Fully automated deep learning based auto-contouring of liver segments and spleen on contrast-enhanced CT images.

Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text]. BA was used with vessels ([Formula: see text] and spleen ([Formula: see text] to assess the impact on segment contouring. Models were trained, validated, and tested on 160 ([Formula: see text]), 40 ([Formula: see text]), 33 ([Formula: see text]), 25 (CCH) and 20 (CPVE) CECT of LC patients. [Formula: see text] outperformed [Formula: see text] across all segments with median differences in Dice similarity coefficients (DSC) ranging 0.03-0.05 (p < 0.05). [Formula: see text], and [Formula: see text] were not statistically different (p > 0.05), however, both were slightly better than [Formula: see text] by DSC up to 0.02. The final model, [Formula: see text], showed a mean DSC of 0.89, 0.82, 0.88, 0.87, 0.96, and 0.95 for segments 1, 2, 3, 4, 5-8, and spleen, respectively on entire test sets. Qualitatively, more than 85% of cases showed a Likert score [Formula: see text] 3 on test sets. Our final model provides clinically acceptable contours of liver segments and spleen which are usable in treatment planning.

Leveraging deep learning-based segmentation and contours-driven deformable registration for dose accumulation in abdominal structures.

Purpose: Discrepancies between planned and delivered dose to GI structures during radiation therapy (RT) of liver cancer may hamper the prediction of treatment outcomes. The purpose of this study is to develop a streamlined workflow for dose accumulation in a treatment planning system (TPS) during liver image-guided RT and to assess its accuracy when using different deformable image registration (DIR) algorithms. Materials and Methods: Fifty-six patients with primary and metastatic liver cancer treated with external beam radiotherapy guided by daily CT-on-rails (CTOR) were retrospectively analyzed. The liver, stomach and duodenum contours were auto-segmented on all planning CTs and daily CTORs using deep-learning methods. Dose accumulation was performed for each patient using scripting functionalities of the TPS and considering three available DIR algorithms based on: (i) image intensities only; (ii) intensities + contours; (iii) a biomechanical model (contours only). Planned and accumulated doses were converted to equivalent dose in 2Gy (EQD2) and normal tissue complication probabilities (NTCP) were calculated for the stomach and duodenum. Dosimetric indexes for the normal liver, GTV, stomach and duodenum and the NTCP values were exported from the TPS for analysis of the discrepancies between planned and the different accumulated doses. Results: Deep learning segmentation of the stomach and duodenum enabled considerable acceleration of the dose accumulation process for the 56 patients. Differences between accumulated and planned doses were analyzed considering the 3 DIR methods. For the normal liver, stomach and duodenum, the distribution of the 56 differences in maximum doses (D2%) presented a significantly higher variance when a contour-driven DIR method was used instead of the intensity only-based method. Comparing the two contour-driven DIR methods, differences in accumulated minimum doses (D98%) in the GTV were >2Gy for 15 (27%) of the patients. Considering accumulated dose instead of planned dose in standard NTCP models of the duodenum demonstrated a high sensitivity of the duodenum toxicity risk to these dose discrepancies, whereas smaller variations were observed for the stomach. Conclusion: This study demonstrated a successful implementation of an automatic workflow for dose accumulation during liver cancer RT in a commercial TPS. The use of contour-driven DIR methods led to larger discrepancies between planned and accumulated doses in comparison to using an intensity only based DIR method, suggesting a better capability of these approaches in estimating complex deformations of the GI organs.

Technical Note: Histological validation of anatomical imaging for breast modeling using a novel cryo-microtome.

PURPOSE: Precise correlation between three-dimensional (3D) imaging and histology can aid biomechanical modeling of the breast. We develop a framework to register ex vivo images to histology using a novel cryo-fluorescence tomography (CFT) device. METHODS: A formalin-fixed cadaveric breast specimen, including chest wall, was subjected to high-resolution magnetic resonance (MR) imaging. The specimen was then frozen and embedded in an optimal cutting temperature (OCT) compound. The OCT block was placed in a CFT device with an overhead camera and 50 µm thick slices were successively shaved off the block. After each shaving, the block-face was photographed. At select locations including connective/adipose tissue, muscle, skin, and fibroglandular tissue, 20 µm sections were transferred onto cryogenic tape for manual hematoxylin and eosin staining, histological assessment, and image capture. A 3D white-light image was automatically reconstructed from the photographs by aligning fiducial markers embedded in the OCT block. The 3D MR image, 3D white-light image, and photomicrographs were rigidly registered. Target registration errors (TREs) were computed based on 10 pairs of points marked at fibroglandular intersections. The overall MR-histology registration was used to compare the MR intensities at tissue extraction sites with a one-way analysis of variance. RESULTS: The MR image to CFT-captured white-light image registration achieved a mean TRE of 0.73 ± 0.25 mm (less than the 1 mm MR slice resolution). The block-face white-light image and block-face photomicrograph registration showed visually indistinguishable alignment of anatomical structures and tissue boundaries. The MR intensities at the four tissue sites identified from histology differed significantly (p < 0.01). Each tissue pair, except the skin-connective/adipose tissue pair, also had significantly different MR intensities (p < 0.01). CONCLUSIONS: Fine sectioning in a highly controlled imaging/sectioning environment enables accurate registration between the MR image and histology. Statistically significant differences in MR signal intensities between histological tissues are indicators for the specificity of correlation between MRI and histology.

Detection of vessel bifurcations in CT scans for automatic objective assessment of deformable image registration accuracy.

PURPOSE: Objective assessment of deformable image registration (DIR) accuracy often relies on the identification of anatomical landmarks in image pairs, a manual process known to be extremely time-expensive. The goal of this study is to propose a method to automatically detect vessel bifurcations in images and assess their use for the computation of target registration errors (TREs). MATERIALS AND METHODS: Three image datasets were retrospectively analyzed. The first dataset included 10 pairs of inhale/exhale phases from lung 4DCTs and full inhale and exhale breath-hold CT scans from 10 patients presenting with chronic obstructive pulmonary disease, with 300 corresponding landmarks available for each case (DIR-Lab). The second dataset included six pairs of inhale/exhale phases from lung 4DCTs (POPI dataset), with 100 pairs of landmarks for each case. The third dataset included 28 pairs of pre/post-radiotherapy liver contrast-enhanced CT scans, each with five manually picked vessel bifurcation correspondences. For all images, the vasculature was autosegmented by computing and thresholding a vesselness image. Images of the vasculature centerline were computed, and bifurcations were detected based on centerline voxel neighbors' count. The vasculature segmentations were independently registered using a Demons algorithm between representations of their surface with distance maps. Detected bifurcations were considered as corresponding when distant by less than 5 mm after vasculature DIR. The selected pairs of bifurcations were used to calculate TRE after registration of the images considering three algorithms: rigid registration, Anaconda, and a Demons algorithm. For comparison with the ground truth, TRE values calculated using the automatically detected correspondences were interpolated in the whole organs to generate TRE maps. The performance of the method in automatically calculating TRE after image registration was quantified by measuring the correlation with the TRE obtained when using the ground truth landmarks. RESULTS: The median Pearson correlation coefficients between ground truth TRE and corresponding values in the generated TRE maps were r = 0.81 and r = 0.67 for the lung and liver cases, respectively. The correlation coefficients between mean TRE for each case were r = 0.99 and r = 0.64 for the lung and liver cases, respectively. CONCLUSION: For lungs or liver CT scans DIR, a strong correlation was obtained between TRE calculated using manually picked or landmarks automatically detected with the proposed method. This tool should be particularly useful in studies requiring assessing the reliability of a high number of DIRs.

Geometric and dosimetric accuracy of deformable image registration between average-intensity images for 4DCT-based adaptive radiotherapy for non-small cell lung cancer.

PURPOSE: Re-planning for four-dimensional computed tomography (4DCT)-based lung adaptive radiotherapy commonly requires deformable dose mapping between the planning average-intensity image (AVG) and the newly acquired AVG. However, such AVG-AVG deformable image registration (DIR) lacks accuracy assessment. The current work quantified and compared geometric accuracies of AVG-AVG DIR and corresponding phase-phase DIRs, and subsequently investigated the clinical impact of such AVG-AVG DIR on deformable dose mapping. METHODS AND MATERIALS: Hybrid intensity-based AVG-AVG and phase-phase DIRs were performed between the planning and mid-treatment 4DCTs of 28 non-small cell lung cancer patients. An automated landmark identification algorithm detected vessel bifurcation pairs in both lungs. Target registration error (TRE) of these landmark pairs was calculated for both DIR types. The correlation between TRE and respiratory-induced landmark motion in the planning 4DCT was analyzed. Global and local dose metrics were used to assess the clinical implications of AVG-AVG deformable dose mapping with both DIR types. RESULTS: TRE of AVG-AVG and phase-phase DIRs averaged 3.2 ± 1.0 and 2.6 ± 0.8 mm respectively (p < 0.001). Using AVG-AVG DIR, TREs for landmarks with <10 mm motion averaged 2.9 ± 2.0 mm, compared to 3.1 ± 1.9 mm for the remaining landmarks (p < 0.01). Comparatively, no significant difference was demonstrated for phase-phase DIRs. Dosimetrically, no significant difference in global dose metrics was observed between doses mapped with AVG-AVG DIR and the phase-phase DIR, but a positive linear relationship existed (p = 0.04) between the TRE of AVG-AVG DIR and local dose difference. CONCLUSIONS: When the region of interest experiences <10 mm respiratory-induced motion, AVG-AVG DIR may provide sufficient geometric accuracy; conversely, extra attention is warranted, and phase-phase DIR is recommended. Dosimetrically, the differences in geometric accuracy between AVG-AVG and phase-phase DIRs did not impact global lung-based metrics. However, as more localized dose metrics are needed for toxicity assessment, phase-phase DIR may be required as its lower mean TRE improved voxel-based dosimetry.

Biomechanical modeling of radiation dose-induced volumetric changes of the parotid glands for deformable image registration.

PURPOSE: Early animal studies suggest that parotid gland (PG) toxicity prediction could be improved by an accurate estimation of the radiation dose to sub-regions of the PG. Translation to clinical investigation requires voxel-level dose accumulation in this organ that responds volumetrically throughout treatment. To date, deformable image registration (DIR) has been evaluated for the PG using only surface alignment. We sought to develop and evaluate an advanced DIR technique capable of modeling these complex PG volume changes over the course of radiation therapy. MATERIALS AND METHODS: Planning and mid-treatment magnetic resonance images from 19 patients and computed tomography images from nine patients who underwent radiation therapy for head and neck cancer were retrospectively evaluated. A finite element model (FEM)-based DIR algorithm was applied between the corresponding pairs of images, based on boundary conditions on the PG surfaces only (Morfeus-spatial). To investigate an anticipated improvement in accuracy, we added a population model-based thermal expansion coefficient to simulate the dose distribution effect on the volume change inside the glands (Morfeus-spatialDose). The model accuracy was quantified using target registration error for magnetic resonance images, where corresponding anatomical landmarks could be identified. The potential clinical impact was evaluated using differences in mean dose, median dose, D98, and D50 of the PGs. RESULTS: In the magnetic resonance images, the mean (±standard deviation) target registration error significantly reduced by 0.25 ± 0.38 mm (p = 0.01) when using Morfeus-spatialDose instead of Morfeus-spatial. In the computed tomography images, differences in the mean dose, median dose, D98, and D50 of the PGs reached 2.9 ± 0.8, 3.8, 4.1, and 3.8 Gy, respectively, between Morfeus-spatial and Morfeus-spatialDose. CONCLUSION: Differences between Morfeus-spatial and Morfeus-spatialDose may be impactful when considering high-dose gradients of radiation in the PGs. The proposed DIR model can allow more accurate PG alignment than the standard model and improve dose estimation and toxicity prediction modeling.

Accuracy of deformable image registration techniques for alignment of longitudinal cholangiocarcinoma CT images.

PURPOSE: Response assessment of radiotherapy for the treatment of intrahepatic cholangiocarcinoma (IHCC) across longitudinal images is challenging due to anatomical changes. Advanced deformable image registration (DIR) techniques are required to correlate corresponding tissues across time. In this study, the accuracy of five commercially available DIR algorithms in four treatment planning systems (TPS) was investigated for the registration of planning images with posttreatment follow-up images for response assessment or re-treatment purposes. METHODS: Twenty-nine IHCC patients treated with hypofractionated radiotherapy and with pretreatment and posttreatment contrast-enhanced computed tomography (CT) images were analyzed. Liver segmentations were semiautomatically generated on all CTs and the posttreatment CT was then registered to the pretreatment CT using five commercially available algorithms (Demons, B-splines, salient feature-based, anatomically constrained and finite element-based) in four TPSs. This was followed by an in-depth analysis of 10 DIR strategies (plus global and liver-focused rigid registration) in one of the TPSs. Eight of the strategies were variants of the anatomically constrained DIR while the two were based on a finite element-based biomechanical registration. The anatomically constrained techniques were combinations of: (a) initializations with the two rigid registrations; (b) two similarity metrics - correlation coefficient (CC) and mutual information (MI); and (c) with and without a controlling region of interest (ROI) - the liver. The finite element-based techniques were initialized by the two rigid registrations. The accuracy of each registration was evaluated using target registration error (TRE) based on identified vessel bifurcations. The results were statistically analyzed with a one-way analysis of variance (ANOVA) and pairwise comparison tests. Stratified analysis was conducted on the inter-TPS data (plus the liver-focused rigid registration) using treatment volume changes, slice thickness, time between scans, and abnormal lab values as stratifying factors. RESULTS: The complex deformation observed following treatment resulted in average TRE exceeding the image voxel size for all techniques. For the inter-TPS comparison, the Demons algorithm had the lowest TRE, which was significantly superior to all the other algorithms. The respective mean (standard deviation) TRE (in mm) for the Demons, B-splines, salient feature-based, anatomically constrained, and finite element-based algorithms were 4.6 (2.0), 7.4 (2.7), 7.2 (2.6), 6.3 (2.3), and 7.5 (4.0). In the follow-up comparison of the anatomically constrained DIR, the strategy with liver-focused rigid registration initialization, CC as similarity metric and liver as a controlling ROI had the lowest mean TRE - 6.0 (2.0). The maximum TRE for all techniques exceeded 10 mm. Selection of DIR strategy was found to be a statistically significant factor for registration accuracy. Tumor volume change had a significant effect on TRE for finite element-based registration and B-splines DIR. Time between scans had a substantial effect on TRE for all registrations but was only significant for liver-focused rigid, finite element-based and salient feature-based DIRs. CONCLUSIONS: This study demonstrates the limitations of commercially available DIR techniques in TPSs for alignment of longitudinal images of liver cancer presenting complex anatomical changes including local hypertrophy and fibrosis/necrosis. DIR in this setting should be used with caution and careful evaluation.

Biomechanical modeling of neck flexion for deformable alignment of the salivary glands in head and neck cancer images.

During head and neck (HN) cancer radiation therapy, analysis of the dose-response relationship for the parotid glands (PG) relies on the ability to accurately align soft tissue organs between longitudinal images. In order to isolate the response of the salivary glands to delivered dose, from deformation due to patient position, it is important to resolve the patient postural changes, mainly due to neck flexion. In this study we evaluate the use of a biomechanical model-based deformable image registration (DIR) algorithm to estimate the displacements and deformations of the salivary glands due to postural changes. A total of 82 pairs of CT images of HN cancer patients with varying angles of neck flexion were retrospectively obtained. The pairs of CTs of each patient were aligned using bone-based rigid registration. The images were then deformed using biomechanical model-based DIR method that focused on the mandible, C1 vertebrae, C3 vertebrae, and external contour. For comparison, an intensity-based DIR was also performed. The accuracy of the biomechanical model-based DIR was assessed using Dice similarity coefficient (DSC) for all images and for the subset of images where the PGs had a volume change within 20%. The accuracy was compared to the intensity-based DIR. The PG mean ± STD DSC were 0.63 ± 0.18, 0.80 ± 0.08, and 0.82 ± 0.15 for the rigid registration, biomechanical model-based DIR, and intensity based DIR, respectively, for patients with a PG volume change up to 20%. For the entire cohort of patients, where the PG volume change was up to 57%, the PG mean ± STD DSC were 0.60 ± 0.18, 0.78 ± 0.09, and 0.81 ± 0.14 for the rigid registration, biomechanical model-based DIR, and intensity based DIR, respectively. The difference in DSC of the intensity and biomechanical model-based DIR methods was not statistically significant when the volume change was less than 20% (two-sided paired t-test, p  = 0.12). When all volume changes were considered, there was a significant difference between the two registration approaches, although the magnitude was small. These results demonstrate that the proposed biomechanical model with boundary conditions on the bony anatomy can serve to describe the varying angles of neck flexion appearing in images during radiation treatment and to align the salivary glands for proper analysis of dose-response relationships. It also motivates the need for dose response modeling following neck flexion for cases where parotid gland response is noted.

Predictive Models to Determine Clinically Relevant Deviations in Delivered Dose for Head and Neck Cancer.

PURPOSE: This study aimed to improve the understanding of deviations between planned and accumulated doses and to establish metrics to predict clinically significant dosimetric deviations midway through treatment to evaluate the potential need to re-plan during fractionated radiation therapy (RT). METHODS AND MATERIALS: A total of 100 patients with head and neck cancer were retrospectively evaluated. Contours were mapped from the planning computed tomography (CT) scan to each fraction cone beam CT via deformable image registration. The dose was calculated on each cone beam CT and evaluated based on the mapped contours. The mean dose at each fraction was averaged to approximate the accumulated dose for structures with mean dose constraints, and the daily maximum dose was summed to approximate the accumulated dose for structures with maximum dose constraints. A threshold deviation value was calculated to predict for patients needing midtreatment re-planning. This predictive model was applied to 52 patients treated at a separate institution. RESULTS: Dose was accumulated on 10 organs over 100 patients. To generate a threshold deviation that predicted the need to re-plan with 100% sensitivity, the submandibular glands required re-planning if the delivered dose was at least 3.5 Gy higher than planned by fraction 15. This model predicts the need to re-plan the submandibular glands with 98.7% specificity. In the independent evaluation cohort, this model predicts the need to re-plan the submandibular glands with 100% sensitivity and 98.0% specificity. The oral cavity, intermediate clinical target volume, left parotid, and inferior constrictor patient groups each had 1 patient who exceeded the threshold deviation by the end of RT. By fraction 15 of 30 to 35 total fractions, the left parotid gland, inferior constrictor, and intermediate clinical target volume had a dose deviation of 3.1 Gy, 5.9 Gy, and 4.8 Gy, respectively. When a deformable image registration failure was observed, the dose deviation exceeded the threshold for at least 1 organ, demonstrating that an automated deformable image registration-based dose assessment process could be developed with user evaluation for cases that result in dose deviations. CONCLUSIONS: A midtreatment threshold deviation was determined to predict the need to replan for the submandibular glands by fraction 15 of 30 to 35 total fractions of RT.

Magnetic Resonance-based Response Assessment and Dose Adaptation in Human Papilloma Virus Positive Tumors of the Oropharynx treated with Radiotherapy (MR-ADAPTOR): An R-IDEAL stage 2a-2b/Bayesian phase II trial.

BACKGROUND: Current standard radiotherapy for oropharynx cancer (OPC) is associated with high rates of severe toxicities, shown to adversely impact patients' quality of life. Given excellent outcomes of human papilloma virus (HPV)-associated OPC and long-term survival of these typically young patients, treatment de-intensification aimed at improving survivorship while maintaining excellent disease control is now a central concern. The recent implementation of magnetic resonance image - guided radiotherapy (MRgRT) systems allows for individual tumor response assessment during treatment and offers possibility of personalized dose-reduction. In this 2-stage Bayesian phase II study, we propose to examine weekly radiotherapy dose-adaptation based on magnetic resonance imaging (MRI) evaluated tumor response. Individual patient's plan will be designed to optimize dose reduction to organs at risk and minimize locoregional failure probability based on serial MRI during RT. Our primary aim is to assess the non-inferiority of MRgRT dose adaptation for patients with low risk HPV-associated OPC compared to historical control, as measured by Bayesian posterior probability of locoregional control (LRC). METHODS: Patients with T1-2 N0-2b (as per AJCC 7th Edition) HPV-positive OPC, with lymph node <3 cm and <10 pack-year smoking history planned for curative radiotherapy alone to a dose of 70 Gy in 33 fractions will be eligible. All patients will undergo pre-treatment MRI and at least weekly intra-treatment MRI. Patients undergoing MRgRT will have weekly adaptation of high dose planning target volume based on gross tumor volume response. The stage 1 of this study will enroll 15 patients to MRgRT dose adaptation. If LRC at 6 months with MRgRT dose adaptation is found sufficiently safe as per the Bayesian model, stage 2 of the protocol will expand enrollment to an additional 60 patients, randomized to either MRgRT or standard IMRT. DISCUSSION: Multiple methods for safe treatment de-escalation in patients with HPV-positive OPC are currently being studied. By leveraging the ability of advanced MRI techniques to visualize tumor and soft tissues through the course of treatment, this protocol proposes a workflow for safe personalized radiation dose-reduction in good responders with radiosensitive tumors, while ensuring tumoricidal dose to more radioresistant tumors. MRgRT dose adaptation could translate in reduced long term radiation toxicities and improved survivorship while maintaining excellent LRC outcomes in favorable OPC. TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT03224000; Registration date: 07/21/2017.

A simulation study to assess the potential impact of developing normal tissue complication probability models with accumulated dose.

PURPOSE: This study aimed to analyze the potential clinical impact of the differences between planned and accumulated doses on the development and use of normal tissue complication probability (NTCP) models. METHODS AND MATERIALS: Thirty patients who were previously treated with stereotactic body radiation therapy for liver cancer and for whom the accumulated dose was computed were assessed retrospectively. The linear quadratic equivalent dose at 2 Gy per fraction and generalized equivalent uniform dose were calculated for planned and accumulated doses. Stomach and duodenal Lyman-Kutcher-Burman NTCP models (α/ß = 2.5; n = .09) were developed on the basis of planned and accumulated generalized equivalent uniform doses and the differences between the models assessed. In addition, the error in determining the probability of toxicity on the basis of the planned dose was evaluated by comparing planned doses in the NTCP model that were created from accumulated doses. RESULTS: The standard, planned-dose NTCP model overestimates toxicity risk for both the duodenal and stomach models at doses that are below approximately 20 Gy (6 fractions) and underestimates toxicity risk for doses above approximately 20 Gy (6 fractions). Building NTCP models with accumulated rather than planned doses changes the predicted risk by up to 16% (mean: 6%; standard deviation: 7%) for duodenal toxicity and 6% (mean: 2%; standard deviation: 2%) for stomach toxicity. For a protocol that plans a 10% iso-toxicity risk to the duodenum, a 15.7 Gy (6 fractions) maximum dose constraint would be necessary when using standard NTCP models on the basis of a planned dose and a 17.6 Gy (6 fractions) maximum dose would be allowed when using NTCP models on the basis of accumulated doses. CONCLUSIONS: Assuming that accumulated dose is a more accurate representation of the true delivered dose than the planned dose, this simulation study indicates the need for prospective clinical trials to evaluate the impact of building NTCP models on the basis of accumulated doses.

Medical Professional Radiation Dosimeter Usage: Reasons for Noncompliance.

The purpose of this study was to assess the attitudes of occupationally exposed employees at a large teaching hospital about wearing their assigned personal radiation dosimeters. A 16-question multiple-answer survey was used to report the reasons why medical professionals may not wear their dosimetry during procedures involving ionizing radiation. In all, 302 employees responded to the survey. The majority of respondents who reported always or almost always wearing their dosimeters do so because they consider themselves well informed concerning the importance of personal dosimetry measurement and appreciate the importance of federal and state regulations. For respondents who reported not always wearing their dosimeters, the most commonly stated reason was the inconvenience of remembering to bring and wear their dosimeters when working in multiple locations, for which a potential solution would be to provide dosimeters to each affected wearer in each location where they work.