reference to create the process. Results According to the calculated dose rate distribution, the dose rates inside the maze, near the treatment room door, and near the console room were ≅ 10-2 [cGy · h-1], 10-3 [cGy · h-1], and << 10-3 [cGy · h-1], respectively. Based on these findings, in the emergency process, the recorder was evacuated to the console room, and the rescuer waited inside the maze until the radiation source was recovered. This emergency response manual is currently a critical workflow once a year with vendors. Conclusions We reported our experience of the source stuck event. Details of the event and proposed emergency process will be helpful in managing a patient safety program for other HDR brachytherapy users.

Purpose: To evaluate the influence of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) on proton density fat fraction (PDFF) using multiple vendors’ DIXON methods in a multicenter, multivendor phantom study. Materials and Methods: Pairs of phantoms with varying fat volume percentages (0, 5, 10, 15, 20, 30, 40, and 50) and Gd-EOB-DTPA concentrations (0 and 0.4 mM) were constructed. The phantom without Gd-EOB-DTPA in each pair was defined as the precontrast phantom, and the corresponding phantom with Gd-EOB-DTPA in each pair was defined as the postcontrast phantom. The phantoms were scanned via three vendors’ DIXON techniques to determine PDFFs. Agreement between PDFFs determined in precontrast and postcontrast phantoms was evaluated via Bland–Altman analysis. Results: Mean differences (precontrast PDFF - postcontrast PDFF) and limits of agreement were Philips 5.1% (−0.8% to 11.0%), Siemens 6.1% (−0.9% to 13.1%), and GE 1.3% (−1.2% to 3.9%). Conclusions: PDFFs measured using the three vendors’ DIXON techniques were smaller in the postcontrast phantoms than in the corresponding precontrast phantoms regardless of different scanning parameters, because T1 bias was improved by Gd-EOB-DTPA.

For interventional radiology (IR), understanding the precise dose distribution is crucial to reduce the risks of radiation dermatitis to patients and staff. Visualization of dose distribution is expected to support radiation safety efforts immensely. This report presents techniques for perceiving the dose distribution using virtual reality (VR) technology and for estimating the air dose distribution accurately using Monte Carlo simulation for VR dose visualization. We adopted an earlier reported Monte-Carlo-based estimation system for IR and simulated the dose in a geometrical area resembling an IR room with fluoroscopic conditions. Users of our VR system experienced a simulated air dose distribution in the IR room while the irradiation angle, irradiation timing, and lead shielding were controlled. The estimated air dose was evaluated through comparison with measurements taken using a radiophotoluminescence glass dosimeter. Our dose estimation results were consistent with dosimeter readings, showing a 13.5% average mutual difference. The estimated air dose was visualized in VR: users could view a virtual IR room and walk around in it. Using our VR system, users experienced dose distribution changes dynamically with C-arm rotation. Qualitative tests were conducted to evaluate the workload and usability of our VR system. The perceived overall workload score (18.00) was lower than the scores reported in the literature for medical tasks (50.60) and computer activities (54.00). This VR visualization is expected to open new horizons for understanding dose distributions intuitively, thereby aiding the avoidance of radiation injury.

We sought to verify the reliability of machine learning (ML) in developing diabetes prediction models by utilizing big data. To this end, we compared the reliability of gradient boosting decision tree (GBDT) and logistic regression (LR) models using data obtained from the Kokuho-database of the Osaka prefecture, Japan. To develop the models, we focused on 16 predictors from health checkup data from April 2013 to December 2014. A total of 277,651 eligible participants were studied. The prediction models were developed using a light gradient boosting machine (LightGBM), which is an effective GBDT implementation algorithm, and LR. Their reliabilities were measured based on expected calibration error (ECE), negative log-likelihood (Logloss), and reliability diagram. Similarly, their classification accuracies were measured in the area under the curve (AUC). We further analyzed their reliabilities while changing the sample size for training. Among the 277,651 participants, 15,900 (7978 males and 7922 females) were newly diagnosed with diabetes within three years. LightGBM (LR) achieved an ECE of 0.0017±0.00033 (0.0048±0.00058), a Logloss of 0.167±0.00062 (0.172±0.00090), and an AUC of 0.845±0.0025 (0.826±0.0035). From sample size analysis, the reliability of LightGBM became higher than that of LR when the sample size increased more than 10^4. Thus, we confirmed that GBDT provides a more reliable model than LR in the development of diabetes prediction models using big data. ML could potentially produce a highly reliable diabetes prediction model, a helpful tool for improving lifestyle and preventing diabetes.

BackgroundStress echocardiography is an emerging tool used to detect exercise-induced pulmonary hypertension (EIPH). However, facilities that can perform stress echocardiography are limited by issues such as cost and equipment.ObjectiveWe evaluated the usefulness of a deep learning (DL) approach based on a chest X-ray (CXR) to predict EIPH in 6-min walk stress echocardiography.MethodsThe study enrolled 142 patients with scleroderma or mixed connective tissue disease with scleroderma features who performed a 6-min walk stress echocardiographic test. EIPH was defined by abnormal cardiac output (CO) responses that involved an increase in mean pulmonary artery pressure (mPAP). We used the previously developed AI model to predict PH and calculated PH probability in this cohort.ResultsEIPH defined as ΔmPAP/ΔCO >3.3 and exercise mPAP >25 mmHg was observed in 52 patients, while non-EIPH was observed in 90 patients. The patients with EIPH had a higher mPAP at rest than those without EIPH. The probability of PH based on the DL model was significantly higher in patients with EIPH than in those without EIPH. Multivariate analysis showed that gender, mean PAP at rest, and the probability of PH based on the DL model were independent predictors of EIPH. A model based on baseline parameters (age, gender, and mPAP at rest) was improved by adding the probability of PH predicted by the DL model (AUC: from 0.65 to 0.74; p = 0.046).ConclusionApplying the DL model based on a CXR may have a potential for detection of EIPH in the clinical setting.

For interventional radiology, dose management has persisted as a crucially important issue to reduce radiation exposure to patients and medical staff. This study designed a real-time dose visualization system for interventional radiology designed with mixed reality technology and Monte Carlo simulation. An earlier report described a Monte-Carlo-based estimation system, which simulates a patient’s skin dose and air dose distributions, adopted for our system. We also developed a system of acquiring fluoroscopic conditions to input them into the Monte Carlo system. Then we combined the Monte Carlo system with a wearable device for three-dimensional holographic visualization. The estimated doses were transferred sequentially to the device. The patient’s dose distribution was then projected on the patient body. The visualization system also has a mechanism to detect one’s position in a room to estimate the user’s exposure dose to detect and display the exposure level. Qualitative tests were conducted to evaluate the workload and usability of our mixed reality system. An end-to-end system test was performed using a human phantom. The acquisition system accurately recognized conditions that were necessary for real-time dose estimation. The dose hologram represents the patient dose. The user dose was changed correctly, depending on conditions and positions. The perceived overall workload score (33.50) was lower than the scores reported in the literature for medical tasks (50.60) for computer activities (54.00). Mixed reality dose visualization is expected to improve exposure dose management for patients and health professionals by exhibiting the invisible radiation exposure in real space. Supplementary Information The online version of this article (10.1007/s10916-020-01700-9) contains supplementary material, which is available to authorized users.

A novel application of machine-learning (ML) based image processing algorithms is proposed to analyze an all-sky map (ASM) obtained using the Fermi Gamma-ray Space Telescope. An attempt was made to simulate a one-year ASM from a short-exposure ASM generated from one-week observation by applying three ML based image processing algorithms: dictionary learning, U-net, and Noise2Noise. Although the inference based on ML is less clear compared to standard likelihood analysis, the quality of the ASM was generally improved. In particular, the complicated diffuse emission associated with the galactic plane was successfully reproduced only from one-week observation data to mimic a ground truth (GT) generated from a one-year observation. Such ML algorithms can be implemented relatively easily to provide sharper images without various assumptions of emission models. In contrast, large deviations between simulated ML maps and GT map were found, which are attributed to the significant temporal variability of blazar-type active galactic nuclei (AGNs) over a year. Thus, the proposed ML methods are viable not only to improve the image quality of an ASM, but also to detect variable sources, such as AGNs, algorithmically, i.e., without human bias. Moreover, we argue that this approach is widely applicable to ASMs obtained by various other missions; thus, it has the potential to examine giant structures and transient events, both of which are rarely found in pointing observations., Comment: 12 pages, 11 figures, accepted for publication in ApJ

Out‐of‐field organs are not commonly designated as dose calculation targets during radiation therapy treatment planning, but they might entail risks of second cancer. Risk components include specific internal body scatter, which is a dominant source of out‐of‐field doses, and head leakage, which can be reduced by external shielding. Our simulation study quantifies out‐of‐field organ doses and estimates second cancer risks attributable to internal body scatter in whole‐breast radiotherapy (WBRT) with or without additional regional nodal radiotherapy (RNRT), respectively, for right and left breast cancer using Monte Carlo code PHITS. Simulations were conducted using a complete whole‐body female model. Second cancer risk was estimated using the calculated doses with a concept of excess absolute risk. Simulation results revealed marked differences between WBRT alone and WBRT plus RNRT in out‐of‐field organ doses. The ratios of mean doses between them were as large as 3.5–8.0 for the head and neck region and about 1.5–6.6 for the lower abdominal region. Potentially, most out‐of‐field organs had excess absolute risks of less than 1 per 10,000 persons‐year. Our study surveyed the respective contributions of internal body scatter to out‐of‐field organ doses and second cancer risks in breast radiotherapy on this intact female model.

Introduction: Chest X-ray (CXR) is a useful and economical modality for the detection of congestive heart failure. However, the accuracy is limited by the subjective nature of its interpretation. Deep learning (DL) can be used to recognize diseases or findings objectively in various imaging modalities, and may outperform previous diagnostic techniques. Hypothesis: We hypothesized that DL-based analysis of CXR detect the presence of elevated pulmonary arterial wedge pressure (PAWP) in patients with suspected heart failure. Methods: We enrolled 1,013 patients with paired right heart catheterization and CXR performed from October 2009 to February 2020 in our hospital. DL algorithm for the detection of elevated PAWP was developed using the training dataset, based on a single CXR image. Independent evaluation cohort of 115 patients was performed using CXR-based DL model and echocardiographic data to detect the presence of high PAWP. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the DL-based models compared with echocardiographic data. Results: The study included 1,013 patients (mean age, 67±13 years; 569 males [56%]). The mean PAWP was 12.5±6.4 mmHg and 218 patients (22%) had more than 18mmHg. To detect high PAWP, the AUC produced by DL algorithms was effective, and the DL algorithm with the largest AUC was ResNet50. In an evaluation cohort, to detect high PAWP, the AUC using the DL model with CXR was similar to the AUC produced by the echocardiographic left ventricular diastolic dysfunction algorithm (0.77 vs. 0.70; respectively; p=0.27), and significantly higher than the AUC by measurements of echocardiographic parameters (ResNet50 vs. other parameters; all compared p (Figure) . Conclusions: The present results demonstrated that DL based on analysis of CXR can detect the presence of high PAWP. This finding suggests that the DL based approach may support an objective evaluation of CXR in the clinical setting.

Background Early detection of pulmonary hypertension (PH) is crucial to ensure that patients receive timely treatment for the progressive clinical course. The chest X-ray (CXR), a routine method at hospitals, has recommended in order to reveal features supportive of a diagnosis of PH. However, it is well known that the sensitivity and specificity are low. Purpose We tested the hypothesis that application of artificial intelligence (AI) to the CXR could identify PH. Methods We retrospectively enrolled 900 data with paired CXR and right heart catheter (RHC), including the pulmonary artery pressure, from October 2009 to December 2018. We trained a convolutional neural network to identify patients with PH as actual value of pulmonary artery pressure, using the CXR alone (Figure). The diagnosis of PH was performed using hemodynamic measurements according to the most recent World Symposium standards: mean PAP ≥20 mmHg. We have compared the area under the curve (AUC) by human observers, measurements of CXR images, and AI for detection of PH. Results Subjects were divided into two groups with PH (439 patients; mean age, 66±14 years; 233 male) and without PH (461 patients; mean age, 68±12 years; 278 male). In an independent set, AI was the highest diagnostic ability for detection of PH (AUC: 0.71). The AUC by the AI algorithm was significantly higher than the AUC by measurements of CXR images and human observers (0.71 vs. 0.60 and vs. 0.63, all compared p Conclusion Applying AI to the CXR (a classical, universal, low-cost test) permits the CXR images to serve as a powerful tool to screen for PH. Neural network Funding Acknowledgement Type of funding source: None

This manuscript is a supplement to the machine learning course at JSMP Medical Physics Summer School held in 2019. The idea of Kulbuck-Leibler divergence, a key concept in machine learning, is introduced with mutual information.

This study was conducted to improve cone-beam computed tomography (CBCT) image quality using the super-resolution technique, a method of inferring a high-resolution image from a low-resolution image. This technique is used with two matrices, so-called dictionaries, constructed respectively from high-resolution and low-resolution image bases. For this study, a CBCT image, as a low-resolution image, is represented as a linear combination of atoms, the image bases in the low-resolution dictionary. The corresponding super-resolution image was inferred by multiplying the coefficients and the high-resolution dictionary atoms extracted from planning CT images. To evaluate the proposed method, we computed the root mean square error (RMSE) and structural similarity (SSIM). The resulting RMSE and SSIM between the super-resolution images and the planning CT images were, respectively, as much as 0.81 and 1.29 times better than those obtained without using the super-resolution technique. We used super-resolution technique to improve the CBCT image quality.

Low-count SPECT images are well known to be smoothed strongly by a Butterworth filter for statistical noise reduction. Reconstructed images have a low signal-to-noise ratio (SNR) and spatial resolution because of the removal of high-frequency signal components. Using the developed robust adaptive bilateral filter (RABF), which was designed as a pre-stage filter of the Butterworth filter, this study was conducted to improve SNR without degrading the spatial resolution for low-count SPECT imaging. The filter can remove noise while preserving spatial resolution. To evaluate the proposed method, we extracted SNR and spatial resolution in a phantom study. We also conducted paired comparison for visual image quality evaluation in a clinical study. Results show that SNR was increased 1.4 times without degrading the spatial resolution. Visual image quality was improved significantly (p < 0.01) for clinical low-count data. Moreover, the accumulation structure became sharper. A structure embedded in noise emerged. Our method, which denoises without degrading the spatial resolution for low-count SPECT images, is expected to increase the effectiveness of diagnosis for low-dose scanning and short acquisition time scanning.

To minimise the radiation dermatitis related to interventional radiology (IR), rapid and accurate dose estimation has been sought for all procedures. We propose a technique for estimating the patient skin dose rapidly and accurately using Monte Carlo (MC) simulation with a graphical processing unit (GPU, GTX 1080; Nvidia Corp.). The skin dose distribution is simulated based on an individual patient’s computed tomography (CT) dataset for fluoroscopic conditions after the CT dataset has been segmented into air, water and bone based on pixel values. The skin is assumed to be one layer at the outer surface of the body. Fluoroscopic conditions are obtained from a log file of a fluoroscopic examination. Estimating the absorbed skin dose distribution requires calibration of the dose simulated by our system. For this purpose, a linear function was used to approximate the relation between the simulated dose and the measured dose using radiophotoluminescence (RPL) glass dosimeters in a water-equivalent phantom. Differences of maximum skin dose between our system and the Particle and Heavy Ion Transport code System (PHITS) were as high as 6.1%. The relative statistical error (2 σ) for the simulated dose obtained using our system was ≤3.5%. Using a GPU, the simulation on the chest CT dataset aiming at the heart was within 3.49 s on average: the GPU is 122 times faster than a CPU (Core i7–7700K; Intel Corp.). Our system (using the GPU, the log file, and the CT dataset) estimated the skin dose more rapidly and more accurately than conventional methods.

The purpose of this study is to evaluate the accuracy for classification of hepatic tumors by characterization of T1-weighted magnetic resonance (MR) images using two radiomics approaches with machine learning models: texture analysis and topological data analysis using persistent homology. This study assessed non-contrast-enhanced fat-suppressed three-dimensional (3D) T1-weighted images of 150 hepatic tumors. The lesions included 50 hepatocellular carcinomas (HCCs), 50 metastatic tumors (MTs), and 50 hepatic hemangiomas (HHs) found respectively in 37, 23, and 33 patients. For classification, texture features were calculated, and also persistence images of three types (degree 0, degree 1 and degree 2) were obtained for each lesion from the 3D MR imaging data. We used three classification models. In the classification of HCC and MT (resp. HCC and HH, HH and MT), we obtained accuracy of 92% (resp. 90%, 73%) by texture analysis, and the highest accuracy of 85% (resp. 84%, 74%) when degree 1 (resp. degree 1, degree 2) persistence images were used. Our methods using texture analysis or topological data analysis allow for classification of the three hepatic tumors with considerable accuracy, and thus might be useful when applied for computer-aided diagnosis with MR images.

X-ray computed tomography (CT) has been widely used in medical diagnostic imaging. However, conventional, energy-integrated CT requires a high radiation dose and can only provide monochromatic images that cannot eliminate various artifacts. In contrast, photon-counting CT (PC-CT) provides low-dose multicolor CT imaging, which enables the identification of multiple contrast agents. However, in the PC-CT system, the lack of photon statistics, which is also caused by image reconstruction in the limited energy band, severely affects the image quality. In this study, we applied three types of machine-learning (ML) techniques to improved the image quality of PC-CT, that is, dictionary learning, U-Net, and Noise2Noise. These ML models were trained using low- and high-dose image pairs created in simple steps. The trained ML models were applied to simulated data, and experimental PC-CT images of contrast agents used in clinical practice. Consequently, in the simulated data, the peak signal-to-noise ratio (PSNR) value improved from 21.3 for the input to 26.6, 33.3, and 30.1 for dictionary learning, U-Net, and Noise2Noise, respectively. Furthermore, in the actual PC-CT images, we successfully reproduced PC-CT images with high PSNR, which enabled simultaneous imaging of multiple contrast agents with improved accuracy of concentration estimation. As a future perspective, we will develop a processing technique that can be applied to in vivo CT images.

To identify predictive factors for embolic material conversion to N-butyl cyanoacrylate (NBCA) for the treatment of primary postpartum hemorrhage (PPH) after failed transcatheter arterial embolization (TAE) using gelatin sponge (GS). Institutional review board approval was obtained. We retrospectively studied 62 consecutive women with primary PPH who underwent TAE between January 2006 and March 2015. Five of them were excluded for the following: cardiopulmonary arrest at arrival (n = 1), uterine inversion (n = 1), and hysterectomy after TAE (n = 3). Remaining 57 women (age range, 21–43 years; mean, 32.6 years) comprised study population. TAE was initially performed using GS in all cases and then converted to NBCA after two embolizations using GS with persistent hemodynamic instability or vaginal bleeding. The patients’ background, uterine height, vital signs, laboratory tests, disseminated intravascular coagulation score, and details of procedure were reviewed. Univariate and multivariate analyses were performed to determine factors related to embolic material conversion. Technical success rate was 100%. Fourteen patients (25%) needed embolic material conversion to NBCA. Univariate analysis showed that uterine height, systolic blood pressure (sBP), and hemoglobin level were significantly related to embolic material conversion to NBCA (P = 0.029, 0.030, and 0.042). Logistic regression analysis showed that uterine height (odds ratio, 1.37; P = 0.025) and sBP (odds ratio, 0.96; P = 0.003) were associated with embolic material conversion to NBCA. Uterine height and sBP can be predictive factors for embolic material conversion to NBCA for the treatment of PPH. Level 4, Case Control Study

The realization of automatic anomaly detection of respiratory motion could be very useful to prevent accidental damage during radiation therapy. In this paper, we proposed an automatic anomaly detection method using singular value decomposition analysis. Before applying this method, the investigator needs a normal respiratory motion data of a patient. From these data, a trajectory matrix representing normal time-series feature is created. Decomposing the matrix, we obtained the feature of normal time series. Then, we applied the same procedure to real-time data and obtained real-time features. Calculating the similarity of those feature matrixes, an anomaly score was obtained. Patient motion was observed by a depth camera. In our simulation, two types of motion e.g. cough and sudden stop of breathing were successfully detected, while gradual change of respiratory cycle frequency was not detected clearly.

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.

In medical imaging, precise and reliable images are very important. However, the quality of medical images is sometimes limited by low-event statistics owing to the low sensitivity of the detectors commonly used in radiology. On the other hand, long exposure to radiation and long inspection duration can become a burden for patients. In this paper, we propose a method for generating high-quality images of gamma ray sources from low statistic data by using machine learning methods based on dictionary learning and sparse coding. As the first application, we generated a high-quality image of 137Cs, which emits 662-keV gamma rays, from low-event statistics measured using a Compton camera. We simulated with Geant4 various geometries of the gamma-ray source (137Cs; 662 keV) as measured with a Compton camera by Geant4. Then, complete sets of low-resolution and high-resolution dictionaries were prepared. We generated super-resolution images from low-resolution test images obtained from actual measurements. The convergence of the gamma-ray images was similar for both the ground truth and predicted images, as supported by the improvements in the structural similarity (SSIM), peak signal-to-noise (PSNR) ratio, and root mean square error (RMSE) in the corresponding images. We also discuss future plans to use the super-resolution technique for visualizing radium chloride (223RaCl2) in the patient’s body, which will make it possible to achieve in-vivo imaging of alpha-particle internal therapy for the first time.

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 (pCTr). Next, a 39-layer DCNN model was trained to learn a direct mapping from the CBCT to the corresponding pCTr images. 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 pCTr 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.

A diameter of glass bottles in phantoms in the above article (2 cm) was incorrect. The correct diameter is 4.5 cm.

This phantom study assessed the effect of Gd-EOB-DTPA on T1 bias (difference in T1 between water and fat) of the proton density fat fraction when using magnetic resonance spectroscopy. Phantoms containing varying fat percentages, without and with Gd-EOB-DTPA (precontrast and postcontrast, respectively), were scanned with repetition times ranging from 1000 to 5000 ms. The relationship between the proton density fat fraction at a reference repetition time of 5000 ms and that using different repetition times, was evaluated in the precontrast and postcontrast phantoms using linear regression and Bland–Altman analyses. In the precontrast phantom, as the repetition time increased, the slope tended to approach one. In the postcontrast phantom, the slope and intercept were near one and zero, respectively. The mean difference was smaller in the postcontrast phantom (range − 0.24 to − 0.01%) than in the precontrast phantom (range 0.12 to 3.52%). We conclude that I1 bias is minimized by Gd-EOB-DTPA.

To use inductively coupled plasma mass spectroscopy (ICP-MS) to evaluate gadolinium accumulation in brain tissues, including the dentate nucleus (DN) and globus pallidus (GP), in subjects who received a gadolinium-based contrast agent (GBCA).Institutional review board approval was obtained for this study. Written informed consent for postmortem investigation was obtained either from the subject prior to his or her death or afterward from the subject's relatives. Brain tissues obtained at autopsy in five subjects who received a linear GBCA (GBCA group) and five subjects with no history of GBCA administration (non-GBCA group) were examined with ICP-MS. Formalin-fixed DN tissue, the inner segment of the GP, cerebellar white matter, the frontal lobe cortex, and frontal lobe white matter were obtained, and their gadolinium concentrations were measured. None of the subjects had received a diagnosis of severely compromised renal function (estimated glomerular filtration rate45 mL/min/1.73 m(2)) or acute renal failure. Fisher permutation test was used to compare gadolinium concentrations between the two groups and among brain regions.Gadolinium was detected in all specimens in the GBCA agent group (mean, 0.25 µg per gram of brain tissue ± 0.44 [standard deviation]), with significantly higher concentrations in each region (P = .004 vs the non-GBCA group for all regions). In the GBCA group, the DN and GP showed significantly higher gadolinium concentrations (mean, 0.44 µg/g ± 0.63) than other regions (0.12 µg/g ± 0.16) (P = .029).Even in subjects without severe renal dysfunction, GBCA administration causes gadolinium accumulation in the brain, especially in the DN and GP.

To assess whether an association exists between hyperintensity in the dentate nucleus (DN) on unenhanced T1-weighted magnetic resonance (MR) images and previous administration of gadolinium-based contrast agents (GBCAs) that contain different types of gadolinium chelates.The institutional review board approved this study. Written informed consent was waived because this was a retrospective study. Evaluated were 127 cases among 360 consecutive patients who underwent contrast agent-enhanced brain MR imaging. Two radiologists conducted visual evaluation and quantitative analysis on unenhanced T1-weighted MR images by using regions of interest. DN-to-cerebellum (DN/cerebellum) signal intensity ratios were calculated and the relationship between DN/cerebellum and several factors was evaluated, including the number of previous linear chelate and/or macrocyclic GBCA administrations by using a generalized additive model. The Akaike information criterion was used in model selection. Interobserver correlation was evaluated with paired t tests and the Lin concordance correlation coefficient.The images of nine patients (7.1%) showed hyperintensity in the DN. Twenty-three patients (18.1%) received linear GBCAs (median, two patients; maximum, 11 patients), 36 patients (28.3%) received macrocyclic GBCAs (median, two patients; maximum, 15 patients), 14 patients (11.0%) received both types of GBCA (linear [median, two patients; maximum, five patients] and macrocyclic [median, three patients; maximum, eight patients]), and 54 patients (42.5%) had no history of administration of gadolinium chelate. Interobserver correlation was almost perfect (0.992 [95% confidence interval: 0.990, 0.994]). The DN/cerebellum ratio was associated with linear GBCA (P.001), but not with macrocyclic GBCA exposure (P = .875). According to the Akaike information criterion, only linear GBCA was selected for the final model, and the DN/cerebellum ratio had strong association only with linear GBCA.Hyperintensity in the DN on unenhanced T1-weighted MR images is associated with previous administration of linear GBCA, while the previous administration of macrocyclic GBCAs showed no such association.

Three-dimensional (3D) radiation dosimeter has received growing interest with the implementation of highly conformal radiotherapy treatments. Optical Computed tomography (CT) scanners have been developed for 3D quantitative measurement of optical attenuation. Malachite green and Leuco Crystal Violet (LCV) dye radiochromic gels were recently developed as radiation dosimeters in combination with optical CT scanners. Malachite green and LCV are colorless dyes and they become green or violet after irradiation, respectively. The dyes mixed with gelatin and surfactant became hardened and can be used as a 3D gel dosimeter. The radiochromic gels dosimeter with optical CT scanners provides many of desired features such as: low cost, easy to fabricate, low toxicity and fast readout. In this article, the fundamental characteristics of radiochromic gel dosimeter with optical CT scanners are reviewed.

Purpose To evaluate the reproducibility of proton density fat fraction (PDFF) and T2* in a fat-water phantom on three different 3 T MRI systems using 6-point DIXON methods. Methods A phantom which included varying fat volume percentages (true fat fraction [FF]) was scanned by three 3 T MR machines, and PDFF and T2* were measured. Results The mean difference between true FF and PDFF was small in all vendors (−2.11% to 0.41%). However, the difference ratio for T2* values was large among vendors (1.79 to 3.36). Conclusions True FF and PDFF were consistent across vendors; however, T2* varied greatly.