Web-Based Technology for Remote Viewing of Radiological Images: App Validation.

BACKGROUND: Internet technologies can create advanced and rich web-based apps that allow radiologists to easily access teleradiology systems and remotely view medical images. However, each technology has its own drawbacks. It is difficult to balance the advantages and disadvantages of these internet technologies and identify an optimal solution for the development of medical imaging apps. OBJECTIVE: This study aimed to compare different internet platform technologies for remotely viewing radiological images and analyze their advantages and disadvantages. METHODS: Oracle Java, Adobe Flash, and HTML5 were each used to develop a comprehensive web-based medical imaging app that connected to a medical image server and provided several required functions for radiological interpretation (eg, navigation, magnification, windowing, and fly-through). Java-, Flash-, and HTML5-based medical imaging apps were tested on different operating systems over a local area network and a wide area network. Three computed tomography colonography data sets and 2 ordinary personal computers were used in the experiment. RESULTS: The experimental results demonstrated that Java-, Flash-, and HTML5-based apps had the ability to provide real-time 2D functions. However, for 3D, performances differed between the 3 apps. The Java-based app had the highest frame rate of volume rendering. However, it required the longest time for surface rendering and failed to run surface rendering in macOS. The HTML5-based app had the fastest surface rendering and the highest speed for fly-through without platform dependence. Volume rendering, surface rendering, and fly-through performances of the Flash-based app were significantly worse than those of the other 2 apps. CONCLUSIONS: Oracle Java, Adobe Flash, and HTML5 have individual strengths in the development of remote access medical imaging apps. However, HTML5 is a promising technology for remote viewing of radiological images and can provide excellent performance without requiring any plug-ins.

Imaging of the small bowel: a review of current practice.

This article summarises radiological imaging of the small bowel, with an emphasis on Crohn's disease. Different imaging techniques are discussed, including the advantages and disadvantages of each modality, and radiological findings for common small bowel pathologies are described, supplemented with pictorial examples.

Radiomic prediction models for the level of Ki-67 and p53 in glioma.

OBJECTIVE: To identify glioma radiomic features associated with proliferation-related Ki-67 antigen and cellular tumour antigen p53 levels, common immunohistochemical markers for differentiating benign from malignant tumours, and to generate radiomic prediction models. METHODS: Patients with glioma, who were scanned before therapy using standard brain magnetic resonance imaging (MRI) protocols on T1 and T2 weighted imaging, were included. For each patient, regions-of-interest (ROI) were drawn based on tumour and peritumoral areas (5/10/15/20 mm), and features were identified using feature calculations, and used to create and assess logistic regression models for Ki-67 and p53 levels. RESULTS: A total of 92 patients were included. The best area under the curve (AUC) for the Ki-67 model was 0.773 for T2 weighted imaging in solid glioma (sensitivity, 0.818; specificity, 0.833), followed by a less reliable AUC of 0.773 (sensitivity, 0.727; specificity 0.667) in 20-mm peritumoral areas. The highest AUC for the p53 model was 0.709 (sensitivity, 1; specificity, 0.4) for T2 weighted imaging in 10-mm peritumoral areas. CONCLUSION: Using T2-weighted imaging, the prediction model for Ki-67 level in solid glioma tissue was better than the p53 model. The 20-mm and 10-mm peritumoral areas in the Ki-67 and p53 model, respectively, showed predictive effects, suggesting value in further research into areas without conventional MRI features.

Including mRECIST in the Metroticket 2.0 criteria improves prediction of hepatocellular carcinoma-related death after liver transplant.

BACKGROUND & AIMS: In the context of liver transplantation (LT) for hepatocellular carcinoma (HCC), prediction models are used to ensure that the risk of post-LT recurrence is acceptably low. However, the weighting that 'response to neoadjuvant therapies' should have in such models remains unclear. Herein, we aimed to incorporate radiological response into the Metroticket 2.0 model for post-LT prediction of "HCC-related death", to improve its clinical utility. METHODS: Data from 859 transplanted patients (2000-2015) who received neoadjuvant therapies were included. The last radiological assessment before LT was reviewed according to the modified RECIST criteria. Competing-risk analysis was applied. The added value of including radiological response into the Metroticket 2.0 was explored through category-based net reclassification improvement (NRI) analysis. RESULTS: At last radiological assessment prior to LT, complete response (CR) was diagnosed in 41.3%, partial response/stable disease (PR/SD) in 24.9% and progressive disease (PD) in 33.8% of patients. The 5-year rates of "HCC-related death" were 3.1%, 9.6% and 13.4% in those with CR, PR/SD, or PD, respectively (p <0.001). Log10AFP (p <0.001) and the sum of number and diameter of the tumour/s (p <0.05) were determinants of "HCC-related death" for PR/SD and PD patients. To maintain the post-LT 5-year incidence of "HCC-related death" <30%, the Metroticket 2.0 criteria were restricted in some cases of PR/SD and in all cases with PD, correctly reclassifying 9.4% of patients with "HCC-related death", at the expense of 3.5% of patients who did not have the event. The overall/net NRI was 5.8. CONCLUSION: Incorporating the modified RECIST criteria into the Metroticket 2.0 framework can improve its predictive ability. The additional information provided can be used to better judge the suitability of candidates for LT following neoadjuvant therapies. LAY SUMMARY: In the context of liver transplantation for patients with hepatocellular carcinoma, prediction models are used to ensure that the risk of recurrence after transplantation is acceptably low. The Metroticket 2.0 model has been proposed as an accurate predictor of "tumour-related death" after liver transplantation. In the present study, we show that its accuracy can be improved by incorporating information relating to the radiological responses of patients to neoadjuvant therapies.

Radiomics: from qualitative to quantitative imaging.

Historically, medical imaging has been a qualitative or semi-quantitative modality. It is difficult to quantify what can be seen in an image, and to turn it into valuable predictive outcomes. As a result of advances in both computational hardware and machine learning algorithms, computers are making great strides in obtaining quantitative information from imaging and correlating it with outcomes. Radiomics, in its two forms "handcrafted and deep," is an emerging field that translates medical images into quantitative data to yield biological information and enable radiologic phenotypic profiling for diagnosis, theragnosis, decision support, and monitoring. Handcrafted radiomics is a multistage process in which features based on shape, pixel intensities, and texture are extracted from radiographs. Within this review, we describe the steps: starting with quantitative imaging data, how it can be extracted, how to correlate it with clinical and biological outcomes, resulting in models that can be used to make predictions, such as survival, or for detection and classification used in diagnostics. The application of deep learning, the second arm of radiomics, and its place in the radiomics workflow is discussed, along with its advantages and disadvantages. To better illustrate the technologies being used, we provide real-world clinical applications of radiomics in oncology, showcasing research on the applications of radiomics, as well as covering its limitations and its future direction.

Deep Convolution Neural Network (DCNN) Multiplane Approach to Synthetic CT Generation From MR images-Application in Brain Proton Therapy.

PURPOSE: The first aim of this work is to present a novel deep convolution neural network (DCNN) multiplane approach and compare it to single-plane prediction of synthetic computed tomography (sCT) by using the real computed tomography (CT) as ground truth. The second aim is to demonstrate the feasibility of magnetic resonance imaging (MRI)-based proton therapy planning for the brain by assessing the range shift error within the clinical acceptance threshold. METHODS AND MATERIALS: The image database included 15 pairs of MRI/CT scans of the head. Three DCNNs were trained to estimate, for each voxel, the Hounsfield unit (HU) value from MRI intensities. Each DCNN gave an estimation in the axial, sagittal, and coronal plane, respectively. The median HU among the 3 values was selected to build the sCT. The sCT/CT agreement was evaluated by a mean absolute error (MAE) and mean error, computed within the head contour and on 6 different tissues. Dice similarity coefficients were calculated to assess the geometric overlap of bone and air cavities segmentations. A 3-beam proton therapy plan was simulated for each patient. Beam-by-beam range shift (RS) analysis was conducted to assess the proton-stopping power estimation. RS analysis was performed using clinically accepted thresholds of (1) 3.5% + 1 mm and (2) 2.5% + 1.5 mm of the total range. RESULTS: DCNN multiplane statistically outperformed single-plane prediction of sCT (P < .025). MAE and mean error within the head were 54 ± 7 HU and -4 ± 17 HU (mean ± standard deviation), respectively. Soft tissues were very close to perfect agreement (11 ± 3 HU in terms of MAE). Segmentation of air and bone regions led to a Dice similarity coefficient of 0.92 ± 0.03 and 0.93 ± 0.02, respectively. Proton RS was always below clinical acceptance thresholds, with a relative RS error of 0.14% ± 1.11%. CONCLUSIONS: The multiplane DCNN approach significantly improved the sCT prediction compared with other DCNN methods presented in the literature. The method was demonstrated to be highly accurate for MRI-only proton planning purposes.

2016 New Horizons Lecture: Beyond Imaging-Radiology of Tomorrow.

This article is based on the New Horizons lecture delivered at the 2016 Radiological Society of North America Annual Meeting. It addresses looming changes for radiology, many of which stem from the disruptive effects of the Fourth Industrial Revolution. This is an emerging era of unprecedented rapid innovation marked by the integration of diverse disciplines and technologies, including data science, machine learning, and artificial intelligence-technologies that narrow the gap between man and machine. Technologic advances and the convergence of life sciences, physical sciences, and bioengineering are creating extraordinary opportunities in diagnostic radiology, image-guided therapy, targeted radionuclide therapy, and radiology informatics, including radiologic image analysis. This article uses the example of oncology to make the case that, if members in the field of radiology continue to be innovative and continuously reinvent themselves, radiology can play an ever-increasing role in both precision medicine and value-driven health care. © RSNA, 2018.

Measuring and correcting wobble in large-scale transmission radiography.

BACKGROUND: Large-scale transmission radiography scanners are used to image vehicles and cargo containers. Acquired images are inspected for threats by a human operator or a computer algorithm. To make accurate detections, it is important that image values are precise. However, due to the scale (∼5 m tall) of such systems, they can be mechanically unstable, causing the imaging array to wobble during a scan. This leads to an effective loss of precision in the captured image. OBJECTIVE: We consider the measurement of wobble and amelioration of the consequent loss of image precision. METHODS: Following our previous work, we use Beam Position Detectors (BPDs) to measure the cross-sectional profile of the X-ray beam, allowing for estimation, and thus correction, of wobble. We propose: (i) a model of image formation with a wobbling detector array; (ii) a method of wobble correction derived from this model; (iii) methods for calibrating sensor sensitivities and relative offsets; (iv) a Random Regression Forest based method for instantaneous estimation of detector wobble; and (v) using these estimates to apply corrections to captured images of difficult scenes. RESULTS: We show that these methods are able to correct for 87% of image error due wobble, and when applied to difficult images, a significant visible improvement in the intensity-windowed image quality is observed. CONCLUSIONS: The method improves the precision of wobble affected images, which should help improve detection of threats and the identification of different materials in the image.

Lu-177 preparation for radiotherapy application.

A separation study using a (176)Yb target for the preparation of nca (177)Lu, which is a beta-emitting nuclide used not only in radioimmunotherapy applications but also in the treatment of various lesions, has been performed. A material having a better selectivity and separation efficiency for Lu than Yb was developed, and the separation conditions of (177)Lu were derived using this from a neutron irradiated (176)Yb target. The separation material was an organo-ceramic hybrid material containing a phosphate group. Adsorption behavior was determined through batch experiments, and (177)Lu separation from the Yb target was evaluated through column experiments. The Yb target, with a 99.72% in (176)Yb, was irradiated in the irradiation hole of HANARO, which has a thermal neutron flux of 1.6E+14ncm(-2)s(-1). The batch experiments revealed that the organo-ceramic hybrid material (Sol-POS) had a separation factor of 1.6 at 0.5M HCl. Separation was performed through extraction chromatography using a 5mg enriched Yb target, and the separation yield of the NCA (177)Lu was about 78%. If the amount of Yb target is increased to produce curies level (177)Lu, additional purification will be needed.

DOSE TO RADIOLOGICAL TECHNOLOGISTS FROM INDUCED RADIONUCLIDES IN CARBON ION RADIOTHERAPY.

Radioactive nuclides are induced in irradiation devices and patients during high-energy photon and ion beam radiotherapies. These nuclides potentially become sources of exposure to radiation workers. Radiological technologists (RTs) are often required to enter an irradiation room and approach activated devices and patients. In this study, annual doses to RTs working in a carbon ion radiotherapy facility were estimated based on measurements with the Si-semiconductor personal dosemeter. In addition, the time decay of dose around a patient couch after irradiation was obtained by phantom experiments. The annual Hp(10) values for passive and scanned beams were estimated to be 61 and 2 µSv, respectively, when assuming the number of treatments in 2013. These are much lower than the ICRP recommended dose limit for radiation workers. The time-series data of dose to RTs during their work and the time decay of the dose should be helpful for reducing their dose further.

Automated synthesis of [(18)F](2S,4R)-4-fluoroglutamine on a GE TRACERlab™ FX-N Pro module.

Glutamine (Gln) and its analogues may serve as imaging agents for tumor diagnosis using positron emission tomography (PET), especially for tumors with negative [(18)F]FDG scan. We report the first automated synthesis of [(18)F](2S,4R)-4-fluoroglutamine ([(18)F]FGln) on a GE TRACERlab™ FX-N Pro module. [(18)F]FGln was obtained in 80±3min with a radiochemical yield of 21±3% (n=5, uncorrected). The radiochemical purity was >98%, and optical purity 90±5%. The synthesis is highly reproducible with good chemical purity, radiochemical yield, and is suitable for translation to cGMP production.

MRI of Perfusion: Principles and Clinical Applications.

The principle and clinical application of measurement of cerebral blood perfusion (CBP) using MRI are described. Purposes of measuring CBP using MRI are wide-ranging. Generally, it is used to diagnose cerebro-vascular disorders or brain tumors. There are two types of measuring methods. One is dynamic susceptibility contrast (DSC) method using a contrast agent as a tracer. Another is an arterial spin labeling (ASL) method using protons in arterial blood as an endogenous tracer, instead of bio-exogenous tracer. Basic theory of ASL method was published in the 1990s, recently, its clinical application has been spreading rapidly by the technological innovations. ASL method is attractive as a way to measure CBP because of its non-invasiveness (no radiation-exposure, not need intravenous injection or blood sampling), and the imaging time is about 5 minutes, thereby the measurement can be repeated. The analysis of DSC method has not been standardized, though various valuable parameters are provided. And the prerequisite of DSC method is uncertain in vivo. On the other hand, the result of ASL is affected by the post labeling delay, and limited to the arterial information.

Applications of Machine Learning for Radiation Therapy.

Radiation therapy has been highly advanced as image guided radiation therapy (IGRT) by making advantage of image engineering technologies. Recently, novel frameworks based on image engineering technologies as well as machine learning technologies have been studied for sophisticating the radiation therapy. In this review paper, the author introduces several researches of applications of machine learning for radiation therapy. For examples, a method to determine the threshold values for standardized uptake value (SUV) for estimation of gross tumor volume (GTV) in positron emission tomography (PET) images, an approach to estimate the multileaf collimator (MLC) position errors between treatment plans and radiation delivery time, and prediction frameworks for esophageal stenosis and radiation pneumonitis risk after radiation therapy are described. Finally, the author introduces seven issues that one should consider when applying machine learning models to radiation therapy.