The 50 most-cited articles in Medical Physics, 2019

The biological effectiveness of proton beams relative to photon beams in radiation therapy has been taken to be 1.1 throughout the history of proton therapy. While potentially appropriate as an average value, actual relative biological effectiveness (RBE) values may differ. This Task Group report outlines the basic concepts of RBE as well as the biophysical interpretation and mathematical concepts. The current knowledge on RBE variations is reviewed and discussed in the context of the current clinical use of RBE and the clinical relevance of RBE variations (with respect to physical as well as biological parameters). The following task group aims were designed to guide the current clinical practice: Assess whether the current clinical practice of using a constant RBE for protons should be revised or maintained. Identifying sites and treatment strategies where variable RBE might be utilized for a clinical benefit. Assess the potential clinical consequences of delivering biologically weighted proton doses based on variable RBE and/or LET models implemented in treatment planning…

BACKGROUND: The rapid development and complexity of new x-ray computed tomography (CT) technologies and the need for evidence-based optimization of image quality with respect to radiation and contrast media dose call for an updated approach towards CT performance evaluation. AIMS: This report offers updated testing guidelines for testing CT systems with an enhanced focus on the operational performance including iterative reconstructions and automatic exposure control (AEC) techniques. MATERIALS AND METHODS: The report was developed based on a comprehensive review of best methods and practices in the scientific literature. The detailed methods include the assessment of 1) CT noise (magnitude, texture, nonuniformity, inhomogeneity), 2) resolution (task transfer function under varying conditions and its scalar reflections), 3) task-based performance (detectability, estimability), and 4) AEC performance (spatial, noise, and mA concordance of attenuation and exposure modulation). The methods include varying reconstruction and tube current modulation conditions, standardized testing…

PURPOSE: Automated synthetic computed tomography (sCT) generation based on magnetic resonance imaging (MRI) images would allow for MRI-only based treatment planning in radiation therapy, eliminating the need for CT simulation and simplifying the patient treatment workflow. In this work, the authors propose a novel method for generation of sCT based on dense cycle-consistent generative adversarial networks (cycle GAN), a deep-learning based model that trains two transformation mappings (MRI to CT and CT to MRI) simultaneously. METHODS AND MATERIALS: The cycle GAN-based model was developed to generate sCT images in a patch-based framework. Cycle GAN was applied to this problem because it includes an inverse transformation from CT to MRI, which helps constrain the model to learn a one-to-one mapping. Dense block-based networks were used to construct generator of cycle GAN. The network weights and variables were optimized via a gradient difference (GD) loss and a novel distance loss metric between sCT and original CT. RESULTS: Leave-one-out cross-validation was performed to validate the…

PURPOSE: Accurate and timely organs-at-risk (OARs) segmentation is key to efficient and high-quality radiation therapy planning. The purpose of this work is to develop a deep learning-based method to automatically segment multiple thoracic OARs on chest computed tomography (CT) for radiotherapy treatment planning. METHODS: We propose an adversarial training strategy to train deep neural networks for the segmentation of multiple organs on thoracic CT images. The proposed design of adversarial networks, called U-Net-generative adversarial network (U-Net-GAN), jointly trains a set of U-Nets as generators and fully convolutional networks (FCNs) as discriminators. Specifically, the generator, composed of U-Net, produces an image segmentation map of multiple organs by an end-to-end mapping learned from CT image to multiorgan-segmented OARs. The discriminator, structured as an FCN, discriminates between the ground truth and segmented OARs produced by the generator. The generator and discriminator compete against each other in an adversarial learning process to produce the optimal…

PURPOSE: Intensity-Modulated Radiation Therapy (IMRT), including its variations (including IMRT, Volumetric Arc Therapy (VMAT), and Tomotherapy), is a widely used and critically important technology for cancer treatment. It is a knowledge-intensive technology due not only to its own technical complexity, but also to the inherently conflicting nature of maximizing tumor control while minimizing normal organ damage. As IMRT experience and especially the carefully designed clinical plan data are accumulated during the past two decades, a new set of methods commonly termed knowledge-based planning (KBP) have been developed that aim to improve the quality and efficiency of IMRT planning by learning from the database of past clinical plans. Some of this development has led to commercial products recently that allowed the investigation of KBP in numerous clinical applications. In this literature review, we will attempt to present a summary of published methods of knowledge-based approaches in IMRT and recent clinical validation results. METHODS: In March 2018, a literature search was…

PURPOSE: The incorporation of cone-beam computed tomography (CBCT) has allowed for enhanced image-guided radiation therapy. While CBCT allows for daily 3D imaging, images suffer from severe artifacts, limiting the clinical potential of CBCT. In this work, a deep learning-based method for generating high quality corrected CBCT (CCBCT) images is proposed. METHODS: The proposed method integrates a residual block concept into a cycle-consistent adversarial network (cycle-GAN) framework, called res-cycle GAN, to learn a mapping between CBCT images and paired planning CT images. Compared with a GAN, a cycle-GAN includes an inverse transformation from CBCT to CT images, which constrains the model by forcing calculation of both a CCBCT and a synthetic CBCT. A fully convolution neural network with residual blocks is used in the generator to enable end-to-end CBCT-to-CT transformations. The proposed algorithm was evaluated using 24 sets of patient data in the brain and 20 sets of patient data in the pelvis. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized…

PURPOSE: Task Group (TG) 224 was established by the American Association of Physicists in Medicine's Science Council under the Radiation Therapy Committee and Work Group on Particle Beams. The group was charged with developing comprehensive quality assurance (QA) guidelines and recommendations for the three commonly employed proton therapy techniques for beam delivery: scattering, uniform scanning, and pencil beam scanning. This report supplements established QA guidelines for therapy machine performance for other widely used modalities, such as photons and electrons (TG 142, TG 40, TG 24, TG 22, TG 179, and Medical Physics Practice Guideline 2a) and shares their aims of ensuring the safe, accurate, and consistent delivery of radiation therapy dose distributions to patients. METHODS: To provide a basis from which machine-specific QA procedures can be developed, the report first describes the different delivery techniques and highlights the salient components of the related machine hardware. Depending on the particular machine hardware, certain procedures may be more or less…

Thermoluminescent dosimeters (TLD) and optically stimulated luminescent dosimeters (OSLD) are practical, accurate, and precise tools for point dosimetry in medical physics applications. The charges of Task Group 191 were to detail the methodologies for practical and optimal luminescence dosimetry in a clinical setting. This includes: (a) to review the variety of TLD/OSLD materials available, including features and limitations of each; (b) to outline the optimal steps to achieve accurate and precise dosimetry with luminescent detectors and to evaluate the uncertainty induced when less rigorous procedures are used; (c) to develop consensus guidelines on the optimal use of luminescent dosimeters for clinical practice; and (d) to develop guidelines for special medically relevant uses of TLDs/OSLDs such as mixed photon/neutron field dosimetry, particle beam dosimetry, and skin dosimetry. While this report provides general guidelines for TLD and OSLD processes, the report provides specific details for TLD‐100 and nanoDot TM dosimeters because of their prevalence in clinical practice.

PURPOSE: Cone-beam computed tomography (CBCT) scanning is used daily or weekly (i.e., on-treatment CBCT) for accurate patient setup in image-guided radiotherapy. However, inaccuracy of CT numbers prevents CBCT from performing advanced tasks such as dose calculation and treatment planning. Motivated by the promising performance of deep learning in medical imaging, we propose a deep U-net-based approach that synthesizes CT-like images with accurate numbers from planning CT, while keeping the same anatomical structure as on-treatment CBCT. METHODS: We formulated the CT synthesis problem under a deep learning framework, where a deep U-net architecture was used to take advantage of the anatomical structure of on-treatment CBCT and image intensity information of planning CT. U-net was chosen because it exploits both global and local features in the image spatial domain, matching our task to suppress global scattering artifacts and local artifacts such as noise in CBCT. To train the synthetic CT generation U-net (sCTU-net), we include on-treatment CBCT and initial planning CT of 37…

PURPOSE: The use of neural networks to directly predict three-dimensional dose distributions for automatic planning is becoming popular. However, the existing methods use only patient anatomy as input and assume consistent beam configuration for all patients in the training database. The purpose of this work was to develop a more general model that considers variable beam configurations in addition to patient anatomy to achieve more comprehensive automatic planning with a potentially easier clinical implementation, without the need to train specific models for different beam settings. METHODS: The proposed anatomy and beam (AB) model is based on our newly developed deep learning architecture, and hierarchically densely connected U-Net (HD U-Net), which combines U-Net and DenseNet. The AB model contains 10 input channels: one for beam setup and the other 9 for anatomical information (PTV and organs). The beam setup information is represented by a 3D matrix of the non-modulated beam's eye view ray-tracing dose distribution. We used a set of images from 129 patients with lung cancer…

PURPOSE: Reliable automated segmentation of the prostate is indispensable for image-guided prostate interventions. However, the segmentation task is challenging due to inhomogeneous intensity distributions, variation in prostate anatomy, among other problems. Manual segmentation can be time-consuming and is subject to inter- and intraobserver variation. We developed an automated deep learning-based method to address this technical challenge. METHODS: We propose a three-dimensional (3D) fully convolutional networks (FCN) with deep supervision and group dilated convolution to segment the prostate on magnetic resonance imaging (MRI). In this method, a deeply supervised mechanism was introduced into a 3D FCN to effectively alleviate the common exploding or vanishing gradients problems in training deep models, which forces the update process of the hidden layer filters to favor highly discriminative features. A group dilated convolution which aggregates multiscale contextual information for dense prediction was proposed to enlarge the effective receptive field of convolutional neural…

PURPOSE: Our goal was to use a generative adversarial network (GAN) with feature matching and task-specific perceptual loss to synthesize standard-dose amyloid Positron emission tomography (PET) images of high quality and including accurate pathological features from ultra-low-dose PET images only. METHODS: Forty PET datasets from 39 participants were acquired with a simultaneous PET/MRI scanner following injection of 330 ± 30 MBq of the amyloid radiotracer 18F-florbetaben. The raw list-mode PET data were reconstructed as the standard-dose ground truth and were randomly undersampled by a factor of 100 to reconstruct 1% low-dose PET scans. A 2D encoder-decoder network was implemented as the generator to synthesize a standard-dose image and a discriminator was used to evaluate them. The two networks contested with each other to achieve high-visual quality PET from the ultra-low-dose PET. Multi-slice inputs were used to reduce noise by providing the network with 2.5D information. Feature matching was applied to reduce hallucinated structures. Task-specific perceptual loss was designed…

Managing radiotherapy patients with implanted cardiac devices (implantable cardiac pacemakers and implantable cardioverter-defibrillators) has been a great practical and procedural challenge in radiation oncology practice. Since the publication of the AAPM TG-34 in 1994, large bodies of literature and case reports have been published about different kinds of radiation effects on modern technology implantable cardiac devices and patient management before, during, and after radiotherapy. This task group report provides the framework that analyzes the potential failure modes of these devices and lays out the methodology for patient management in a comprehensive and concise way, in every step of the entire radiotherapy process.

PURPOSE: To develop a knowledge-based automated planning pipeline that generates treatment plans without feature engineering, using deep neural network architectures for predicting three-dimensional (3D) dose. METHODS: Our knowledge-based automated planning (KBAP) pipeline consisted of a knowledge-based planning (KBP) method that predicts dose for a contoured computed tomography (CT) image followed by two optimization models that learn objective function weights and generate fluence-based plans, respectively. We developed a novel generative adversarial network (GAN)-based KBP approach, a 3D GAN model, which predicts dose for the full 3D CT image at once and accounts for correlations between adjacent CT slices. Baseline comparisons were made against two state-of-the-art deep learning-based KBP methods from the literature. We also developed an additional benchmark, a two-dimensional (2D) GAN model which predicts dose to each axial slice independently. For all models, we investigated the impact of multiplicatively scaling the predictions before optimization, such that the predicted…

PURPOSE: To investigate two deep learning-based modeling schemes for predicting short-term risk of developing breast cancer using prior normal screening digital mammograms in a case-control setting. METHODS: We conducted a retrospective Institutional Review Board-approved study on a case-control cohort of 226 patients (including 113 women diagnosed with breast cancer and 113 controls) who underwent general population breast cancer screening. For each patient, a prior normal (i.e., with negative or benign findings) digital mammogram examination [including mediolateral oblique (MLO) view and craniocaudal (CC) view two images] was collected. Thus, a total of 452 normal images (226 MLO view images and 226 CC view images) of this case-control cohort were analyzed to predict the outcome, i.e., developing breast cancer (cancer cases) or remaining breast cancer-free (controls) within the follow-up period. We implemented an end-to-end deep learning model and a GoogLeNet-LDA model and compared their effects in several experimental settings using two mammographic view images and inputting two…

PURPOSE: Transrectal ultrasound (TRUS) is a versatile and real-time imaging modality that is commonly used in image-guided prostate cancer interventions (e.g., biopsy and brachytherapy). Accurate segmentation of the prostate is key to biopsy needle placement, brachytherapy treatment planning, and motion management. Manual segmentation during these interventions is time-consuming and subject to inter- and intraobserver variation. To address these drawbacks, we aimed to develop a deep learning-based method which integrates deep supervision into a three-dimensional (3D) patch-based V-Net for prostate segmentation. METHODS AND MATERIALS: We developed a multidirectional deep-learning-based method to automatically segment the prostate for ultrasound-guided radiation therapy. A 3D supervision mechanism is integrated into the V-Net stages to deal with the optimization difficulties when training a deep network with limited training data. We combine a binary cross-entropy (BCE) loss and a batch-based Dice loss into the stage-wise hybrid loss function for a deep supervision training. During…

Purpose To develop a deep learning method for prediction of three‐dimensional (3D) voxel‐by‐voxel dose distributions of helical tomotherapy (HT). Methods Using previously treated HT plans as training data, a deep learning model named U‐ResNet‐D was trained to predict a 3D dose distribution. First, the contoured structures and dose volumes were converted from plan database to 3D matrix with a program based on a developed visualization toolkit (VTK), then transferred to U‐ResNet‐D for correlating anatomical features and dose distributions at voxel‐level. One hundred and ninety nasopharyngeal cancer (NPC) patients treated by HT with multiple planning target volumes (PTVs) in different prescription patterns were studied. The model was typically trained from scratch with weights randomly initialized rather than using transfer‐learning method, and used to predict new patient's 3D dose distributions. The predictive accuracy was evaluated with three methods: (a) The dose difference at the position r, δ(r, r) = Dc(r) − Dp(r), was calculated for each voxel. The mean (μδ(r,r)) and standard…

PURPOSE: Automatic segmentation of organs-at-risk (OARs) is a key step in radiation treatment planning to reduce human efforts and bias. Deep convolutional neural networks (DCNN) have shown great success in many medical image segmentation applications but there are still challenges in dealing with large 3D images for optimal results. The purpose of this study is to develop a novel DCNN method for thoracic OARs segmentation using cropped 3D images. METHODS: To segment the five organs (left and right lungs, heart, esophagus and spinal cord) from the thoracic CT scans, preprocessing to unify the voxel spacing and intensity was first performed, a 3D U-Net was then trained on resampled thoracic images to localize each organ, then the original images were cropped to only contain one organ and served as the input to each individual organ segmentation network. The segmentation maps were then merged to get the final results. The network structures were optimized for each step, as well as the training and testing strategies. A novel testing augmentation with multiple iterations of image…

The GE Discovery MI PET/CT system has a modular digital detector design allowing three, four, or five detector block rings that extend the axial field-of-view (FOV) from 15 to 25 cm in 5 cm increments. This study investigated the performance of the 5-ring system and compared it to 3- and 4-ring systems; the GE Discovery IQ system that uses conventional photomultiplier tubes; and the GE Signa PET/MR system that has a reduced transaxial FOV. METHODS: PET performance was evaluated at three different institutions. Spatial resolution, sensitivity, counting rate performance, accuracy, and image quality were measured in accordance with National Electrical Manufacturers Association NU 2-2012 standards. The mean energy resolution, mean timing resolution, and PET/CT subsystem alignment were also measured. Phantoms were used to determine the effects of varying acquisition time and reconstruction parameters on image quality. Retrospective patient scans were reconstructed with various scan durations to evaluate the impact on image quality. RESULTS: Results from all three institutions were…

PURPOSE: To provide an overview of the types of adverse events reported to the US Food and Drug Administration (US FDA) for magnetic resonance (MR) systems over a 10-yr period. METHODS: Two reviewers independently reviewed adverse events reported to FDA for MR systems from 1 January 2008 to 31 December 2017 and manually categorized events into eight event types. Thermal events were further subcategorized by probable cause. Objects that became projectiles were also categorized. RESULTS: FDA received 1568 adverse event reports for MR systems between 1 January 2008 and 31 December 2017. This analysis included 1548 reports. Thermal events were the most commonly reported serious injury (59% of analyzed reports). Mechanical events - defined as slips, falls, crush injuries, broken bones, and cuts; musculoskeletal injuries from lifting or movement of the device - (11%), projectile events (9%), and acoustic events (6%) were also observed. CONCLUSIONS: Adverse events related to MR systems consistent with the known hazards of the MR environment continue to be reported to FDA. Increased…

Dr. Jia and Dr. Ren have no relevant conflict of interest.

PURPOSE: The improved soft tissue contrast of magnetic resonance imaging (MRI) compared to computed tomography (CT) makes it a useful imaging modality for radiotherapy treatment planning. Even when MR images are acquired for treatment planning, the standard clinical practice currently also requires a CT for dose calculation and x-ray-based patient positioning. This increases workloads, introduces uncertainty due to the required inter-modality image registrations, and involves unnecessary irradiation. While it would be beneficial to use exclusively MR images, a method needs to be employed to estimate a synthetic CT (sCT) for generating electron density maps and patient positioning reference images. We investigated 2D and 3D convolutional neural networks (CNNs) to generate a male pelvic sCT using a T1-weighted MR image and compare their performance. METHODS: A retrospective study was performed using CTs and T1-weighted MR images of 20 prostate cancer patients. CTs were deformably registered to MR images to create CT-MR pairs for training networks. The proposed 2D CNN, which contained…

PURPOSE: Intensity-modulated radiation therapy (IMRT) quality assurance (QA) measurements are routinely performed prior to treatment delivery to verify dose calculation and delivery accuracy. In this work, we applied a machine learning-based approach to predict portal dosimetry based IMRT QA gamma passing rates. METHODS: 182 IMRT plans for various treatment sites were planned and delivered with portal dosimetry on two TrueBeam and two Trilogy LINACs. A total of 1497 beams were collected and analyzed using gamma criteria of 2%/2 mm with a 5% threshold. The datasets for building the machine learning models consisted of 1269 beams. Ten-fold cross-validation was utilized to tune the model and prevent "overfitting." A separate test set with the remaining 228 beams was used to evaluate model performance. Each beam was characterized by a set of 31 features including both plan complexity metrics and machine characteristics. Three tree-based machine learning algorithms (AdaBoost, Random Forest, and XGBoost) were used to train the models and predict gamma passing rates. RESULTS: Both AdaBoost…

PURPOSE: To evaluate pix2pix and CycleGAN and to assess the effects of multiple combination strategies on accuracy for patch-based synthetic computed tomography (sCT) generation for magnetic resonance (MR)-only treatment planning in head and neck (HN) cancer patients. MATERIALS AND METHODS: Twenty-three deformably registered pairs of CT and mDixon FFE MR datasets from HN cancer patients treated at our institution were retrospectively analyzed to evaluate patch-based sCT accuracy via the pix2pix and CycleGAN models. To test effects of overlapping sCT patches on estimations, we (a) trained the models for three orthogonal views to observe the effects of spatial context, (b) we increased effective set size by using per-epoch data augmentation, and (c) we evaluated the performance of three different approaches for combining overlapping Hounsfield unit (HU) estimations for varied patch overlap parameters. Twelve of twenty-three cases corresponded to a curated dataset previously used for atlas-based sCT generation and were used for training with leave-two-out cross-validation. Eight cases…

Purpose To develop and evaluate a patch‐based convolutional neural network (CNN) to generate synthetic computed tomography (sCT) images for magnetic resonance (MR)‐only workflow for radiotherapy of head and neck tumors. A patch‐based deep learning method was chosen to improve robustness to abnormal anatomies caused by large tumors, surgical excisions, or dental artifacts. In this study, we evaluate whether the generated sCT images enable accurate MR‐based dose calculations in the head and neck region. Methods We conducted a retrospective study on 34 patients with head and neck cancer who underwent both CT and MR imaging for radiotherapy treatment planning. To generate the sCTs, a large field‐of‐view T2‐weighted Turbo Spin Echo MR sequence was used from the clinical protocol for multiple types of head and neck tumors. To align images as well as possible on a voxel‐wise level, CT scans were nonrigidly registered to the MR (CT reg ). The CNN was based on a U‐net architecture and consisted of 14 layers with 3 × 3 × 3 filters. Patches of 48 × 48 × 48 were randomly extracted and fed into…

PURPOSE: Cone-beam computed tomography (CBCT) offers advantages over conventional fan-beam CT in that it requires a shorter time and less exposure to obtain images. However, CBCT images suffer from low soft-tissue contrast, noise, and artifacts compared to conventional fan-beam CT images. Therefore, it is essential to improve the image quality of CBCT. METHODS: In this paper, we propose a synthetic approach to translate CBCT images with deep neural networks. Our method requires only unpaired and unaligned CBCT images and planning fan-beam CT (PlanCT) images for training. The CBCT images and PlanCT images may be obtained from other patients as long as they are acquired with the same scanner settings. Once trained, three-dimensionally reconstructed CBCT images can be directly translated into high-quality PlanCT-like images. RESULTS: We demonstrate the effectiveness of our method with images obtained from 20 prostate patients, and provide a statistical and visual comparison. The image quality of the translated images shows substantial improvement in voxel values, spatial uniformity,…

PURPOSE: This study aims to characterize the performance of a prototype rapid kilovoltage (kV) x-ray image guidance system onboard the newly released Halcyon 2.0 linear accelerator (Varian Medical Systems, Palo Alto, CA) by use of conventional and innovatively designed testing procedures. METHODS: Basic imaging system performance tests and radiation dose measurements were performed for all eleven kV-cone beam computed tomography (CBCT) imaging protocols available on a preclinical Halcyon 2.0 LINAC. Both conventional CBCT reconstruction using the Feldkamp-Davis-Kress (FDK) algorithm and a novel, advanced iterative reconstruction (iCBCT) available on this platform were evaluated. Standard image quality metrics, including slice thickness accuracy, high-contrast resolution, low-contrast resolution, regional uniformity and noise, and CT Hounsfield unit (HU) number accuracy and linearity were evaluated using a manufacturer-supplied QUART phantom (GmbH, Zorneding, Germany) and an independent image quality phantom (Catphan 500, The Phantom Laboratory, New York, NY). Due to the simplified…

PURPOSE: To develop a head and neck normal structures autocontouring tool that could be used to automatically detect the errors in autocontours from a clinically validated autocontouring tool. METHODS: An autocontouring tool based on convolutional neural networks (CNN) was developed for 16 normal structures of the head and neck and tested to identify the contour errors from a clinically validated multiatlas-based autocontouring system (MACS). The computed tomography (CT) scans and clinical contours from 3495 patients were semiautomatically curated and used to train and validate the CNN-based autocontouring tool. The final accuracy of the tool was evaluated by calculating the Sørensen-Dice similarity coefficients (DSC) and Hausdorff distances between the automatically generated contours and physician-drawn contours on 174 internal and 24 external CT scans. Lastly, the CNN-based tool was evaluated on 60 patients' CT scans to investigate the possibility to detect contouring failures. The contouring failures on these patients were classified as either minor or major errors. The criteria…

PURPOSE: Convolutional neural network (CNN)-based image denoising techniques have shown promising results in low-dose CT denoising. However, CNN often introduces blurring in denoised images when trained with a widely used pixel-level loss function. Perceptual loss and adversarial loss have been proposed recently to further improve the image denoising performance. In this paper, we investigate the effect of different loss functions on image denoising performance using task-based image quality assessment methods for various signals and dose levels. METHODS: We used a modified version of U-net that was effective at reducing the correlated noise in CT images. The loss functions used for comparison were two pixel-level losses (i.e., the mean-squared error and the mean absolute error), Visual Geometry Group network-based perceptual loss (VGG loss), adversarial loss used to train the Wasserstein generative adversarial network with gradient penalty (WGAN-GP), and their weighted summation. Each image denoising method was applied to reconstructed images and sinogram images independently and…

PURPOSE: In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. METHOD: We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in…

PURPOSE: Radiation dose to cardiac substructures is related to radiation-induced heart disease. However, substructures are not considered in radiation therapy planning (RTP) due to poor visualization on CT. Therefore, we developed a novel deep learning (DL) pipeline leveraging MRI's soft tissue contrast coupled with CT for state-of-the-art cardiac substructure segmentation requiring a single, non-contrast CT input. MATERIALS/METHODS: Thirty-two left-sided whole-breast cancer patients underwent cardiac T2 MRI and CT-simulation. A rigid cardiac-confined MR/CT registration enabled ground truth delineations of 12 substructures (chambers, great vessels (GVs), coronary arteries (CAs), etc.). Paired MRI/CT data (25 patients) were placed into separate image channels to train a three-dimensional (3D) neural network using the entire 3D image. Deep supervision and a Dice-weighted multi-class loss function were applied. Results were assessed pre/post augmentation and post-processing (3D conditional random field (CRF)). Results for 11 test CTs (seven unique patients) were compared to ground…

PURPOSE: Quantification of carotid plaques has been shown to be important for assessing as well as monitoring the progression and regression of carotid atherosclerosis. Various metrics have been proposed and methods of measurements ranging from manual tracing to automated segmentations have also been investigated. Of those metrics, quantification of carotid plaques by measuring vessel-wall-volume (VWV) using the segmented media-adventitia (MAB) and lumen-intima (LIB) boundaries has been shown to be sensitive to temporal changes in carotid plaque burden. Thus, semi-automatic MAB and LIB segmentation methods are required to help generate VWV measurements with high accuracy and less user interaction. METHODS: In this paper, we propose a semiautomatic segmentation method based on deep learning to segment the MAB and LIB from carotid three-dimensional ultrasound (3DUS) images. For the MAB segmentation, we convert the segmentation problem to a pixel-by-pixel classification problem. A dynamic convolutional neural network (Dynamic CNN) is proposed to classify the patches generated by…

PURPOSE: Currently, four-dimensional (4D) cone-beam computed tomography (CBCT) requires a 3-4 min full-fan scan to ensure usable image quality. Recent advancements in sparse-view 4D-CBCT reconstruction have opened the possibility to reduce scan time and dose. The aim of this study is to provide a common framework for systematically evaluating algorithms for 4D-CBCT reconstruction from a 1-min scan. Using this framework, the AAPM-sponsored SPARE Challenge was conducted in 2018 to identify and compare state-of-the-art algorithms. METHODS: A clinically realistic CBCT dataset was simulated using patient CT volumes from the 4D-Lung database. The selected patients had multiple 4D-CT sessions, where the first 4D-CT was used as the prior CT, and the rest were used as the ground truth volumes for simulating CBCT projections. A GPU-based Monte Carlo tool was used to simulate the primary, scatter, and quantum noise signals. A total of 32 CBCT scans of nine patients were generated. Additional qualitative analysis was performed on a clinical Varian and clinical Elekta dataset to validate the…

PURPOSE: Scatter is a major factor degrading the image quality of cone beam computed tomography (CBCT). Conventional scatter correction strategies require handcrafted analytical models with ad hoc assumptions, which often leads to less accurate scatter removal. This study aims to develop an effective scatter correction method using a residual convolutional neural network (CNN). METHODS: A U-net based 25-layer CNN was constructed for CBCT scatter correction. The establishment of the model consists of three steps: model training, validation, and testing. For model training, a total of 1800 pairs of x-ray projection and the corresponding scatter-only distribution in nonanthropomorphic phantoms taken in full-fan scan were generated using Monte Carlo simulation of a CBCT scanner installed with a proton therapy system. An end-to-end CNN training was implemented with two major loss functions for 100 epochs with a mini-batch size of 10. Image rotations and flips were randomly applied to augment the training datasets during training. For validation, 200 projections of a digital head phantom…

PURPOSE: Dual-energy CT (DECT) has been increasingly used in imaging applications because of its capability for material differentiation. However, material decomposition suffers from magnified noise from two CT images of independent scans, leading to severe degradation of image quality. Existing algorithms exhibit suboptimal decomposition performance because they fail to fully depict the mapping relationship between DECT images and basis materials under noisy conditions. Convolutional neural network exhibits great promise in the modeling of data coupling and has recently become an important technique in medical imaging application. Inspired by its impressive potential, we developed a new Butterfly network to perform the image domain dual material decomposition. METHODS: The Butterfly network is derived from the model of image domain DECT decomposition by exploring the geometric relationship between the mapping functions of the data model and network components. The network is designed as the double-entry double-out crossover architecture based on the decomposition formulation. It…

Purpose We propose a novel domain‐specific loss, which is a differentiable loss function based on the dose‐volume histogram (DVH), and combine it with an adversarial loss for the training of deep neural networks. In this study, we trained a neural network for generating Pareto optimal dose distributions, and evaluate the effects of the domain‐specific loss on the model performance. Methods In this study, three loss functions — mean squared error (MSE) loss, DVH loss, and adversarial (ADV) loss — were used to train and compare four instances of the neural network model: (a) MSE, (b) MSE + ADV, (c) MSE + DVH, and (d) MSE + DVH+ADV. The data for 70 prostate patients, including the planning target volume (PTV), and the organs at risk (OAR) were acquired as 96 × 96 × 24 dimension arrays at 5 mm 3 voxel size. The dose influence arrays were calculated for 70 prostate patients, using a 7 equidistant coplanar beam setup. Using a scalarized multicriteria optimization for intensity‐modulated radiation therapy, 1200 Pareto surface plans per patient were generated by pseudo‐randomizing the PTV…

PURPOSE: Computed tomography (CT) is an effective method for detecting and characterizing lung nodules in vivo. With the growing use of chest CT, the detection frequency of lung nodules is increasing. Noninvasive methods to distinguish malignant from benign nodules have the potential to decrease the clinical burden, risk, and cost involved in follow-up procedures on the large number of false-positive lesions detected. This study examined the benefit of including perinodular parenchymal features in machine learning (ML) tools for pulmonary nodule assessment. METHODS: Lung nodule cases with pathology confirmed diagnosis (74 malignant, 289 benign) were used to extract quantitative imaging characteristics from computed tomography scans of the nodule and perinodular parenchyma tissue. A ML tool development pipeline was employed using k-medoids clustering and information theory to determine efficient predictor sets for different amounts of parenchyma inclusion and build an artificial neural network classifier. The resulting ML tool was validated using an independent cohort (50 malignant,…

PURPOSE: Accurate segmentation of the prostate on computed tomography (CT) for treatment planning is challenging due to CT's poor soft tissue contrast. Magnetic resonance imaging (MRI) has been used to aid prostate delineation, but its final accuracy is limited by MRI-CT registration errors. We developed a deep attention-based segmentation strategy on CT-based synthetic MRI (sMRI) to deal with the CT prostate delineation challenge without MRI acquisition. METHODS AND MATERIALS: We developed a prostate segmentation strategy which employs an sMRI-aided deep attention network to accurately segment the prostate on CT. Our method consists of three major steps. First, a cycle generative adversarial network was used to estimate an sMRI from CT images. Second, a deep attention fully convolution network was trained based on sMRI and the prostate contours deformed from MRIs. Attention models were introduced to pay more attention to prostate boundary. The prostate contour for a query patient was obtained by feeding the patient's CT images into the trained sMRI generation model and segmentation…

PURPOSE: In order to attain anatomical models, surgical guides and implants for computer-assisted surgery, accurate segmentation of bony structures in cone-beam computed tomography (CBCT) scans is required. However, this image segmentation step is often impeded by metal artifacts. Therefore, this study aimed to develop a mixed-scale dense convolutional neural network (MS-D network) for bone segmentation in CBCT scans affected by metal artifacts. METHOD: Training data were acquired from 20 dental CBCT scans affected by metal artifacts. An experienced medical engineer segmented the bony structures in all CBCT scans using global thresholding and manually removed all remaining noise and metal artifacts. The resulting gold standard segmentations were used to train an MS-D network comprising 100 convolutional layers using far fewer trainable parameters than alternative convolutional neural network (CNN) architectures. The bone segmentation performance of the MS-D network was evaluated using a leave-2-out scheme and compared with a clinical snake evolution algorithm and two…

PURPOSE: In diffusion-weighted magnetic resonance imaging (DW-MRI), the fiber orientation distribution function (fODF) is of great importance for solving complex fiber configurations to achieve reliable tractography throughout the brain, which ultimately facilitates the understanding of brain connectivity and exploration of neurological dysfunction. Recently, multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD) method has been explored for reconstructing full fODFs. To achieve a reliable fitting, similar to other model-based approaches, a large number of diffusion measurements is typically required for MSMT-CSD method. The prolonged acquisition is, however, not feasible in practical clinical routine and is prone to motion artifacts. To accelerate the acquisition, we proposed a method to reconstruct the fODF from downsampled diffusion-weighted images (DWIs) by leveraging the strong inference ability of the deep convolutional neural network (CNN). METHODS: The method treats spherical harmonics (SH)-represented DWI signals and fODF coefficients as inputs and outputs,…

Purpose To perform a radiomics analysis with comparisons of multidomain features and a variety of feature selection strategies and classifiers, with the goal of evaluating the value of quantified radiomics method for noninvasively differentiating autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC) in 18 F‐fluorodeoxglucose positron emission tomography/computed tomography ( 18 F FDG PET/CT) images. Methods We extracted 251 expert‐designed features from 2D and 3D PET/CT images of 111 patients, and recombined these features into five feature sets according to their modalities and dimensions. Among the five feature sets, the optimal one was found leveraging four feature selection strategies and four machine learning classifiers based on the area under the receiver operating characteristic curve (AUC). The feature selection strategies include spearman’s rank correlation coefficient, minimum redundancy maximum relevance, support vector machine recursive feature elimination (SVM‐RFE), and no feature selection, while the classifiers are random forest, adaptive…

PURPOSE: Deep neural network-based image reconstruction has demonstrated promising performance in medical imaging for undersampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is especially challenging to train the reconstruction networks for three-dimensional computed tomography (CT) because of the high resolution of CT images. The purpose of this work is to reduce the memory and time consumption of the training of the reconstruction networks for CT to make it practical for current hardware, while maintaining the quality of the reconstructed images. METHODS: We unrolled the proximal gradient descent algorithm for iterative image reconstruction to finite iterations and replaced the terms related to the penalty function with trainable convolutional neural networks (CNN). The network was trained greedily iteration by iteration in the image domain on patches, which requires reasonable amount of memory and time on mainstream graphics processing unit (GPU). To overcome the local-minimum problem caused by greedy learning, we…

PURPOSE: Cardiac image segmentation is a critical process for generating personalized models of the heart and for quantifying cardiac performance parameters. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV), and the myocardium from cardiac cine MR images is challenging due to variability of the normal and abnormal anatomy, as well as the imaging protocols. This study proposes a multi-task learning (MTL)-based regularization of a convolutional neural network (CNN) to obtain accurate segmenation of the cardiac structures from cine MR images. METHODS: We train a CNN network to perform the main task of semantic segmentation, along with the simultaneous, auxiliary task of pixel-wise distance map regression. The network also predicts uncertainties associated with both tasks, such that their losses are weighted by the inverse of their corresponding uncertainties. As a result, during training, the task featuring a higher uncertainty is weighted less and vice versa. The proposed distance map regularizer is a decoder network added to the bottleneck layer of an…

BACKGROUND AND PURPOSE: Motion-induced uncertainties hamper the clinical implementation of pencil beam scanning proton therapy (PBS-PT). Prospective pretreatment evaluations only provide multiscenario predictions without giving a clear conclusion for the actual treatment. Therefore, in this proof-of-concept study we present a methodology for a fraction-wise retrospective four-dimensional (4D) dose reconstruction and accumulation aiming at the evaluation of treatment quality during and after treatment. MATERIAL AND METHODS: We implemented an easy-to-use, script-based 4D dose assessment of PBS-PT for patients with moving tumors in a commercially available treatment planning system. This 4D dose accumulation uses treatment delivery log files and breathing pattern records of each fraction as well as weekly repeated 4D-CT scans acquired during the treatment course. The approach was validated experimentally and was executed for an exemplary dataset of a lung cancer patient. RESULTS: The script-based 4D dose reconstruction and accumulation was implemented successfully, requiring minimal…

PURPOSE: Magnetic resonance (MR) imaging with a long scan time can lead to degraded images due to patient motion, patient discomfort, and increased costs. For these reasons, the role of rapid MR imaging is important. In this study, we propose the joint reconstruction of multicontrast brain MR images from down-sampled data to accelerate the data acquisition process using a novel deep-learning network. METHODS: Twenty-one healthy volunteers (female/male = 7/14, age = 26 ± 4 yr, range 22-35 yr) and 16 postoperative patients (female/male = 7/9, age = 49 ± 9 yr, range 37-62 yr) were scanned on a 3T whole-body scanner for prospective and retrospective studies, respectively, using both T1-weighted spin-echo (SE) and T2-weighted fast spin-echo (FSE) sequences. We proposed a network which we term "X-net" to reconstruct both T1- and T2-weighted images from down-sampled images as well as a network termed "Y-net" which reconstructs T2-weighted images from highly down-sampled T2-weighted images and fully sampled T1-weighted images. Both X-net and Y-net are composed of two concatenated…

PURPOSE: Recent efforts have demonstrated that radiomic features extracted from the peritumoral region, the area surrounding the tumor parenchyma, have clinical utility in various cancer types. However, as like any radiomic features, peritumoral features could also be unstable and/or nonreproducible. Hence, the purpose of this study was to assess the stability and reproducibility of computed tomography (CT) radiomic features extracted from the peritumoral regions of lung lesions where stability was defined as the consistency of a feature by different segmentations, and reproducibility was defined as the consistency of a feature to different image acquisitions. METHODS: Stability was measured utilizing the "moist run" dataset and reproducibility was measured utilizing the Reference Image Database to Evaluate Therapy Response test-retest dataset. Peritumoral radiomic features were extracted from incremental distances of 3-12 mm outside the tumor segmentation. A total of 264 statistical, histogram, and texture radiomic features were assessed from the selected peritumoral…

PURPOSE: This retrospective study was designed to investigate the ability of radiomics to predict the mutation status of epidermal growth factor receptor (EGFR) subtypes (19Del and L858R) in patients with non-small cell lung cancer (NSCLC). METHODS: In total, 312 patients with NSCLC were included, and 580 radiomic features were extracted from the computed tomography images of each patient. In the training set, univariate analysis was performed on the clinical and radiomic features; logistic regression models were established using a 5-fold cross validation strategy for the prediction of EGFR subtypes 19Del and L858R. Subsequently, the predictive ability of the joint models was evaluated using the test set. RESULTS: The results revealed that the radiomic features specific for EGFR 19Del and L858R were Gabor's MTRVariance, Gabor's PTREntropy, and sphericity. Additionally, the respective areas under the receiver operating characteristic curves of the EGFR 19Del and L858R joint models were 0.7925 and 0.7750 for the test set. CONCLUSIONS: Our study demonstrated the potential for…

PURPOSE: The dosimetric accuracies of volumetric modulated arc therapy (VMAT) plans were predicted using plan complexity parameters via machine learning. METHODS: The dataset consisted of 600 cases of clinical VMAT plans from a single institution. The predictor variables (n = 28) for each plan included complexity parameters, machine type, and photon beam energy. Dosimetric measurements were performed using a helical diode array (ArcCHECK), and the dosimetric accuracy of the passing rates for a 5% dose difference (DD5%) and gamma index of 3%/3 mm (γ3%/3 mm) were predicted using three machine learning models: regression tree analysis (RTA), multiple regression analysis (MRA), and neural networks (NNs). First, the prediction models were applied to 500 cases of the VMAT plans. Then, the dosimetric accuracy was predicted using each model for the remaining 100 cases (evaluation dataset). The error between the predicted and measured passing rates was evaluated. RESULTS: For the 600 cases, the mean ± standard deviation of the measured passing rates was 92.3% ± 9.1% and 96.8% ± 3.1% for DD5%…

PURPOSE: The purpose of the paper was to use a virtual phantom to identify a set of radiomic features from T1-weighted and T2-weighted magnetic resonance imaging (MRI) of the brain which is stable to variations in image acquisition parameters and to evaluate the effect of image preprocessing on radiomic features stability. METHODS: Stability to different sources of variability (time of repetition and echo, voxel size, random noise and intensity non-uniformity) was evaluated for both T1-weighted and T2-weighted MRI images. A set of 107 radiomic features, accounting for shape and size, first order statistics, and textural features was used. Feature stability was quantified using intraclass correlation coefficient (ICC). For each source of variability, stability was evaluated before and after preprocessing (Z-score normalization, resampling, gaussian filtering and bias field correction). Features that have ICC > 0.75 in all the analysis of variability are selected as stable features. Last, the robust feature sets were tested on images acquired with random simulation parameters to…

Purpose Small field dosimetry has been an active area of research for over a decade. It is now known that large dosimetric errors can be introduced if proper detectors or correction factors are not used. The International Atomic Energy Agency (IAEA) through the technical report series No. 483 provides guidelines for small field dosimetry procedures as well as correction factors for most detectors available in the market. The plastic scintillator detector (PSD) Exradin W1 has been found to have a correction factor close to unity; however, it is not designed for beam scanning. To overcome this limitation, the new PSD Exradin W2 has been developed to be used as a scanning as well as a relative dosimeter. Characterization of this detector in small field dosimetry is presented in this study. Methods A 6 MV beam from a Varian‐Edge linac was used to collect data for the characterization of a W2 detector. Cerenkov light ratio (CLR) is corrected through a separate new electrometer system that comes with the W2 detector. The parameters investigated include the dose and dose rate linearity,…