Showing papers in "Journal of Applied Clinical Medical Physics in 2021"

A review on medical imaging synthesis using deep learning and its clinical applications.

Abstract: This paper reviewed the deep learning-based studies for medical imaging synthesis and its clinical application. Specifically, we summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs, and reported performances with related clinical applications on representative studies. The challenges among the reviewed studies were then summarized with discussion.

Knowledge-based radiation treatment planning: A data-driven method survey.

Abstract: This paper surveys the data-driven dose prediction methods investigated for knowledge-based planning (KBP) in the last decade. These methods were classified into two major categories-traditional KBP methods and deep-learning (DL) methods-according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best-matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data-driven KBP methods to dose prediction.

AAPM medical physics practice guideline 1.a: CT protocol management and review practice guideline.

Abstract: The American Association of Physicists in Medicine (AAPM) is a nonprofit professional society whose primary purposes are to advance the science, education and professional practice of medical physics The AAPM has more than 8000 members and is the principal organization of medical physicists in the United States The AAPM will periodically define new practice guidelines for medical physics practice to help advance the science of medical physics and to improve the quality of service to patients throughout the United States Existing medical physics practice guidelines will be reviewed for the purpose of revision or renewal, as appropriate, on their fifth anniversary or sooner Each medical physics practice guideline represents a policy statement by the AAPM, has undergone a thorough consensus process in which it has been subjected to extensive review, and requires the approval of the Professional Council The medical physics practice guidelines recognize that the safe and effective use of diagnostic and therapeutic radiology requires specific training, skills, and techniques, as described in each document Reproduction or modification of the published practice guidelines and technical standards by those entities not providing these services is not authorized The following terms are used in the AAPM practice guidelines: (a) Must and Must Not: Used to indicate that adherence to the recommendation is considered necessary to conform to this practice guideline (b) Should and Should Not: Used to indicate a prudent practice to which exceptions may occasionally be made in appropriate circumstances

Varian ethos online adaptive radiotherapy for prostate cancer: Early results of contouring accuracy, treatment plan quality, and treatment time.

Abstract: The Varian Ethos system allows for online adaptive treatments through the utilization of artificial intelligence (AI) and deformable image registration which automates large parts of the anatomical contouring and plan optimization process. In this study, treatments of intact prostate and prostate bed, with and without nodes, were simulated for 182 online adaptive fractions, and then a further 184 clinical fractions were delivered on the Ethos system. Frequency and magnitude of contour edits were recorded, as well as a range of plan quality metrics. From the fractions analyzed, 11% of AI generated contours, known as influencer contours, required no change, and 81% required minor edits in any given fraction. The frequency of target and noninfluencer organs at risk (OAR) contour editing varied substantially between different targets and noninfluencer OARs, although across all targets 72% of cases required no edits. The adaptive plan was the preference in 95% of fractions. The adaptive plan met more goals than the scheduled plan in 78% of fractions, while in 15% of fractions the number of goals met was the same. The online adaptive recontouring and replanning process was carried out in 19 min on average. Significant improvements in dosimetry are possible with the Ethos online adaptive system in prostate radiotherapy.

Prospects for daily online adaptive radiotherapy via ethos for prostate cancer patients without nodal involvement using unedited CBCT auto-segmentation.

Abstract: PURPOSE Implementing new online adaptive radiation therapy technologies is challenging because extra clinical resources are required particularly expert contour review. Here, we provide the first assessment of Varian's Ethos™ adaptive platform for prostate cancer using no manual edits after auto-segmentation to minimize this impact on clinical efficiency. METHODS Twenty-five prostate patients previously treated at our clinic were re-planned using an Ethos™ emulator. Clinical target volumes (CTV) included intact prostate and proximal seminal vesicles. The following clinical margins were used: 3 mm posterior, 5 mm left/right/anterior, and 7 mm superior/inferior. Adapted plans were calculated for 10 fractions per patient using Ethos's auto-segmentation and auto-planning workflow without manual contouring edits. Doses and auto-segmented structures were exported to our clinical treatment planning system where contours were modified as needed for all 250 CTVs and organs-at-risk. Dose metrics from adapted plans were compared to unadapted plans to evaluate CTV and OAR dose changes. RESULTS Overall 96% of fractions required auto-segmentation edits, although corrections were generally minor (<10% of the volume for 70% of CTVs, 88% of bladders, and 90% of rectums). However, for one patient the auto-segmented CTV failed to include the superior portion of prostate that extended into the bladder at all 10 fractions resulting in under-contouring of the CTV by 31.3% ± 6.7%. For the 24 patients with minor auto-segmentation corrections, adaptation improved CTV D98% by 2.9% ± 5.3%. For non-adapted fractions where bladder or rectum V90% exceeded clinical thresholds, adaptation reduced them by 13.1% ± 1.0% and 6.5% ± 7.3%, respectively. CONCLUSION For most patients, Ethos's online adaptive radiation therapy workflow improved CTV D98% and reduced normal tissue dose when structures would otherwise exceed clinical thresholds, even without time-consuming manual edits. However, for one in 25 patients, large contour edits were required and thus scrutiny of the daily auto-segmentation is necessary and not all patients will be good candidates for adaptation.

Experimental evaluation of the GE NM/CT 870 CZT clinical SPECT system equipped with WEHR and MEHRS collimator.

Abstract: Purpose A high-energy-resolution whole-body SPECT-CT device (NM/CT 870 CZT; C-SPECT) equipped with a CZT detector has been developed and is being used clinically. A MEHRS collimator has also been developed recently, with an expected improvement in imaging accuracy using medium-energy radionuclides. The objective of this study was to compare and analyze the accuracies of the following devices: a WEHR collimator and the MEHRS collimator installed on a C-SPECT, and a NaI scintillation detector-equipped Anger-type SPECT (A-SPECT) scanner, with a LEHR and LMEGP. Methods A line phantom was used to measure the energy resolutions including collimator characteristics in the planar acquisition of each device using 99m Tc and 123 I. We also measured the system's sensitivity and high-contrast resolution using a lead bar phantom. We evaluated SPECT spatial resolution, high-contrast resolution, radioactivity concentration linearity, and homogeneity, using a basic performance evaluation phantom. In addition, the effect of scatter correction was evaluated by varying the sub window (SW) employed for scattering correction. Results The energy resolution with 99m Tc was 5.6% in C-SPECT with WEHR and 9.9% in A-SPECT with LEHR. Using 123I, the results were 9.1% in C-SPECT with WEHR, 5.5% in C-SPECT with MEHRS, and 10.4% in A-SPECT with LMEGP. The planar spatial resolution was similar under all conditions, but C-SPECT performed better in SPECT acquisition. High-contrast resolution was improved in C-SPECT under planar condition and SPECT. The sensitivity and homogeneity were improved by setting the SW for scattering correction to 3% of the main peak in C-SPECT. Conclusion C-SPECT demonstrates excellent energy resolution and improved high-contrast resolution for each radionuclide. In addition, when using 123I, careful attention should be paid to SW for scatter correction. By setting the appropriate SW, C-SPECT with MEHRS has an excellent scattered ray removal effect, and highly homogenous imaging is possible while maintaining the high-contrast resolution.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

Abstract: Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

Dosimetric evaluation of synthetic CT image generated using a neural network for MR‐only brain radiotherapy

Abstract: PURPOSE AND BACKGROUND The magnetic resonance (MR)-only radiotherapy workflow is urged by the increasing use of MR image for the identification and delineation of tumors, while a fast generation of synthetic computer tomography (sCT) image from MR image for dose calculation remains one of the key challenges to the workflow. This study aimed to develop a neural network to generate the sCT in brain site and evaluate the dosimetry accuracy. MATERIALS AND METHODS A generative adversarial network (GAN) was developed to translate T1-weighted MRI to sCT. First, the "U-net" shaped encoder-decoder network with some image translation-specific modifications was trained to generate sCT, then the discriminator network was adversarially trained to distinguish between synthetic and real CT images. We enrolled 37 brain cancer patients acquiring both CT and MRI for treatment position simulation. Twenty-seven pairs of 2D T1-weighted MR images and rigidly registered CT image were used to train the GAN model, and the remaining 10 pairs were used to evaluate the model performance through the metric of mean absolute error. Furthermore, the clinical Volume Modulated Arc Therapy plan was calculated on both sCT and real CT, followed by gamma analysis and comparison of dose-volume histogram. RESULTS On average, only 15 s were needed to generate one sCT from one T1-weighted MRI. The mean absolute error between synthetic and real CT was 60.52 ± 13.32 Housefield Unit over 5-fold cross validation. For dose distribution on sCT and CT, the average pass rates of gamma analysis using the 3%/3 mm and 2%/2 mm criteria were 99.76% and 97.25% over testing patients, respectively. For parameters of dose-volume histogram for both target and organs at risk, no significant differences were found between both plans. CONCLUSION The GAN model can generate synthetic CT from one single MRI sequence within seconds, and a state-of-art accuracy of CT number and dosimetry was achieved.

Applications of machine and deep learning to patient-specific IMRT/VMAT quality assurance

Abstract: In order to deliver accurate and safe treatment to cancer patients in radiation therapy using advanced techniques such as intensity modulated radiation therapy (IMRT) and volumetric-arc radiation therapy (VMAT), patient specific quality assurance (QA) should be performed before treatment. IMRT/VMAT dose measurements in a phantom using various devices have been clinically adopted as standard method for QA. This approach allows the verification of the accuracy of the dose calculation, data transfer, and the delivery system. However, patient-specific QA procedures are expensive and require significant time and effort by the physicists. Over the past 5 years, machine learning (ML) and deep learning (DL) algorithms for predictions of IMRT/VMAT QA outcome have been investigated. Various ML and DL models have shown promising prediction accuracy and a high potential as time-efficient virtual QA tool. In this paper, we review the ML and DL based models that were developed for patient specific IMRT and VMAT QA outcome predictions from algorithmic and clinical applicability perspectives. We focus on comparing the algorithms, the dataset sizes, the input parameters and features, the QA outcome prediction approaches, the validation, the performance, the clinical applicability, and the potential clinical impact. In addition, we discuss the present challenges as well as the future directions in the implementation of these models. To the best of our knowledge, this is the first review on the application of ML and DL based models in IMRT/VMAT QA predictions.

Deep learning-based auto-segmentation of clinical target volumes for radiotherapy treatment of cervical cancer.

Abstract: Objectives Because radiotherapy is indispensible for treating cervical cancer, it is critical to accurately and efficiently delineate the radiation targets. We evaluated a deep learning (DL)-based auto-segmentation algorithm for automatic contouring of clinical target volumes (CTVs) in cervical cancers. Methods Computed tomography (CT) datasets from 535 cervical cancers treated with definitive or postoperative radiotherapy were collected. A DL tool based on VB-Net was developed to delineate CTVs of the pelvic lymph drainage area (dCTV1) and parametrial area (dCTV2) in the definitive radiotherapy group. The training/validation/test number is 157/20/23. CTV of the pelvic lymph drainage area (pCTV1) was delineated in the postoperative radiotherapy group. The training/validation/test number is 272/30/33. Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD) were used to evaluate the contouring accuracy. Contouring times were recorded for efficiency comparison. Results The mean DSC, MSD, and HD values for our DL-based tool were 0.88/1.32 mm/21.60 mm for dCTV1, 0.70/2.42 mm/22.44 mm for dCTV2, and 0.86/1.15 mm/20.78 mm for pCTV1. Only minor modifications were needed for 63.5% of auto-segmentations to meet the clinical requirements. The contouring accuracy of the DL-based tool was comparable to that of senior radiation oncologists and was superior to that of junior/intermediate radiation oncologists. Additionally, DL assistance improved the performance of junior radiation oncologists for dCTV2 and pCTV1 contouring (mean DSC increases: 0.20 for dCTV2, 0.03 for pCTV1; mean contouring time decrease: 9.8 min for dCTV2, 28.9 min for pCTV1). Conclusions DL-based auto-segmentation improves CTV contouring accuracy, reduces contouring time, and improves clinical efficiency for treating cervical cancer.

The application of metal artifact reduction methods on computed tomography scans for radiotherapy applications: A literature review.

Abstract: Metal artifact reduction (MAR) methods are used to reduce artifacts from metals or metal components in computed tomography (CT). In radiotherapy (RT), CT is the most used imaging modality for planning, whose quality is often affected by metal artifacts. The aim of this study is to systematically review the impact of MAR methods on CT Hounsfield Unit values, contouring of regions of interest, and dose calculation for RT applications. This systematic review is performed in accordance with the PRISMA guidelines; the PubMed and Web of Science databases were searched using the main keywords "metal artifact reduction", "computed tomography" and "radiotherapy". A total of 382 publications were identified, of which 40 (including one review article) met the inclusion criteria and were included in this review. The selected publications (except for the review article) were grouped into two main categories: commercial MAR methods and research-based MAR methods. Conclusion: The application of MAR methods on CT scans can improve treatment planning quality in RT. However, none of the investigated or proposed MAR methods was completely satisfactory for RT applications because of limitations such as the introduction of other errors (e.g., other artifacts) or image quality degradation (e.g., blurring), and further research is still necessary to overcome these challenges.

Potential benefits of adaptive intensity-modulated proton therapy in nasopharyngeal carcinomas

Abstract: PURPOSE To investigate potential advantages of adaptive intensity-modulated proton beam therapy (A-IMPT) by comparing it to adaptive intensity-modulated X-ray therapy (A-IMXT) for nasopharyngeal carcinomas (NPC). METHODS Ten patients with NPC treated with A-IMXT (step and shoot approach) and concomitant chemotherapy between 2014 and 2016 were selected. In the actual treatment, 46 Gy in 23 fractions (46Gy/23Fx.) was prescribed using the initial plan and 24Gy/12Fx was prescribed using an adapted plan thereafter. New treatment planning of A-IMPT was made for the same patients using equivalent dose fractionation schedule and dose constraints. The dose volume statistics based on deformable images and dose accumulation was used in the comparison of A-IMXT with A-IMPT. RESULTS The means of the Dmean of the right parotid gland (P < 0.001), right TM joint (P < 0.001), left TM joint (P < 0.001), oral cavity (P < 0.001), supraglottic larynx (P = 0.001), glottic larynx (P < 0.001), , middle PCM (P = 0.0371), interior PCM (P < 0.001), cricopharyngeal muscle (P = 0.03643), and thyroid gland (P = 0.00216), in A-IMPT are lower than those of A-IMXT, with statistical significance. The means of, D0.03cc , and Dmean of each sub portion of auditory apparatus and D30% for Eustachian tube and D0.5cc for mastoid volume in A-IMPT are significantly lower than those of A-IMXT. The mean doses to the oral cavity, supraglottic larynx, and glottic larynx were all reduced by more than 20 Gy (RBE = 1.1). CONCLUSIONS An adaptive approach is suggested to enhance the potential benefit of IMPT compared to IMXT to reduce adverse effects for patients with NPC.

Performance of deep learning synthetic CTs for MR-only brain radiation therapy.

Abstract: Purpose To evaluate the dosimetric and image-guided radiation therapy (IGRT) performance of a novel generative adversarial network (GAN) generated synthetic CT (synCT) in the brain and compare its performance for clinical use including conventional brain radiotherapy, cranial stereotactic radiosurgery (SRS), planar, and volumetric IGRT. Methods and materials SynCT images for 12 brain cancer patients (6 SRS, 6 conventional) were generated from T1-weighted postgadolinium magnetic resonance (MR) images by applying a GAN model with a residual network (ResNet) generator and a convolutional neural network (CNN) with 5 convolutional layers as the discriminator that classified input images as real or synthetic. Following rigid registration, clinical structures and treatment plans derived from simulation CT (simCT) images were transferred to synCTs. Dose was recalculated for 15 simCT/synCT plan pairs using fixed monitor units. Two-dimensional (2D) gamma analysis (2%/2 mm, 1%/1 mm) was performed to compare dose distributions at isocenter. Dose-volume histogram (DVH) metrics (D95% , D99% , D0.2cc, and D0.035cc ) were assessed for the targets and organ at risks (OARs). IGRT performance was evaluated via volumetric registration between cone beam CT (CBCT) to synCT/simCT and planar registration between KV images to synCT/simCT digital reconstructed radiographs (DRRs). Results Average gamma passing rates at 1%/1mm and 2%/2mm were 99.0 ± 1.5% and 99.9 ± 0.2%, respectively. Excellent agreement in DVH metrics was observed (mean difference ≤0.10 ± 0.04 Gy for targets, 0.13 ± 0.04 Gy for OARs). The population averaged mean difference in CBCT-synCT registrations were 0.05). An outlier with a large resection cavity exhibited the worst-case scenario. Conclusion Brain GAN synCTs demonstrated excellent performance for dosimetric and IGRT endpoints, offering potential use in high precision brain cancer therapy.

Initial analysis of the dosimetric benefit and clinical resource cost of CBCT-based online adaptive radiotherapy for patients with cancers of the cervix or rectum

Abstract: Purpose This provides a benchmark of dosimetric benefit and clinical cost of cone-beam CT-based online adaptive radiotherapy (ART) technology for cervical and rectal cancer patients. Methods An emulator of a CBCT-based online ART system was used to simulate more than 300 treatments for 13 cervical and 15 rectal cancer patients. CBCT images were used to generate adaptive replans. To measure clinical resource cost, the six phases of the workflow were timed. To evaluate the dosimetric benefit, changes in dosimetric values were assessed. These included minimum dose (Dmin) and volume receiving 95% of prescription (V95%) for the planning target volume (PTV) and the clinical target volume (CTV), and maximum 2 cc's (D2cc) of the bladder, bowel, rectum, and sigmoid colon. Results The average duration of the workflow was 24.4 and 9.2 min for cervical and rectal cancer patients, respectively. A large proportion of time was dedicated to editing target contours (13.1 and 2.7 min, respectively). For cervical cancer patients, the replan changed the Dmin to the PTVs and CTVs for each fraction 0.25 and 0.25 Gy, respectively. The replan changed the V95% by 9.2 and 7.9%. The D2cc to the bladder, bowel, rectum, and sigmoid colon for each fraction changed -0.02, -0.08, -0.07, and -0.04 Gy, respectively. For rectal cancer patients, the replan changed the Dmin to the PTVs and CTVs for each fraction of 0.20 and 0.24 Gy, respectively. The replan changed the V95% by 4.1 and 1.5%. The D2cc to the bladder and bowel for each fraction changed 0.02 and -0.02 Gy, respectively. Conclusions Dosimetric benefits can be achieved with CBCT-based online ART that is amenable to conventional appointment slots. The clinical significance of these benefits remains to be determined. Managing contours was the primary factor affecting the total duration and is imperative for safe and effective adaptive radiotherapy.

Identification of robust and reproducible CT-texture metrics using a customized 3D-printed texture phantom.

Abstract: Objective The objective of this study was to evaluate the robustness and reproducibility of computed tomography-based texture analysis (CTTA) metrics extracted from CT images of a customized texture phantom built for assessing the association of texture metrics to three-dimensional (3D) printed progressively increasing textural heterogeneity. Materials and methods A custom-built 3D-printed texture phantom comprising of six texture patterns was used to evaluate the robustness and reproducibility of a radiomics panel under a variety of routine abdominal imaging protocols. The phantom was scanned on four CT scanners (Philips, Canon, GE, and Siemens) to assess reproducibility. The robustness assessment was conducted by imaging the texture phantom across different CT imaging parameters such as slice thickness, field of view (FOV), tube voltage, and tube current for each scanner. The texture panel comprised of 387 features belonging to 15 subgroups of texture extraction methods (e.g., Gray-level Co-occurrence Matrix: GLCM). Twelve unique image settings were tested on all the four scanners (e.g., FOV125). Interclass correlation two-way mixed with absolute agreement (ICC3) was used to assess the robustness and reproducibility of radiomic features. Linear regression was used to test the association between change in radiomic features and increased texture heterogeneity. Results were summarized in heat maps. Results A total of 5612 (23.2%) of 24 090 features showed excellent robustness and reproducibility (ICC ≥ 0.9). Intensity, GLCM 3D, and gray-level run length matrix (GLRLM) 3D features showed best performance. Among imaging variables, changes in slice thickness affected all metrics more intensely compared to other imaging variables in reducing the ICC3. From the analysis of linear trend effect of the CTTA metrics, the top three metrics with high linear correlations across all scanners and scanning settings were from the GLRLM 2D/3D and discrete cosine transform (DCT) texture family. Conclusion The choice of scanner and imaging protocols affect texture metrics. Furthermore, not all CTTA metrics have a linear association with linearly varying texture patterns.

Automatic segmentation of rectal tumor on diffusion-weighted images by deep learning with U-Net

Abstract: Purpose Manual delineation of a rectal tumor on a volumetric image is time-consuming and subjective. Deep learning has been used to segment rectal tumors automatically on T2-weighted images, but automatic segmentation on diffusion-weighted imaging is challenged by noise, artifact, and low resolution. In this study, a volumetric U-shaped neural network (U-Net) is proposed to automatically segment rectal tumors on diffusion-weighted images. Methods Three hundred patients of locally advanced rectal cancer were enrolled in this study and divided into a training group, a validation group, and a test group. The region of rectal tumor was delineated on the diffusion-weighted images by experienced radiologists as the ground truth. A U-Net was designed with a volumetric input of the diffusion-weighted images and an output of segmentation with the same size. A semi-automatic segmentation method was used for comparison by manually choosing a threshold of gray level and automatically selecting the largest connected region. Dice similarity coefficient (DSC) was calculated to evaluate the methods. Results On the test group, deep learning method (DSC = 0.675 ± 0.144, median DSC is 0.702, maximum DSC is 0.893, and minimum DSC is 0.297) showed higher segmentation accuracy than the semi-automatic method (DSC = 0.614 ± 0.225, median DSC is 0.685, maximum DSC is 0.869, and minimum DSC is 0.047). Paired t-test shows significant difference (T = 2.160, p = 0.035) in DSC between the deep learning method and the semi-automatic method in the test group. Conclusion Volumetric U-Net can automatically segment rectal tumor region on DWI images of locally advanced rectal cancer.

Impact of slice thickness, pixel size, and CT dose on the performance of automatic contouring algorithms.

Abstract: Purpose To investigate the impact of computed tomography (CT) image acquisition and reconstruction parameters, including slice thickness, pixel size, and dose, on automatic contouring algorithms Methods Eleven scans from patients with head-and-neck cancer were reconstructed with varying slice thicknesses and pixel sizes CT dose was varied by adding noise using low-dose simulation software The impact of these imaging parameters on two in-house auto-contouring algorithms, one convolutional neural network (CNN)-based and one multiatlas-based system (MACS) was investigated for 183 reconstructed scans For each algorithm, auto-contours for organs-at-risk were compared with auto-contours from scans with 3 mm slice thickness, 0977 mm pixel size, and 100% CT dose using Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD) Results Increasing the slice thickness from baseline value of 3 mm gave a progressive reduction in DSC and an increase in HD and MSD on average for all structures Reducing the CT dose only had a relatively minimal effect on DSC and HD The rate of change with respect to dose for both auto-contouring methods is approximately 0 Changes in pixel size had a small effect on DSC and HD for CNN-based auto-contouring with differences in DSC being within 007 Small structures had larger deviations from the baseline values than large structures for DSC The relative differences in HD and MSD between the large and small structures were small Conclusions Auto-contours can deviate substantially with changes in CT acquisition and reconstruction parameters, especially slice thickness and pixel size The CNN was less sensitive to changes in pixel size, and dose levels than the MACS The results contraindicated more restrictive values for the parameters should be used than a typical imaging protocol for head-and-neck

Image synthesis of monoenergetic CT image in dual-energy CT using kilovoltage CT with deep convolutional generative adversarial networks

Abstract: Purpose To synthesize a dual-energy computed tomography (DECT) image from an equivalent kilovoltage computed tomography (kV-CT) image using a deep convolutional adversarial network. Methods A total of 18,084 images of 28 patients are categorized into training and test datasets. Monoenergetic CT images at 40, 70, and 140 keV and equivalent kV-CT images at 120 kVp are reconstructed via DECT and are defined as the reference images. An image prediction framework is created to generate monoenergetic computed tomography (CT) images from kV-CT images. The accuracy of the images generated by the CNN model is determined by evaluating the mean absolute error (MAE), mean square error (MSE), relative root mean square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mutual information between the synthesized and reference monochromatic CT images. Moreover, the pixel values between the synthetic and reference images are measured and compared using a manually drawn region of interest (ROI). Results The difference in the monoenergetic CT numbers of the ROIs between the synthetic and reference monoenergetic CT images is within the standard deviation values. The MAE, MSE, RMSE, and SSIM are the smallest for the image conversion of 120 kVp to 140 keV. The PSNR is the smallest and the MI is the largest for the synthetic 70 keV image. Conclusions The proposed model can act as a suitable alternative to the existing methods for the reconstruction of monoenergetic CT images in DECT from single-energy CT images.

Accuracy of surface-guided patient setup for conventional radiotherapy of brain and nasopharynx cancer.

Abstract: PURPOSE To evaluate the accuracy of surface-guided radiotherapy (SGRT) in cranial patient setup by direct comparison between optical surface imaging (OSI) and cone-beam computed tomography (CBCT), before applying SGRT-only setup for conventional radiotherapy of brain and nasopharynx cancer METHODS AND MATERIALS Using CBCT as reference, SGRT setup accuracy was examined based on 269 patients (415 treatments) treated with frameless cranial stereotactic radiosurgery (SRS) during 2018-2019 Patients were immobilized in customized head molds and open-face masks and monitored using OSI during treatment The facial skin area in planning CT was used as OSI region of interest (ROI) for automatic surface alignment and the skull was used as the landmark for automatic CBCT/CT registration A 6 degrees of freedom (6DOF) couch was used Immediately after CBCT setup, an OSI verification image was captured, recording the SGRT setup differences These differences were analyzed in 6DOFs and as a function of isocenter positions away from the anterior surface to assess OSI-ROI bias The SGRT in-room setup time was estimated and compared with CBCT and orthogonal 2D kilovoltage (2DkV) setups RESULTS The SGRT setup difference (magnitude) is found to be 10 ± 25 mm and 01˚±14˚ on average among 415 treatments and within 5 mm/3˚ with greater than 95% confidence level (P 50mm and 9 (22%) are >30˚ The setup differences show minor correlations (|r| < 045) between translational and rotational DOFs and a minor increasing trend (<10 mm) in the anterior-to-posterior direction The SGRT setup time is 08 ± 03 min, much shorter than CBCT (5 ± 2 min) and 2DkV (2 ± 1 min) setups CONCLUSION This study demonstrates that SGRT has sufficient accuracy for fast in-room patient setup and allows real-time motion monitoring for beam holding during treatment, potentially useful to guide radiotherapy of brain and nasopharynx cancer with standard fractionation

Impact of four kVp combinations available in a dual-source CT on the spectral performance of abdominal imaging: A task-based image quality assessment on phantom data.

Abstract: Purpose To compare the spectral performance of four combinations of kVp available in a third generation dual-source CT (DSCT) on abdominal imaging. Methods An image-quality phantom was scanned with a DSCT using four kVp pairs (tube "A" voltage/tube "B" voltage): 100/Sn150 kVp, 90/Sn150 kVp, 80/Sn150 kVp, and 70/Sn150 kVp, classic parameters and dose level for abdomen examination (CTDIvol : 11 mGy). The noise power spectrum (NPS) and the task-based transfer function (TTF) of two inserts were computed on virtual monochromatic images (VMIs) at 40/50/60/70 keV and for mixed, low-, and high-kVp images. Detectability index (d') was computed on VMIs and mixed images to model the detection task of liver metastasis (LM) and hepatocellular carcinoma (HCC). Iodine quantification accuracy was assessed using the Root Mean Square Deviation (RMSDiodine ) and the iodine bias (IB). Results Noise magnitude decreased by -55%± 0% between 40 and 70 keV for all kVp pairs. Compared to 70/Sn150 kVp, noise magnitude was increased by 9% ± 0% with 80/Sn150 kVp, by 16% ± 1% with 90/Sn150 kVp and by 24%± 1% with 100/Sn150 kVp. The average NPS spatial frequency (fav ) shifted toward higher frequencies as energy level increased for all kVp pairs. Lowest fav values were found for 70/Sn150 kVp and highest for 100/Sn150 kVp. The value of TTF at 50% (f50 ) shifted toward lower frequencies with increasing energy level. The highest f50 values occurred for 100/Sn150 kVp and the lowest for 80/Sn150 kVp. For both lesions, d' was highest for 70/Sn150 kVp and lowest for 100/Sn150 kVp. Compared to 70/Sn150 kVp, d' decreased by -6% ± 3% with 80/Sn150 kVp, by -11% ± 2% with 90/Sn150 kVp and by -13%± 2% with 100/Sn150 kVp. For all acquisitions, the RSMDiodine and IB were the lowest for 100/Sn150 kVp (0.29 ± 0.10 mg/ml and 0.88 ± 0.30 mg/ml, respectively) and increased when the tube "A" voltage decreased (2.34 ± 0.29 mg/ml for 70/Sn150 kVp and 7.42 ± 0.51 mg/ml respectively). Conclusion 70/Sn150 kVp presented the lowest image noise and highest detectability in VMIs of two small focal liver lesions. 100/Sn150 kVp presented the lowest image noise on mixed images and highest accuracy of iodine quantification in iodine images.

Survey of patient-specific quality assurance practice for IMRT and VMAT.

Abstract: A first-time survey across 15 cancer centers in Ontario, Canada, on the current practice of patient-specific quality assurance (PSQA) for intensity modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT) delivery was conducted. The objectives were to assess the current state of PSQA practice, identify areas for potential improvement, and facilitate the continued improvement in standardization, consistency, efficacy, and efficiency of PSQA regionally. The survey asked 40 questions related to PSQA practice for IMRT/VMAT delivery. The questions addressed PSQA policy and procedure, delivery log evaluation, instrumentation, measurement setup and methodology, data analysis and interpretation, documentation, process, failure modes, and feedback. The focus of this survey was on PSQA activities related to routine IMRT/VMAT treatments on conventional linacs, including stereotactic body radiation therapy but excluding stereotactic radiosurgery. The participating centers were instructed to submit answers that reflected the collective view or opinion of their department and represented the most typical process practiced. The results of the survey provided a snapshot of the current state of PSQA practice in Ontario and demonstrated considerable variations in the practice. A large majority (80%) of centers performed PSQA measurements on all VMAT plans. Most employed pseudo-3D array detectors with a true composite (TC) geometry. No standard approach was found for stopping or reducing frequency of measurements. The sole use of delivery log evaluation was not widely implemented, though most centers expressed interest in adopting this technology. All used the Gamma evaluation method for analyzing PSQA measurements; however, no universal approach was reported on how Gamma evaluation and pass determination criteria were determined. All or some PSQA results were reviewed regularly in two-thirds of the centers. Planning related issues were considered the most frequent source for PSQA failures (40%), whereas the most frequent course of action for a failed PSQA was to review the result and decide whether to proceed to treatment.

Acceptance procedure for the linear accelerator component of the 1.5 T MRI-linac

Abstract: Purpose To develop and implement an acceptance procedure for the new Elekta Unity 1.5 T MRI-linac. Methods Tests were adopted and, where necessary adapted, from AAPM TG106 and TG142, IEC 60976 and NCS 9 and NCS 22 guidelines. Adaptations were necessary because of the atypical maximum field size (57.4 × 22 cm), FFF beam, the non-rotating collimator, the absence of a light field, the presence of the 1.5 T magnetic field, restricted access to equipment within the bore, fixed vertical and lateral table position, and the need for MR image to MV treatment alignment. The performance specifications were set for stereotactic body radiotherapy (SBRT). Results The new procedure was performed similarly to that of a conventional kilovoltage x-ray (kV) image guided radiation therapy (IGRT) linac. Results were acquired for the first Unity system. Conclusions A comprehensive set of tests was developed, described and implemented for the MRI-linac. The MRI-linac met safety requirements for patients and operators. The system delivered radiation very accurately with, for example a gantry rotation locus of isocenter of radius 0.38 mm and an average MLC absolute positional error of 0.29 mm, consistent with use for SBRT. Specifications for clinical introduction were met.

An improved method for automated calculation of the water-equivalent diameter for estimating size-specific dose in CT.

Abstract: Purpose The aim of this study is to propose an algorithm for the automated calculation of water-equivalent diameter (Dw ) and size-specific dose estimation (SSDE) from clinical computed tomography (CT) images containing one or more substantial body part. Methods All CT datasets were retrospectively acquired by the Toshiba Aquilion 128 CT scanner. The proposed algorithm consisted of a contouring stage for the Dw calculation, carried out by taking the six largest objects in the cross-sectional image of the patient's body, followed by the removal of the CT table depending on the center position (y-axis) of each object. Validation of the proposed algorithm used images of patients who had undergone chest examination with both arms raised up, one arm placed down and both arms placed down, images of the pelvic region consisting of one substantial object, and images of the lower extremities consisting of two separated areas. Results The proposed algorithm gave the same results for Dw and SSDE as the previous algorithm when images consisted of one substantial body part. However, when images consisted of more than one substantial body part, the new algorithm was able to detect all parts of the patient within the image. The Dw values from the proposed algorithm were 9.5%, 15.4%, and 39.6% greater than the previous algorithm for the chest region with one arm placed down, both arms placed down, and images with two legs, respectively. The SSDE values from the proposed algorithm were 8.2%, 11.2%, and 20.6% lower than the previous algorithm for the same images, respectively. Conclusions We have presented an improved algorithm for automated calculation of Dw and SSDE. The proposed algorithm is more general and gives accurate results for both Dw and SSDE whether the CT images contain one or more than one substantial body part.

Clinical and radiological predictors of epidermal growth factor receptor mutation in nonsmall cell lung cancer.

Abstract: Purpose To determine the prognostic factors of epidermal growth factor receptor (EGFR) mutation status in a group of patients with nonsmall cell lung cancer (NSCLC) by analyzing their clinical and radiological features. Materials and methods Patients with NSCLC who underwent EGFR mutation detection between 2014 and 2017 were included. Clinical features and general imaging features were collected, and radiomic features were extracted from CT data by 3D Slicer software. Prognostic factors of EGFR mutation status were selected by least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and receiver operating characteristic (ROC) curves were drawn for each prediction model of EGFR mutation. Results A total of 118 patients were enrolled in this study. The smoking index (P = 0.028), pleural retraction (P = 0.041), and three radiomic features were significantly associated with EGFR mutation status. The areas under the ROC curve (AUCs) for prediction models of clinical features, general imaging features, and radiomic features were 0.284, 0.703, and 0.815, respectively, and the AUC for the combined prediction model of the three models was 0.894. Finally, a nomogram was established for individualized EGFR mutation prediction. Conclusions The combination of radiomic features with clinical features and general imaging features can enable discrimination of EGFR mutation status better than the use of any group of features alone. Our study may help develop a noninvasive biomarker to identify EGFR mutation status by using a combination of the three group features.

Prostate SBRT using O-Ring Halcyon Linac - Plan quality, delivery efficiency, and accuracy.

Abstract: Cone beam CT-guided prostate stereotactic body radiotherapy (SBRT) treatment on the recently installed novel O-ring coplanar geometry Halcyon Linac with a single energy 6MV-flattening filter free (FFF) beam and volumetric modulated arc therapy (VMAT) is a fast, safe, and feasible treatment modality for early stage low- and intermediate-risk prostate cancer patients. Following the RTOG-0938 compliance criteria and utilizing two-full arc geometry, VMAT prostate SBRT plans were generated for ten consecutive patients using advanced Acuros-based algorithm for heterogeneity corrections with Halcyon couch insert. Halcyon VMAT plans with the stacked and staggered multileaf collimators (MLC) produced highly conformal SBRT dose distributions to the prostate, lower intermediate dose spillage and similar dose to adjacent organs-at-risks (OARs) compared to SBRT-dedicated Truebeam VMAT plans. Due to lower monitor units per fraction and less MLC modulation through the target, the Halcyon VMAT plan can deliver prostate SBRT fractions in and overall treatment time of less than 10 minutes (for 36.25 Gy in five fractions), significantly improving patient compliance and clinic workflow. Pretreatment quality assurance results were similar to Truebeam VMAT plans. We have implemented Halcyon Linac for prostate SBRT treatment in our institution. We recommend that others use Halcyon for prostate SBRT treatments to expand the access of curative hypofractionated treatments to other clinics only equipped with a Halcyon Linac. Clinical follow-up results for patients who underwent prostate SBRT treatment on our Halcyon Linac is underway.

Image-guided volumetric-modulated arc therapy of total body irradiation: An efficient workflow from simulation to delivery.

Abstract: INTRODUCTION Using multi-isocenter volumetric-modulated arc therapy (VMAT) for total body irradiation (TBI) may improve dose uniformity and vulnerable tissue protection compared with classical whole-body field technique. Two drawbacks limit its application: (1) VMAT-TBI planning is time consuming; (2) VMAT-TBI plans are sensitive to patient positioning uncertainties due to beam matching. This study presents a robust planning technique with image-guided delivery to improve dose delivery accuracy. In addition, a streamlined sim-to-treat workflow with automatic scripts is proposed to reduce planning time. MATERIALS Twenty-five patients were included in this study. Patients were scanned in supine head-first and feet-first directions. An automatic workflow was used to (1) create a whole-body CT by registering two CT scans, (2) contour lungs, kidneys, and planning target volume (PTV), (3) divide PTV into multiple sub-targets for planning, and (4) place isocenters. Treatment planning included feathered AP/PA beams for legs/feet and VMAT for the body. VMAT-TBI was evaluated for plan quality, planning/delivery time, and setup accuracy using image guidance. RESULTS VMAT-TBI planning time can be reduced to a day with automatic scripts. Treatment time took around an hour per fraction. VMAT-TBI improved dose coverage (PTV V100 increased from 76.8 ± 10.5 to 88.5 ± 2.6; p < 0.001) and reduced lung dose (lung mean dose reduced from 10.8 ± 0.7 Gy to 9.4 ± 0.8 Gy, p < 0.001) compared with classic AP/PA technique. CONCLUSION A VMAT-TBI sim-to-treat workflow with robust planning and image-guided delivery was proposed. VMAT-TBI improved the plan quality compared with classical whole-body field techniques.

Analysis of patient-specific quality assurance for Elekta Unity adaptive plans using statistical process control methodology.

Abstract: The Elekta Unity MR-linac utilizes daily magnetic resonance imaging (MRI) for online plan adaptation. In the Unity workflow, adapt to position (ATP) and adapt to shape (ATS) treatment planning options are available which represent a virtual shift or full re-plan with contour adjustments respectively. Both techniques generate a new intensity modulated radiation therapy (IMRT) treatment plan while the patient lies on the treatment table and thus adapted plans cannot be measured prior to treatment delivery. A statistical process control methodology was used to analyze 512 patient-specific IMRT QA measurements performed on the MR-compatible SunNuclear ArcCheck with a gamma criterion of 3%/2 mm using global normalization and a 10% low dose threshold. The lower control limit (LCL) was determined from 68 IMRT reference plan measurements, and a one-sided process capability ratio ( C p , l ) was used to assess the pass rates from 432 measured ATP and 80 measured ATS plans. Further analysis was performed to assess differences between SBRT or conventional fractionation pass rates and to determine whether there was any correlation between the pass rates and plan complexity. The LCL of the reference plans was determined to be a gamma pass rate of 0.958, and the C p , l of the measured ATP plans and measured ATS plans were determined to be 1.403 and 0.940 for ATP and ATS plans, respectively, while a C p , l of 0.902 and 1.383 was found for SBRT and conventional fractionations respectively. For plan complexity, no correlation was found between modulation degree and gamma pass rate, but a statistically significant correlation was observed between the beam-averaged aperture area and gamma pass rate. All adaptive plans passed the TG-218 guidelines, but the ATS and SBRT plans tended to have a smaller beam-averaged aperture area with slightly lower gamma pass rates.

Out-of-field doses from radiotherapy using photon beams: A comparative study for a pediatric renal treatment.

Abstract: Purpose First, this experimental study aims at comparing out-of-field doses delivered by three radiotherapy techniques (3DCRT, VMAT (two different accelerators), and tomotherapy) for a pediatric renal treatment Secondly, the accuracy of treatment planning systems (TPS) for out-of-field calculation is evaluated Methods EBT3 films were positioned in pediatric phantoms (5 and 10 yr old) They were irradiated according to four plans: 3DCRT (Clinac 2100CS, Varian), VMAT (Clinac 2100CS and Halcyon, Varian), and tomotherapy for a same target volume 3D dose determination was performed with an in-house Matlab tool using linear interpolation of film measurements 1D and 3D comparisons were made between techniques Finally, measurements were compared to the Eclipse (Varian) and Tomotherapy (Accuray) TPS calculations Results Advanced radiotherapy techniques (VMATs and tomotherapy) deliver higher out-of-field doses compared to 3DCRT due to increased beam-on time triggered by intensity modulation Differences increase with distance to target and reach a factor of 3 between VMAT and 3DCRT Besides, tomotherapy delivers lower doses than VMAT: although tomotherapy beam-on time is higher than in VMAT, the additional shielding of the Hi-Art system reduces out-of-field doses The latest generation Halcyon system proves to deliver lower peripheral doses than conventional accelerators Regarding TPS calculation, tomotherapy proves to be suitable for out-of-field dose determination up to 30 cm from field edge whereas Eclipse (AAA and AXB) largely underestimates those doses Conclusion This study shows that the high dose conformation allowed by advanced radiotherapy is done at the cost of higher peripheral doses In the context of treatment-related risk estimation, the consequence of this increase might be significative Modern systems require adapted head shielding and a particular attention has to be taken regarding on-board imaging dose Finally, TPS advanced dose calculation algorithms do not certify dose accuracy beyond field edges, and thus, those doses are not suitable for risk assessment

Clinical validation of ring-mounted halcyon linac for lung SBRT: comparison to SBRT-dedicated C-arm linac treatments.

Abstract: Stereotactic body radiotherapy (SBRT) of lung tumors via the ring-mounted Halcyon Linac, a fast kilovoltage cone beam CT-guided treatment with coplanar geometry, a single energy 6MV flattening filter free (FFF) beam and volumetric modulated arc therapy (VMAT) is a fast, safe, and feasible treatment modality for selected lung cancer patients. Four-dimensional (4D) CT-based treatment plans were generated using advanced AcurosXB algorithm with heterogeneity corrections using an SBRT board and Halcyon couch insert. Halcyon VMAT-SBRT plans with stacked and staggered multileaf collimators produced highly conformal radiosurgical dose distribution to the target, lower intermediate dose spillage, and similar dose to adjacent organs at risks (OARs) compared to SBRT-dedicated highly conformal clinical noncoplanar Truebeam VMAT plans following the RTOG-0813 requirements. Due to low monitor units per fraction and less multileaf collimator (MLC) modulation, the Halcyon VMAT plan can deliver lung SBRT fractions with an overall treatment time of less than 15 min (for 50 Gy in five fractions), significantly improving patient comfort and clinic workflow. Higher pass rates of quality assurance results demonstrate a more accurate treatment delivery on Halcyon. We have implemented Halcyon for lung SBRT treatment in our clinic. We suggest others use Halcyon for lung SBRT treatments using abdominal compression or 4D CT-based treatment planning, thus expanding the access of curative ultra-hypofractionated treatments to other centers with only a Halcyon Linac. Clinical follow-up results for patients treated on Halcyon Linac with lung SBRT is ongoing.

Largely reduced OAR doses, and planning and delivery times for challenging robotic SBRT cases, obtained with a novel optimizer.

Abstract: Recently, VOLO™ was introduced as a new optimizer for CyberKnife® planning. In this study, we investigated possibilities to improve treatment plans for MLC-based prostate SBRT with enhanced peripheral zone dose while sparing the urethra, and central lung tumors, compared to existing Sequential Optimization (SO). The primary focus was on reducing OAR doses. For 25 prostate and 25 lung patients treated with SO plans, replanning with VOLO™ was performed with the same planning constraints. For equal PTV coverage, almost all OAR plan parameters were improved with VOLO™. For prostate patients, mean rectum and bladder doses were reduced by 34.2% (P < 0.001) and 23.5% (P < 0.001), with reductions in D0.03cc of 3.9%, 11.0% and 3.1% for rectum, mucosa and bladder (all P ≤ 0.01). Urethra D5% and D10% were 3.8% and 3.0% lower (P ≤ 0.002). For lung patients, esophagus, main bronchus, trachea, and spinal cord D0.03cc was reduced by 18.9%, 11.1%, 16.1%, and 13.2%, respectively (all P ≤ 0.01). Apart from the dosimetric advantages of VOLO™ planning, average reductions in MU, numbers of beams and nodes for prostate/lung were 48.7/32.8%, 26.5/7.9% and 13.4/7.9%, respectively (P ≤ 0.003). VOLO™ also resulted in reduced delivery times with mean/max reductions of: 27/43% (prostate) and 15/41% (lung), P < 0.001. Planning times reduced from 6 h to 1.1 h and from 3 h to 1.7 h for prostate and lung, respectively. The new VOLO™ planning was highly superior to SO planning in terms of dosimetric plan quality, and planning and delivery times.