Planning CT Images Research Articles

Handcrafted Radiomics, Deep Learning Radiomics in the Prediction of Radiation Pneumonitis for NSCLC Patients Treated with Immunotherapy Followed with Thoracic Radiotherapy

Our previous study has shown that NSCLC patients previously received immune checkpoint inhibitors (ICIs) underwent thoracic intensity modulated radiotherapy have a higher risk of acute radiation pneumonitis (RP). This study aimed to establish machine learning models using handcrafted radiomics (HCR), deep learning-based radiomics (DLR) and clinical characteristics to improve the prediction of symptomatic radiation pneumonitis (RP) (grade ≥ 2) status for NSCLC patients treated with immunotherapy followed with thoracic radiotherapy. This study retrospectively collected data of 61 NSCLC patients meeting the requirements of study enrollment. Of these 61 patients, 35 developed symptomatic graded ≥ 2 RP. We defined 3 regions of interest (ROIs) in planning CT images including gross tumor volume (GTV), planning tumor volume (PTV), PTV-GTV. We calculated the mean dose, V5, V10, V20, and V30 within TL-GTV, and the volume of GTV, PTV and total lung. A total of 516 handcrafted radiomics features and 512 deep features were extracted from each 3 ROIs. Person Correlation Analysis and Least Absolute Shrinkage and Selection Operator (LASSO) were used to reduce the dimension of features. The HCR models, DLR models and the fusion models across different ROIs with machine learning classifiers were built and compared. In multi-classifier modeling, models with PTV under logistic regression (LR) classifiers showed better prediction than other ROIs under different machine learning algorithms. Based on PTV with LR, HCR+ DLR model had better performance, with an area under the curve (AUC) of 0.95 (95% confidence interval (CI): 0.893-1) in the training cohort and 0.87 (95% CI: 0.698-1) in the test cohort, which was higher than that of HCR model, with an AUC of 0.86 (95% CI: 0.755-0.9) in the training cohort and 0.82 (95% CI: 0.624-1) in the test cohort, the results of fusion model with HCR, DLR and 7 clinical characteristics including T, N, clinical stage, age, smoking, radiotherapy alone/combined and V30, demonstrated the best distinguishing performance, with an AUC of 0.99 (95% CI: 0.970-1) in the training cohort and 0.91 (95% CI: 0.784-1) in the test cohort. The combination of HCR, DLR and clinical characteristic underwent machine learning algorithms can improve the prediction of symptomatic RP in NSCLC patients treated with ICIs followed with thoracic radiotherapy.

A Hybrid Intelligence (HI) System for Segmenting Rectoprostatic Spacer Gel and Key OARs on CT Images for Prostate Cancer Radiation Therapy Planning

Our hybrid intelligence (HI) system, combining natural and artificial intelligence, is effective for auto-contouring H&N and thorax organs at risk (OARs) for radiation therapy (RT) planning with FDA 510(k) clearance. The purpose of this study is to test the HI system to segment a commercially available retroprostatic hyaluronic acid spacer gel (RSG) and pelvic OARs in planning CT images for prostate cancer RT. HI can achieve clinically acceptable auto segmentation for tissue-equivalent RSG in this domain. RSG is injected in the peri-rectal space in men with prostate cancer prior to RT to minimize rectal toxicity. 190 patients with prostate cancer were included in this post-hoc image analysis from a multi-center, prospective, randomized trial, with 136 in the spacer arm. The HI system has 3 steps: rough recognition from fuzzy model (FM) based automatic anatomy recognition (AAR-R), deep learning-based recognition (DL-R) refinement, and deep learning-based delineation (DL-D) to contour objects guided by the recognition results. FM encodes high level 3D anatomy knowledge of object shape and its relationship with other OARs; DL-R and DL-D focus on pixel-level details. The 190 studies are divided into disjoint training (100) and testing (90) subsets. 100 samples are used in DL-R and DL-D training, with 45 to build the FM for AAR-R. RSG and 4 other OARs (pelvic skin, prostate, bladder, rectum) are contoured. Location error (LE) is used to evaluate recognition; Dice coefficient (DC) and Hausdorff distance (HD) are employed to evaluate delineation. Acceptability scores (AS) (range 1-5, 1 for poor quality, 5 for best quality) from an observer study are recorded for HI-output and ground truth masks of RSG for assessing segmentation quality. The HI system achieves highest DC (0.94±0.07) and lowest HD (1.96±1.61 mm) for bladder, for rectum and prostate similar DC (0.82±0.08) and HD (2.62±1.65mm), for RSG, the most challenging object, a good DC close to 0.7 (0.67±0.10) and excellent HD (2.66±1.44mm). AS for auto-segmentations (3.86±0.85) were significantly better than those for ground truth segmentations (3.45±1.00) (p = 0.02, paired t-test). Table 1 summarizes results. The HI system achieves clinically acceptable segmentations for pelvic OARs and significantly better acceptability of segmentation of RSG compared to clinically performed ground truth segmentations. This has implications in improving efficiency and accuracy of CT-based RT planning in patients with prostate cancer.

Dosimetric Study of Total Marrow and Lymphoid Irradiation on a Ring Gantry-Based Medical Linac with a Two-Layer Multi-Leaf Collimator

In this study, we aimed to evaluate dosimetric quality of total marrow and lymphoid irradiation (TMLI) plans for a ring gantry-based medical Linac with a two-layer multi-leaf collimator. We retrospectively retrieved treatment planning CT images, structure sets, and plan dose for four adult patients, two male and two female, who previously received TMLI treatments on helical tomotherapy (HT) at our institution. TMLI plans were optimized for a ring gantry-based medical Linac with a two-layer multi-leaf collimator (Halcyon, Varian Medical Systems, Inc., Palo Alto, CA). A prescription dose of 12 Gy in 8 fractions was prescribed to the skeletal bones from the skull to mid-thigh, spleen, spinal canal, and lymphoid volume. Five or six isocenters were placed with equal spacing along the patient's longitudinal direction in each TMLI plan with two 6-MV flattening filter-free volumetric modulated arc therapy (VMAT) fields at each isocenter. Isocenter separation ranged from 15 cm to 16.5 cm. Each VMAT field has a field size of 28 cm to 28 cm with the collimator at 90° and a full gantry rotation. The nominal dose rate was 800 MU/minute, and the maximum gantry rotation speed was 24°/sec. Institutional dosimetric constraints were used for optimization including a mean lung dose limit of less than 8 Gy. All the plans were normalized so that 85% the primary planning target volume received the prescription dose. The average mean doses to the target volumes ranged from 12.2 to 12.6 Gy in the Halcyon TMLI plans, while they ranged from 12.1 to 12.5 Gy in the HT TMLI plans. Relative to the prescription dose, the average mean dose for normal organs ranged from 21.3% to 56.6% in the Halcyon TMLI plans, while it ranged from 10.1% to 68.4% in the clinical HT plans. The difference in the average mean dose to normal organs was less than 0.5 Gy except two organs between the Halcyon and HT TMLI plans. The average median dose for normal organs ranged from 18.2% to 48.8% relative to the prescription dose in the Halcyon TMLI plans. The mean lung dose (MLD) in the Halcyon TMLI plans met the institutional limit with an average dose of 6.75±0.42 Gy (range: 6.44 - 7.36 Gy), while the average MLD was 6.54±0.77 Gy (range: 6.24 - 7.22 Gy) in the HT plans (p-value = 0.71 in the paired t-test). The average total monitor unit in the Halcyon TMLI plans was 4,425±906 MU (range: 3,470 - 5,575 MU) with an average beam-on time of 5.1±1.3 minutes (range: 4.1 - 7.0 minutes), which excludes isocenter setup time, while the average beam-on time was 22.2±3.2 minutes (range: 19.6 - 26.1 minutes) with the HT plans. Halcyon TMLI plans met our institutional dosimetric constraints with adequate normal organ sparing and target dose coverage. The beam-on time with the Halcyon plans was significantly shorter than that with the HT plans, which could lead to shorter treatment time and increased patient comfort. This study showed the feasibility of TMLI treatments on the Halcyon machine. The same method could be used for total body irradiation on Halcyon.

Predictive Modeling of Radiation Pneumonitis Induced by Chemoradiotherapy for Locally Advanced Non-Small Cell Lung Cancer Using Radiomics and Clinical Features

The purpose of this study is to establish a prediction model for the development of grade 2 or higher radiation pneumonitis (RP) using radiomics analysis of pretreatment CT images, PET images, and dose distribution, in addition to clinical factors, in patients with locally advanced non-small cell lung cancer (NSCLC) treated with radical chemoradiotherapy. We retrospectively evaluated 128 cases of locally advanced NSCLC treated with radical radiotherapy at our institution from 2008 to 2021. Clinical factors included age, sex, performance status (PS), KL-6, smoking history, histological type, clinical stage, and total radiation dose. Radiomics analysis was performed by analyzing treatment planning CT images, PET images, and dose distribution, and Rad-score (Radiomics-score) was calculated for the extracted features using Lasso-Cox regression. Rad-score (Radiomics-score) was calculated by Lasso-Cox regression for the extracted features. Risk factors were selected by univariate/multivariate analysis of clinical factors and Rad-score. Three models for predicting RP were developed from the identified risk factors using Nomogram: Clinical, Rad-score, and Combined model. The model was evaluated using area under the curve (AUC) based on receiver operating characteristic (ROC) curves and concordance index (C-index). RP was evaluated using the Common Terminology Criteria for Adverse Events (CTCAE) version 5.0. The cumulative incidence of Grade 2 or higher RP was evaluated using the Kaplan-Meier method. Of the 128 cases, grade 2 or higher RP was observed in 50 cases (39%). Regarding clinical factors, gender, smoking status, and histology were selected as significant predictors of RP. Lasso-Cox analysis of radiomics features selected 11 features from CT images, 7 features from PET images, and 16 features from dose distribution as predictors of RP, yielding a total of 34 factors. The combined model (C-index: 0.96, AUC: 0.92) showed the best discrimination performance compared to the clinical model (C-index: 0.73, AUC: 0.56) and the Rad-score model (C-index: 0.87, AUC: 0.92). Risk classification using the combined model showed that the 1-year cumulative incidence of grade 2 or higher RP was 65% in the high-risk group, significantly higher than 15% in the low-risk group (p<0.001). The combined model with Rad-score and clinical factors can predict grade 2 or higher RP in NSCLC patients with high accuracy.

Assessment of the Spatial Bio-Distribution of NBTXR3 for Locally Advanced or Borderline-Resectable Pancreatic Ductal Adenocarcinoma (LAPC or BRPC) Patients Undergoing Radiation Therapy

NBTXR3 is a novel radioenhancer composed of functionalized hafnium oxide nanoparticles that are injected directly into the tumor. An ongoing phase I trial is assessing the application of NBTXR3 in the treatment of locally-advanced or borderline-resectable pancreatic ductal adenocarcinoma, with the primary goal of determining the recommended NBTXR3 dose for a subsequent phase II trial. Using patients from the ongoing phase I trial, we evaluated the spatial bio-distribution of NBTXR3 in the pancreas as function of time and assessed if there is migration of the compound during radiation therapy. Adult patients with LAPC or BRPC were enrolled. Analysis of 8 patients who underwent CT simulation at least 24 hours after receiving the NBTXR3 intratumoral injection in the pancreatic lesion under general anesthesia guided by an endoscopic ultrasound was conducted. Patients were simulated with and without iodinated intravenous contrast under breath hold, with 3mm CT slice thickness and 50-60cm FoV. A contrast-enhanced CT series was chosen for RT planning purposes. All patients were planned for a 15-fraction IMRT course using 6-MV beam energy, with 45Gy and 37.5Gy dose levels (using a simultaneous integrated boost technique) to gross primary tumor and microscopic disease/regional nodes, respectively. Daily image guidance included either cone-beam CT (CBCT, n = 1) or CT-on-Rails (CTOR, n = 7) and were fused to the planning CT images using Velocity, ver. 3.0.1. The NBTXR3 volume was determined by thresholding the images to 165 HU and 300 HU for CTOR and CBCT images, respectively. Bones, stents, and artifacts were manually removed from the NBTXR3 volume. The volumes for the NBTXR3 and the NBTXR3 overlapping with the GTV for each patient were individually fit to a linear model in R, ver. 4.1.3. One patient from the CTOR cohort was excluded from analysis due to the small volume of NBTXR3 (0.02 cm3) compared to the rest of the cohort (0.716 - 6.917 cm3). The total volume of NBTXR3 in the CBCT images could not be analyzed due the substantial image artifacts, only the volume overlapping the GTV was calculated. There were no statistically significant changes (p > 0.1 Adj-R2 = 0.99) in the raw volume of NBTXR3 for the duration of the treatment in all CTOR patients. For the NBTXR3 volume overlapping with the GTV, five cases did not present with a volume change during the treatment (p > 0.1 Adj-R2 = 0.99), while one CTOR case had a reduction in volume of about 1.5%/day (p = 0.7), and the CBCT case had a reduction of 3%/day (p < 0.001). The raw volume of NBTXR3 injected in the pancreas did not significantly change over the duration of the three weeks of treatment. We also did not observe significant changes in the NBTXR3 volume overlapping the GTV in most cases. The stability of NBTXR3 was demonstrated during RT.

Evaluation of synthetically generated computed tomography for use in transcranial focused ultrasound procedures.

Transcranial focused ultrasound (tFUS) is a therapeutic ultrasound method that focuses sound through the skull to a small region noninvasively and often under magnetic resonance imaging (MRI) guidance. CT imaging is used to estimate the acoustic properties that vary between individual skulls to enable effective focusing during tFUS procedures, exposing patients to potentially harmful radiation. A method to estimate acoustic parameters in the skull without the need for CT is desirable. We synthesized CT images from routinely acquired T1-weighted MRI using a 3D patch-based conditional generative adversarial network and evaluated the performance of synthesized CT (sCT) images for treatment planning with tFUS. We compared the performance of sCT with real CT (rCT) images for tFUS planning using Kranion and simulations using the acoustic toolbox, k-Wave. Simulations were performed for 3 tFUS scenarios: (1)no aberration correction, (2)correction with phases calculated from Kranion, and (3)phase shifts calculated from time reversal. From Kranion, the skull density ratio, skull thickness, and number of active elements between rCT and sCT had Pearson's correlation coefficients of 0.94, 0.92, and 0.98, respectively. Among 20 targets, differences in simulated peak pressure between rCT and sCT were largest without phase correction () and smallest with Kranion phases (). The distance between peak focal locations between rCT and sCT was for all simulation cases. Real and synthetically generated skulls had comparable image similarity, skull measurements, and acoustic simulation metrics. Our work demonstrated similar results for 10 testing cases comparing MR-sCTs and rCTs for tFUS planning. Source code and a docker image with the trained model are available at https://github.com/han-liu/SynCT_TcMRgFUS.

Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy.

Image segmentation can be time-consuming and lacks consistency between different oncologists, which is essential in conformal radiotherapy techniques. We aimed to evaluate automatic delineation results generated by convolutional neural networks (CNNs) from geometry and dosimetry perspectives and explore the reliability of these segmentation tools in rectal cancer. Forty-seven rectal cancer cases treated from February 2018 to April 2019 were randomly collected retrospectively in our cancer center. The oncologists delineated regions of interest (ROIs) on planning CT images as the ground truth, including clinical target volume (CTV), bladder, small intestine, and femoral heads. The corresponding automatic segmentation results were generated by DeepLabv3+ and ResUNet, and we also used Atlas-Based Autosegmentation (ABAS) software for comparison. The geometry evaluation was carried out using the volumetric Dice similarity coefficient (DSC) and surface DSC, and critical dose parameters were assessed based on replanning optimized by clinically approved or automatically generated CTVs and organs at risk (OARs), i.e., the Planref and Plantest. Pearson test was used to explore the correlation between geometric metrics and dose parameters. In geometric evaluation, DeepLabv3+ performed better in DCS metrics for the CTV (volumetric DSC, mean = 0.96, P< 0.01; surface DSC, mean = 0.78, P< 0.01) and small intestine (volumetric DSC, mean = 0.91, P< 0.01; surface DSC, mean = 0.62, P< 0.01), ResUNet had advantages in volumetric DSC of the bladder (mean = 0.97, P< 0.05). For critical dose parameters analysis between Planref and Plantest, there was a significant difference for target volumes (P< 0.01), and no significant difference was found for the ResUNet-generated small intestine (P > 0.05). For the correlation test, a negative correlation was found between DSC metrics (volumetric, surface DSC) and dosimetric parameters (δD95, δD95, HI, CI) for target volumes (P< 0.05), and no significant correlation was found for most tests of OARs (P > 0.05). CNNs show remarkable repeatability and time-saving in automatic segmentation, and their accuracy also has a certain potential in clinical practice. Meanwhile, clinical aspects, such as dose distribution, may need to be considered when comparing the performance of auto-segmentation methods.

A transformer-based dual-domain network for reconstructing FOV extended cone-beam CT images from truncated sinograms in radiation therapy

Background and objectiveCone-beam computed tomography (CBCT) is widely used in clinical radiotherapy, but its small field of view (sFOV) limits its application potential. In this study, a transformer-based dual-domain network (dual_swin), which combined image domain restoration and sinogram domain restoration, was proposed for the reconstruction of complete CBCT images with extended FOV from truncated sinograms. MethodsThe planning CT images with large FOV (LFOV) of 330 patients who received radiation therapy were collected. The synthetic CBCT (sCBCT) images with LFOV were generated from CT images by the trained cycleGAN network, and CBCT images with sFOV were obtained through forward projection, projection truncation, and filtered back projection (FBP), comprising the training and test data. The proposed dual_swin includes sinogram domain restoration, image domain restoration, and FBP layer, and the swin transformer blocks were used as the basic feature extraction module in the network to improve the global feature extraction ability. The proposed dual_swin was compared with the image domain method, the sinogram domain method, the U-Net based dual domain network (dual_Unet), and the traditional iterative reconstruction method based on prior image and conjugate gradient least-squares (CGLS) in the test of sCBCT images and clinical CBCT images. The HU accuracy and body contour accuracy of the predicted images by each method were evaluated. ResultsThe images generated using the CGLS method were fuzzy and obtained the lowest structural similarity (SSIM) among all methods in the test of sCBCT and clinical CBCT images. The predicted images by the image domain methods are quite different from the ground truth and have low accuracy on HU value and body contour. In comparison with image domain methods, sinogram domain methods improved the accuracy of HU value and body contour but introduced secondary artifacts and distorted bone tissue. The proposed dual_swin achieved the highest HU and contour accuracy with mean absolute error (MAE) of 23.0 HU, SSIM of 95.7%, dice similarity coefficient (DSC) of 99.6%, and Hausdorff distance (HD) of 4.1 mm in the test of sCBCT images. In the test of clinical patients, images that were predicted by dual_swin yielded MAE, SSIM, DSC, and HD of 38.2 HU, 91.7%, 99.0%, and 5.4 mm, respectively. The predicted images by the proposed dual_swin has significantly higher accuracy than the other methods (P < 0.05). ConclusionsThe proposed dual_swin can accurately reconstruct FOV extended CBCT images from the truncated sinogram to improve the application potential of CBCT images in radiotherapy.

Pre-treatment predictors of cardiac dose exposure in left-sided breast cancer radiotherapy patients after breast conserving surgery

Abstract Objectives This study aimed to identify high-risk factors for high cardiac radiation exposure, based on anatomical measurements taken from planning CT images of patients with left-sided breast cancer who underwent breast-conserving surgery and received radiotherapy. Methods We retrospectively analyzed 45 patients with left-sided breast cancer who underwent whole-breast radiotherapy, either under free breathing (27/45) or deep inspiratory breath-holding (DIBH) (18/45), after breast-conserving surgery. Six anatomical parameters were measured from planning CT images, including treatment planning target volume (PTV), cardiopulmonary volume ratio (CVR), maximum cardiac margin distance, the relative distance between inferior boundaries of heart and PTV (DBIB(H2P)), axial cardiac contact distance, and para-sagittal cardiac contact distance (CCDps). Multiple linear regression analysis was performed using SPSS software to explore the correlation between the six parameters, body mass index (BMI), and the mean heart dose (MHD). Receiver operating characteristic (ROC) analysis was performed to evaluate the predictive power of the selected predictor of cardiac dose exposure. Results Significant correlations were observed between the MHD of patients and the CVR, DBIB(H2P), and CCDps parameters. Among them, the CVR was the most important predictor of cardiac dose exposure, with an area under the curve of 0.915 and a cut-off value of 0.17. Conclusions The study results indicated that CVR, DBIB(H2P), and CCDps are the primary parameters associated with the risk of cardiac dose exposure, with CVR being the most significant predictor. Further prospective studies are required to determine whether these parameters can be used to identify patients who would benefit from the DIBH technique.

A comparative study of rectal volume variation in patients with prostate cancer: A tertiary care center study

IntroductionEvery day variations in rectal filling in prostate cancer radiotherapy can significantly alter the delivered dose distribution from what was intended. The goal of this study was to see if the time of treatment delivery affected the rectal filling. MethodsThis is a retrospective study which included 50 patients with localized prostate cancer treated with volumetric modulated arc therapy (VMAT) to the primary and regional lymph nodes. Cone Beam Computed Tomography (CBCT) image-sets were done for all patient's daily setup verification. The radiation therapist contoured the rectum on all CBCT image sets. The rectal volumes delineated on CBCT and the planning CT image sets were compared. The change in rectal volumes between morning and afternoon treatments were calculated and compared. ResultsA total of 1000 CBCT image sets were obtained on 50 patients in the morning and afternoon. The percentage variation of the CBCT rectal volumes over the planning CT scan was 16.57% in the AM group and 24.35% in the PM group. ConclusionThe percentage change in rectal volume was significantly lesser in AM group compared to PM group and therefore morning treatments may result in dose distribution that is close to the intended dose distribution. Implications for practiceIn prostate cancer radiotherapy our study suggests that a simple technique of changing the time of treatment from afternoon to morning can help to reduce the rectal volume.

Deep neural network-based synthetic image digital fluoroscopy using digitally reconstructed tomography.

We developed a deep neural network (DNN) to generate X-ray flat panel detector (FPD) images from digitally reconstructed radiographic (DRR) images. FPD and treatment planning CT images were acquired from patients with prostate and head and neck (H&N) malignancies. The DNN parameters were optimized for FPD image synthesis. The synthetic FPD images' features were evaluated to compare to the corresponding ground-truth FPD images using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). The image quality of the synthetic FPD image was also compared with that of the DRR image to understand the performance of our DNN. For the prostate cases, the MAE of the synthetic FPD image was improved (= 0.12 ± 0.02) from that of the input DRR image (= 0.35 ± 0.08). The synthetic FPD image showed higher PSNRs (= 16.81 ± 1.54 dB) than those of the DRR image (= 8.74 ± 1.56 dB), while SSIMs for both images (= 0.69) were almost the same. All metrics for the synthetic FPD images of the H&N cases were improved (MAE 0.08 ± 0.03, PSNR 19.40 ± 2.83 dB, and SSIM 0.80 ± 0.04) compared to those for the DRR image (MAE 0.48 ± 0.11, PSNR 5.74 ± 1.63 dB, and SSIM 0.52 ± 0.09). Our DNN successfully generated FPD images from DRR images. This technique would be useful to increase throughput when images from two different modalities are compared by visual inspection.

Quantification of six-degree-of-freedom motion during beam delivery in spine stereotactic body radiotherapy using intra-irradiation cone-beam computed tomography imaging technique

PurposeQuantifying intra-fractional six-degree-of-freedom (6DoF) residual errors or motion from approved patient setups is necessary for accurate beam delivery in spine stereotactic body radiotherapy. However, previously reported errors were not acquired during beam delivery. Therefore, we aimed to quantify the 6DoF residual errors and motions during arc beam delivery using a concurrent cone-beam computed tomography (CBCT) imaging technique, intra-irradiation CBCT. MethodsConsecutive 15 patients, 19 plans for various treatment sites, and 199 CBCT images were analyzed. Pre-irradiation CBCT was performed to verify shifts from the initial patient setup using the ExacTrac system. During beam delivery by two or three co-planar full-arc rotations, CBCT imaging was performed concurrently. Subsequently, an intra-irradiation CBCT image was reconstructed. Pre- and intra-irradiation CBCT images were rigidly registered to a planning CT image based on the bone to quantify 6DoF residual errors. Results6DoF residual errors quantified using pre- and intra-irradiation CBCTs were within 2.0 mm/2.0°, except for one measurement. The mean elapsed time (mean ± standard deviation [min:sec]) after pre-irradiation CBCT to the end of the last arc beam delivery was 6:08 ± 1:25 and 7:54 ± 2:14 for the 2- and 3-arc plans, respectively. Root mean squares of residual errors for several directions showed significant differences; however, they were within 1.0 mm/1.0°. Time-dependent analysis revealed that the residual errors tended to increase with elapsed time. ConclusionThe errors represent the optimal intra-fractional error compared with those acquired using the pre-, inter-beam, and post-6DoF image guidance and can be acquired within a standard treatment timeslot.

Comparison of magnetic resonance imaging and CT scan-based delineation of target volumes and organs at risk in the radiation treatment planning of head and neck malignancies

IntroductionAccuracy of target definition is paramount in radiation treatment planning. The optimal choice of imaging modality to define the tumor volume in head and neck tumors is debatable. The study compared MRI and CT scan-based delineation of target volume and Organs At Risk in head and neck cancers. Materials and methods54 head and neck carcinoma patients underwent rigid image registration of planning CT images with MRI images. The gross tumor volume of the primary tumor, node, and organs at risk were delineated on both CT and MRI images. A volumetric evaluation was done for gross tumors, nodes, and organs at risk. Dice Similarity coefficient (DSC), Conformity index(CI), Sensitivity index(SI), and Inclusion index(II) were calculated for gross tumor, node, brainstem, and bilateral parotids. ResultsThe mean volume of the tumor in CT and MRI obtained were 41 .94 cc and 34.76 ccs, mean DSC, CI, SI, and II of the tumor were 0.71, 0.56, 67.37, and 79.80. The mean volume of the node in CT and MRI were 12.16 cc and 10.24 cc, mean DSC, CI, SI, and II of the node were 0.61, 0.45, 62.47, and 64. The mean volume of the brainstem in CT and MRI was 24.13 cc and 21.21 cc. The mean volume of the right parotid in CT and MRI was 24.39 cc, 26.04 ccs. The mean volume of left parotid in CT and MRI, respectively, were 23.95 ccs and 25.04 ccs. ConclusionsThe study shows that MRI may be used in combination with CT for better delineation of target volume and organs at risk for head and neck malignancies.

Four-Dimensional Cone Beam CT Imaging Using a Single Routine Scan via Deep Learning.

A novel method is proposed to obtain four-dimensional (4D) cone-beam computed tomography (CBCT) images from a routine scan in patients with upper abdominal cancer. The projections are sorted according to the location of the lung diaphragm before being reconstructed to phase-sorted data. A multiscale-discriminator generative adversarial network (MSD-GAN) is proposed to alleviate the severe streaking artifacts in the original images. The MSD-GAN is trained using simulated CBCT datasets from patient planning CT images. The enhanced images are further used to estimate the deformable vector field (DVF) among breathing phases using a deformable image registration method. The estimated DVF is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction approach to generate 4D CBCT images. The proposed MSD-GAN is compared with U-Net on the performance of image enhancement. Results show that the proposed method significantly outperforms the total variation regularization-based iterative reconstruction approach and the method using only MSD-GAN to enhance original phase-sorted images in simulation and patient studies on 4D reconstruction quality. The MSD-GAN also shows higher accuracy than the U-Net. The proposed method enables a practical way for 4D-CBCT imaging from a single routine scan in upper abdominal cancer treatment including liver and pancreatic tumors.

High resolution imaging with focused kV x-rays for small animal radio-neuromodulation.

High precision radiotherapy with small irradiator size has potential in many treatment applications involving small shallow targets, with small animal radio-neuromodulation as an intriguing example. A focused kV technique based on novel usage of polycapillary x-ray lenses can focus x-ray beams to <0.2mm in diameter, which is ideal for such uses. Such an application also requires high resolution CT images for treatment planning and setup. In this work, we demonstrate the feasibility of using a virtual focal spot generated with an x-ray lens to perform high-resolution CBCT acquisition. The experiment with x-ray lens was set up on an x-ray tabletop system to generate a virtual focal spot. The flood field images with and without the x-ray lens were first compared. A pinhole image was acquired for the virtual focal spot and compared with the one acquired with the conventional focal spot without the lens. The planar imaging resolution with and without the lens were evaluated using a line pair resolution phantom. The spatial resolution of the two settings were estimated by reconstructing a 0.15-mm wire phantom and comparing its full width half maximum (FWHM). A CBCT scan of a rodent head was also acquired to further demonstrate the improved resolution using the x-ray lens. The proposed imaging setup with x-ray lens had a limited exposure area of 5cm by 5cm on the detector, which was suitable for guiding radio-neuromodulation to a small target in rodent brain. Compared to conventional imaging acquisition with a measured x-ray focal spot of 0.395mm FWHM, the virtual focal spot size was measured at 0.175mm. The reduction in focal spot size with lens leads to an almost doubled planar imaging resolution and a 26% enhancement in 3D spatial resolution. A realistic CBCT acquisition of a rodent head mimicked the imaging acquisition step for radio-neuromodulation and further showed the improved visualization for fine structures. This work demonstrated that the focused kV x-ray technique was capable of generating small focal spot size of <0.2mm, which substantially improved x-ray imaging resolution for small animal imaging.

Real-time deep neural network-based automatic bowel gas segmentation on X-ray images for particle beam treatment.

Since particle beam distribution is vulnerable to change in bowel gas because of its low density, we developed a deep neural network (DNN) for bowel gas segmentation on X-ray images.We used 6688 image datasets from 209 cases as training data, 736 image datasets from 23 cases as validation data and 102 image datasets from 51 cases as test data (total 283 cases). For the training data, we prepared three types of digitally reconstructed radiographic (DRR) images (all-density, bone and gas) by projecting the treatment planning CT image data. However, the real X-ray images acquired in the treatment room showed low contrast that interfered with manual delineation of bowel gas. Therefore, we used synthetic X-ray images converted from DRR images in addition to real X-ray images.We evaluated DNN segmentation accuracy for the synthetic X-ray images using Intersection over Union, recall, precision, and the Dice coefficient, which measured 0.708 ± 0.208, 0.832 ± 0.170, 0.799 ± 0.191, and 0.807 ± 0.178, respectively. The evaluation metrics for the real X-images were less accurate than those for the synthetic X-ray images (0.408 ± 0237, 0.685 ± 0.326, 0.490 ± 0272, and 0.534 ± 0.271, respectively). Computation time was 29.7 ± 1.3 ms/image. Our DNN appears useful in increasing treatment accuracy in particle beam therapy.

Multi-omics to predict acute radiation esophagitis in patients with lung cancer treated with intensity-modulated radiation therapy

PurposeThe study aimed to predict acute radiation esophagitis (ARE) with grade ≥ 2 for patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics.Methods161 patients with stage IIIA−IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT with a prescribed dose from 45 to 70 Gy from 2015 to 2019 were enrolled retrospectively. All the toxicity gradings were given following the Common Terminology Criteria for Adverse Events V4.0. Multi-omics features, including radiomics, dosiomics (including dose−volume histogram dosimetric parameters), were extracted based on the planning CT image and three-dimensional dose distribution. All data were randomly divided into training cohorts (N = 107) and testing cohorts (N = 54). In the training cohorts, features with reliably high outcome relevance and low redundancy were selected under random patient subsampling. Four classification models (using clinical factors (CF) only, using radiomics features (RFs) only, dosiomics features (DFs) only, and the hybrid features (HFs) containing clinical factors, radiomics and dosiomics) were constructed employing the Ridge classifier using two-thirds of randomly selected patients as the training cohort. The remaining patient was treated as the testing cohort. A series of models were built with 30 times training–testing splits. Their performances were assessed using the area under the ROC curve (AUC) and accuracy.ResultsAmong all patients, 51 developed ARE grade ≥ 2, with an incidence of 31.7%. Next, 8990 radiomics and 213 dosiomics features were extracted, and 3, 6, 12, and 13 features remained after feature selection in the CF, DF, RF and DF models, respectively. The RF and HF models achieved similar classification performance, with the training and testing AUCs of 0.796 ± 0.023 (95% confidence interval (CI [0.79, 0.80])/0.744 ± 0.044 (95% CI [0.73, 0.76]) and 0.801 ± 0.022 (95% CI [0.79, 0.81]) (p = 0.74), respectively. The model performances using CF and DF features were poorer, with training and testing AUCs of 0.573 ± 0.026 (95% CI [0.56, 0.58])/ 0.509 ± 0.072 (95% CI [0.48, 0.53]) and 0.679 ± 0.027 (95% CI [0.67, 0.69])/0.604 ± 0.041 (95% CI [0.53, 0.63]) compared with the above two models (p < 0.001), respectively.ConclusionsIn LALC patients treated with CRT IMRT, the ARE grade ≥ 2 can be predicted using the pretreatment radiotherapy image features. To predict ARE, the multi-omics features had similar predictability with radiomics features; however, the dosiomics features and clinical factors had a limited classification performance.

How smart is artificial intelligence in organs delineation? Testing a CE and FDA-approved Deep-Learning tool using multiple expert contours delineated on planning CT images.

A CE- and FDA-approved cloud-based Deep learning (DL)-tool for automatic organs at risk (OARs) and clinical target volumes segmentation on computer tomography images is available. Before its implementation in the clinical practice, an independent external validation was conducted. At least a senior and two in training Radiation Oncologists (ROs) manually contoured the volumes of interest (VOIs) for 6 tumoral sites. The auto-segmented contours were retrieved from the DL-tool and, if needed, manually corrected by ROs. The level of ROs satisfaction and the duration of contouring were registered. Relative volume differences, similarity indices, satisfactory grades, and time saved were analyzed using a semi-automatic tool. Seven thousand seven hundred sixty-five VOIs were delineated on the CT images of 111 representative patients. The median (range) time for manual VOIs delineation, DL-based segmentation, and subsequent manual corrections were 25.0 (8.0-115.0), 2.3 (1.2-8) and 10.0 minutes (0.3-46.3), respectively. The overall time for VOIs retrieving and modification was statistically significantly lower than for manual contouring (p<0.001). The DL-tool was generally appreciated by ROs, with 44% of vote 4 (well done) and 43% of vote 5 (very well done), correlated with the saved time (p<0.001). The relative volume differences and similarity indexes suggested a better inter-agreement of manually adjusted DL-based VOIs than manually segmented ones. The application of the DL-tool resulted satisfactory, especially in complex delineation cases, improving the ROs inter-agreement of delineated VOIs and saving time.

Applying Multi-Metric Deformable Image Registration for Dose Accumulation in Combined Cervical Cancer Radiotherapy

(1) Purpose: Challenges remain in dose accumulation for cervical cancer radiotherapy combined with external beam radiotherapy (EBRT) and brachytherapy (BT) as there are many large and complex organ deformations between different treatments. This study aims to improve deformable image registration (DIR) accuracy with the introduction of multi-metric objectives for dose accumulation of EBRT and BT. (2) Materials and methods: Twenty cervical cancer patients treated with EBRT (45-50 Gy/25 fractions) and high-dose-rate BT (≥20 Gy in 4 fractions) were included for DIR. The multi-metric DIR algorithm included an intensity-based metric, three contour-based metrics, and a penalty term. Nonrigid B-spine transformation was used to transform the planning CT images from EBRT to the first BT, with a six-level resolution registration strategy. To evaluate its performance, the multi-metric DIR was compared with a hybrid DIR provided by commercial software. The DIR accuracy was measured by the Dice similarity coefficient (DSC) and Hausdorff distance (HD) between deformed and reference organ contours. The accumulated maximum dose of 2 cc (D2cc) of the bladder and rectum was calculated and compared to simply addition of D2cc from EBRT and BT (ΔD2cc). (3) Results: The mean DSC of all organ contours for the multi-metric DIR were significantly higher than those for the hybrid DIR (p ≤ 0.011). In total, 70% of patients had DSC > 0.8 using the multi-metric DIR, while 15% of patients had DSC > 0.8 using the commercial hybrid DIR. The mean ΔD2cc of the bladder and rectum for the multi-metric DIR were 3.25 ± 2.29 and 3.54 ± 2.02 GyEQD2, respectively, whereas those for the hybrid DIR were 2.68 ± 2.56 and 2.32 ± 3.25 GyEQD2, respectively. The multi-metric DIR resulted in a much lower proportion of unrealistic D2cc than the hybrid DIR (2.5% vs. 17.5%). (4) Conclusions: Compared with the commercial hybrid DIR, the introduced multi-metric DIR significantly improved the registration accuracy and resulted in a more reasonable accumulated dose distribution.

An Investigation of Dosimetric Consequences of the Anatomic Changes at First Fraction in VMAT of Prostate Cancer Cases using Deformable Planning CT and KVCBCT Image Registration

An Investigation of Dosimetric Consequences of the Anatomic Changes at First Fraction in VMAT of Prostate Cancer Cases using Deformable Planning CT and KVCBCT Image Registration