Target Definition in Prostate, Head, and Neck

Robustness evaluation of pencil beam scanning proton therapy treatment planning: A systematic review

Compared to conventional radiotherapy using X-rays, proton therapy, in principle, allows better conformity of the dose distribution to target volumes, at the cost of greater sensitivity to physical, anatomical, and positioning uncertainties. Robust planning, both in terms of plan optimization and evaluation, has gained high visibility in publications on the subject and is part of clinical practice in many centers. However, there is currently no consensus on the methods and parameters to be used for robust optimization or robustness evaluation. We propose to overcome this deficiency by following the modified Delphi consensus method. This method first requires a systematic review of the literature. We performed this review using the PubMed and Web Of Science databases, via two different experts. Potential conflicts were resolved by a third expert. We then explored the different methods before focusing on clinical studies that evaluate robustness on a significant number of patients. Many robustness assessment methods are proposed in the literature. Some are more successful than others and their implementation varies between centers. Moreover, they are not all statistically or mathematically equivalent. The most sophisticated and rigorous methods have seen more limited application due to the difficulty of their implementation and their lack of widespread availability.

Probability maps for deep learning-based head and neck tumor segmentation: Graphical User Interface design and test

BACKGROUND

The different tumor appearance of head and neck cancer across imaging modalities, scanners, and acquisition parameters accounts for the highly subjective nature of the manual tumor segmentation task. The variability of the manual contours is one of the causes of the lack of generalizability and the suboptimal performance of deep learning (DL) based tumor auto-segmentation models. Therefore, a DL-based method was developed that outputs predicted tumor probabilities for each PET-CT voxel in the form of a probability map instead of one fixed contour. The aim of this study was to show that DL-generated probability maps for tumor segmentation are clinically relevant, intuitive, and a more suitable solution to assist radiation oncologists in gross tumor volume segmentation on PET-CT images of head and neck cancer patients.

METHOD

A graphical user interface (GUI) was designed, and a prototype was developed to allow the user to interact with tumor probability maps. Furthermore, a user study was conducted where nine experts in tumor delineation interacted with the interface prototype and its functionality. The participants' experience was assessed qualitatively and quantitatively.

RESULTS

The interviews with radiation oncologists revealed their preference for using a rainbow colormap to visualize tumor probability maps during contouring, which they found intuitive. They also appreciated the slider feature, which facilitated interaction by allowing the selection of threshold values to create single contours for editing and use as a starting point. Feedback on the prototype highlighted its excellent usability and positive integration into clinical workflows.

CONCLUSIONS

This study shows that DL-generated tumor probability maps are explainable, transparent, intuitive and a better alternative to the single output of tumor segmentation models.

Towards more precise automatic analysis: a systematic review of deep learning-based multi-organ segmentation

Accurate segmentation of multiple organs in the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy. In the past few years, with a data-driven feature extraction approach and end-to-end training, automatic deep learning-based multi-organ segmentation methods have far outperformed traditional methods and become a new research topic. This review systematically summarizes the latest research in this field. We searched Google Scholar for papers published from January 1, 2016 to December 31, 2023, using keywords "multi-organ segmentation" and "deep learning", resulting in 327 papers. We followed the PRISMA guidelines for paper selection, and 195 studies were deemed to be within the scope of this review. We summarized the two main aspects involved in multi-organ segmentation: datasets and methods. Regarding datasets, we provided an overview of existing public datasets and conducted an in-depth analysis. Concerning methods, we categorized existing approaches into three major classes: fully supervised, weakly supervised and semi-supervised, based on whether they require complete label information. We summarized the achievements of these methods in terms of segmentation accuracy. In the discussion and conclusion section, we outlined and summarized the current trends in multi-organ segmentation.

Application of simultaneous uncertainty quantification and segmentation for oropharyngeal cancer use-case with Bayesian deep learning

BACKGROUND

Radiotherapy is a core treatment modality for oropharyngeal cancer (OPC), where the primary gross tumor volume (GTVp) is manually segmented with high interobserver variability. This calls for reliable and trustworthy automated tools in clinician workflow. Therefore, accurate uncertainty quantification and its downstream utilization is critical.

METHODS

Here we propose uncertainty-aware deep learning for OPC GTVp segmentation, and illustrate the utility of uncertainty in multiple applications. We examine two Bayesian deep learning (BDL) models and eight uncertainty measures, and utilize a large multi-institute dataset of 292 PET/CT scans to systematically analyze our approach.

RESULTS

We show that our uncertainty-based approach accurately predicts the quality of the deep learning segmentation in 86.6% of cases, identifies low performance cases for semi-automated correction, and visualizes regions of the scans where the segmentations likely fail.

CONCLUSIONS

Our BDL-based analysis provides a first-step towards more widespread implementation of uncertainty quantification in OPC GTVp segmentation.

Evaluation of safety margins for cone beam CT-based adaptive prostate radiotherapy

Adaptive radiotherapy is characterized by the use of a daily imaging system, such as CBCT (Cone-Beam Computed Tomography) images to re-optimize the treatment based on the daily anatomy and position of the patient. By systematically re-delineating the Clinical Target Volume (CTV) at each fraction, target delineation uncertainty features a random component instead of a pure systematic. The goal of this work is to identify the random and systematic contributions of the delineation error and compute a new relevant Planning Target Volume (PTV) safety margin. 169 radiotherapy sessions from 10 prostate cancer patients treated on the Varian ETHOS treatment system have been analyzed. Intra-patient and inter-patient delineation variabilities were computed in six directions, by considering the prostate as a rigid, non-rotating volume. By doing so, we were able to directly compare the delineations done by the physicians on daily CBCT images with the initial delineation done on the CT-sim and MRI, and sort them by direction using the polar coordinates of the points. The computed variabilities were then used to compute a PTV margin based on Van Herk margin recipe. The total margin computed with random and systematic delineation uncertainties was of 2.7, 2.4, 5.6, 4.8, 4.9 and 3.6 mm in the left, right, anterior, posterior, cranial and caudal directions, respectively. According to our results, the gain offered by the separation of the delineation uncertainty into systematic and random contributions due to the adaptive delineation process justifies a reduction of the PTV margin down to 3 to 5 mm in every direction.

CT synthesis from MR images using frequency attention conditional generative adversarial network

Magnetic resonance (MR) image-guided radiotherapy is widely used in the treatment planning of malignant tumors, and MR-only radiotherapy, a representative of this technique, requires synthetic computed tomography (sCT) images for effective radiotherapy planning. Convolutional neural networks (CNN) have shown remarkable performance in generating sCT images. However, CNN-based models tend to synthesize more low-frequency components and the pixel-wise loss function usually used to optimize the model can result in blurred images. To address these problems, a frequency attention conditional generative adversarial network (FACGAN) is proposed in this paper. Specifically, a frequency cycle generative model (FCGM) is designed to enhance the inter-mapping between MR and CT and extract more rich tissue structure information. Additionally, a residual frequency channel attention (RFCA) module is proposed and incorporated into the generator to enhance its ability in perceiving the high-frequency image features. Finally, high-frequency loss (HFL) and cycle consistency high-frequency loss (CHFL) are added to the objective function to optimize the model training. The effectiveness of the proposed model is validated on pelvic and brain datasets and compared with state-of-the-art deep learning models. The results show that FACGAN produces higher-quality sCT images while retaining clearer and richer high-frequency texture information.

Artificial Intelligence-Based Organ Delineation for Radiation Treatment Planning of Prostate Cancer on Computed Tomography

Purpose

Meticulous manual delineations of the prostate and the surrounding organs at risk are necessary for prostate cancer radiation therapy to avoid side effects to the latter. This process is time consuming and hampered by inter- and intraobserver variability, all of which could be alleviated by artificial intelligence (AI). This study aimed to evaluate the performance of AI compared with manual organ delineations on computed tomography (CT) scans for radiation treatment planning.

Methods and Materials

Manual delineations of the prostate, urinary bladder, and rectum of 1530 patients with prostate cancer who received curative radiation therapy from 2006 to 2018 were included. Approximately 50% of those CT scans were used as a training set, 25% as a validation set, and 25% as a test set. Patients with hip prostheses were excluded because of metal artifacts. After training and fine-tuning with the validation set, automated delineations of the prostate and organs at risk were obtained for the test set. Sørensen-Dice similarity coefficient, mean surface distance, and Hausdorff distance were used to evaluate the agreement between the manual and automated delineations.

Results

The median Sørensen-Dice similarity coefficient between the manual and AI delineations was 0.82, 0.95, and 0.88 for the prostate, urinary bladder, and rectum, respectively. The median mean surface distance and Hausdorff distance were 1.7 and 9.2 mm for the prostate, 0.7 and 6.7 mm for the urinary bladder, and 1.1 and 13.5 mm for the rectum, respectively.

Conclusions

Automated CT-based organ delineation for prostate cancer radiation treatment planning is feasible and shows good agreement with manually performed contouring.

A Comprehensive Primer on Radiation Oncology for Non-Radiation Oncologists

Background: Multidisciplinary management is crucial in cancer diagnosis and treatment. Multidisciplinary teams include specialists in surgery, medical therapies, and radiation therapy (RT), each playing unique roles in oncology care. One significant aspect is RT, guided by radiation oncologists (ROs). This paper serves as a detailed primer for non-oncologists, medical students, or non-clinical investigators, educating them on contemporary RT practices. Methods: This report follows the process of RT planning and execution. Starting from the decision-making in multidisciplinary teams to the completion of RT and subsequent patient follow-up, it aims to offer non-oncologists an understanding of the RO's work in a comprehensive manner. Results: The first step in RT is a planning session that includes obtaining a CT scan of the area to be treated, known as the CT simulation. The patients are imaged in the exact position in which they will receive treatment. The second step, which is the primary source of uncertainty, involves the delineation of treatment targets and organs at risk (OAR). The objective is to ensure precise irradiation of the target volume while sparing the OARs as much as possible. Various radiation modalities, such as external beam therapy with electrons, photons, or particles (including protons and carbon ions), as well as brachytherapy, are utilized. Within these modalities, several techniques, such as three-dimensional conformal RT, intensity-modulated RT, volumetric modulated arc therapy, scattering beam proton therapy, and intensity-modulated proton therapy, are employed to achieve optimal treatment outcomes. The RT plan development is an iterative process involving medical physicists, dosimetrists, and ROs. The complexity and time required vary, ranging from an hour to a week. Once approved, RT begins, with image-guided RT being standard practice for patient alignment. The RO manages acute toxicities during treatment and prepares a summary upon completion. There is a considerable variance in practices, with some ROs offering lifelong follow-up and managing potential late effects of treatment. Conclusions: Comprehension of RT clinical effects by non-oncologists providers significantly elevates long-term patient care quality. Hence, educating non-oncologists enhances care for RT patients, underlining this report's importance.

A high-resolution cone beam computed tomography (HRCBCT) reconstruction framework for CBCT-guided online adaptive therapy

BACKGROUND

Kilo-voltage cone-beam computed tomography (CBCT) is a prevalent modality used for adaptive radiotherapy (ART) due to its compatibility with linear accelerators and ability to provide online imaging. However, the widely-used Feldkamp-Davis-Kress (FDK) reconstruction algorithm has several limitations, including potential streak aliasing artifacts and elevated noise levels. Iterative reconstruction (IR) techniques, such as total variation (TV) minimization, dictionary-based methods, and prior information-based methods, have emerged as viable solutions to address these limitations and improve the quality and applicability of CBCT in ART.

PURPOSE

One of the primary challenges in IR-based techniques is finding the right balance between minimizing image noise and preserving image resolution. To overcome this challenge, we have developed a new reconstruction technique called high-resolution CBCT (HRCBCT) that specifically focuses on improving image resolution while reducing noise levels.

METHODS

The HRCBCT reconstruction technique builds upon the conventional IR approach, incorporating three components: the data fidelity term, the resolution preservation term, and the regularization term. The data fidelity term ensures alignment between reconstructed values and measured projection data, while the resolution preservation term exploits the high resolution of the initial Feldkamp-Davis-Kress (FDK) algorithm. The regularization term mitigates noise during the IR process. To enhance convergence and resolution at each iterative stage, we applied Iterative Filtered Backprojection (IFBP) to the data fidelity minimization process.

RESULTS

We evaluated the performance of the proposed HRCBCT algorithm using data from two physical phantoms and one head and neck patient. The HRCBCT algorithm outperformed all four different algorithms; FDK, Iterative Filtered Back Projection (IFBP), Compressed Sensing based Iterative Reconstruction (CSIR), and Prior Image Constrained Compressed Sensing (PICCS) methods in terms of resolution and noise reduction for all data sets. Line profiles across three line pairs of resolution revealed that the HRCBCT algorithm delivered the highest distinguishable line pairs compared to the other algorithms. Similarly, the Modulation Transfer Function (MTF) measurements, obtained from the tungsten wire insert on the CatPhan 600 physical phantom, showed a significant improvement with HRCBCT over traditional algorithms.

CONCLUSION

The proposed HRCBCT algorithm offers a promising solution for enhancing CBCT image quality in adaptive radiotherapy settings. By addressing the challenges inherent in traditional IR methods, the algorithm delivers high-definition CBCT images with improved resolution and reduced noise throughout each iterative step. Implementing the HR CBCT algorithm could significantly impact the accuracy of treatment planning during online adaptive therapy.

Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis

BACKGROUND

Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate accurate sCT from fixed MRI acquisitions. However, MRI protocols may change over time or differ between centres resulting in low-quality sCT due to poor model generalisation.

PURPOSE

investigating domain randomisation (DR) to increase the generalisation of a DL model for brain sCT generation.

METHODS

CT and corresponding T1-weighted MRI with/without contrast, T2-weighted, and FLAIR MRI from 95 patients undergoing RT were collected, considering FLAIR the unseen sequence where to investigate generalisation. A "Baseline" generative adversarial network was trained with/without the FLAIR sequence to test how a model performs without DR. Image similarity and accuracy of sCT-based dose plans were assessed against CT to select the best-performing DR approach against the Baseline.

RESULTS

The Baseline model had the poorest performance on FLAIR, with mean absolute error (MAE) = 106 ± 20.7 HU (mean ±σ). Performance on FLAIR significantly improved for the DR model with MAE = 99.0 ± 14.9 HU, but still inferior to the performance of the Baseline+FLAIR model (MAE = 72.6 ± 10.1 HU). Similarly, an improvement in γ-pass rate was obtained for DR vs Baseline.

CONCLUSION

DR improved image similarity and dose accuracy on the unseen sequence compared to training only on acquired MRI. DR makes the model more robust, reducing the need for re-training when applying a model on sequences unseen and unavailable for retraining.

Quality assurance and temporal stability of a 1.5 T MRI scanner for MR-guided Photon and Particle Therapy

PURPOSE

To describe performance measurements, adaptations and time stability over 20 months of a diagnostic MR scanner for integration into MR-guided photon and particle radiotherapy.

MATERIAL AND METHODS

For realization of MR-guided photon and particle therapy (MRgRT/MRgPT), a 1.5 T MR scanner was installed at the Heidelberg Ion Beam Therapy Center. To integrate MRI into the treatment process, a flat tabletop and dedicated coil holders for flex coils were used, which prevent deformation of the patient external contour and allow for the use of immobilization tools for reproducible positioning. The signal-to-noise ratio (SNR) was compared for the diagnostic and therapy-specific setup using the flat couch top and flexible coils for the a) head & neck and b) abdominal region as well as for different bandwidths and clinical pulse sequences. Additionally, a quality assurance (QA) protocol with monthly measurements of the ACR phantom and measurement of geometric distortions for a large field-of-view (FOV) was implemented to assess the imaging quality parameters of the device over the course of 20 months.

RESULTS

The SNR measurements showed a decreased SNR for the RT-specific as compared to the diagnostic setup of (a) 26% to 34% and (b) 11% to 33%. No significant bandwidth dependency for this ratio was found. The longitudinal assessment of the image quality parameters with the ACR and distortion phantom confirmed the long-term stability of the MRI device.

CONCLUSION

A diagnostic MRI was commissioned for use in MR-guided particle therapy. Using a radiotherapy specific setup, a high geometric accuracy and signal homogeneity was obtained after some adaptions and the measured parameters were shown to be stable over a period of 20 months.

Current practices and perspectives on the integration of contrast agents in MRI-guided radiation therapy clinical practice: a worldwide survey

Aims

The introduction of on-line magnetic resonance image-guided radiotherapy (MRIgRT) has led to an improvement in the therapeutic workflow of radiotherapy treatments thanks to the better visualization of therapy volumes assured by the higher soft tissue contrast. Magnetic Resonance contrast agents (MRCA) could improve the target delineation in on-line MRIgRT planning as well as reduce inter-observer variability and enable innovative treatment optimization protocols. The aim of this survey is to investigate the utilization of MRCA among centres that clinically implemented on-line MRIgRT technology.

Methods

In September 2021, we conducted an online survey consisting of a sixteen-question questionnaire that was distributed to the all the hospitals around the world equipped with MR Linacs. The questionnaire was developed by two Italian 0.35 T and 1.5 T MR-Linac centres and was validated by four other collaborating centres, using a Delphi consensus methodology.

Results

The survey was distributed to 52 centres and 43 centres completed it (82.7%). Among these centres, 23 institutions (53.5%) used the 0.35T MR-Linac system, while the remaining 20 (46.5%) used the 1.5T MR-Linac system.According to results obtained, 25 (58%) of the centres implemented the use of MRCA for on-line MRIgRT. Gadoxetate (Eovist®; Primovist®) was reported to be the most used MRCA (80%) and liver the most common site of application (58%). Over 70% of responders agreed/strongly agreed to the need for international guidelines.

Conclusions

The use of MRCA in clinical practice presents several pitfalls and future research will be necessary to understand the actual advantage derived from the use of MRCA in clinical practice, their toxicity profiles and better define the need of formulating guidelines for standardising the use of MRCA in MRIgRT workflow.

Application of simultaneous uncertainty quantification for image segmentation with probabilistic deep learning: Performance benchmarking of oropharyngeal cancer target delineation as a use-case

Background

Oropharyngeal cancer (OPC) is a widespread disease, with radiotherapy being a core treatment modality. Manual segmentation of the primary gross tumor volume (GTVp) is currently employed for OPC radiotherapy planning, but is subject to significant interobserver variability. Deep learning (DL) approaches have shown promise in automating GTVp segmentation, but comparative (auto)confidence metrics of these models predictions has not been well-explored. Quantifying instance-specific DL model uncertainty is crucial to improving clinician trust and facilitating broad clinical implementation. Therefore, in this study, probabilistic DL models for GTVp auto-segmentation were developed using large-scale PET/CT datasets, and various uncertainty auto-estimation methods were systematically investigated and benchmarked.

Methods

We utilized the publicly available 2021 HECKTOR Challenge training dataset with 224 co-registered PET/CT scans of OPC patients with corresponding GTVp segmentations as a development set. A separate set of 67 co-registered PET/CT scans of OPC patients with corresponding GTVp segmentations was used for external validation. Two approximate Bayesian deep learning methods, the MC Dropout Ensemble and Deep Ensemble, both with five submodels, were evaluated for GTVp segmentation and uncertainty performance. The segmentation performance was evaluated using the volumetric Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance at 95% (95HD). The uncertainty was evaluated using four measures from literature: coefficient of variation (CV), structure expected entropy, structure predictive entropy, and structure mutual information, and additionally with our novel Dice-risk measure. The utility of uncertainty information was evaluated with the accuracy of uncertainty-based segmentation performance prediction using the Accuracy vs Uncertainty (AvU) metric, and by examining the linear correlation between uncertainty estimates and DSC. In addition, batch-based and instance-based referral processes were examined, where the patients with high uncertainty were rejected from the set. In the batch referral process, the area under the referral curve with DSC (R-DSC AUC) was used for evaluation, whereas in the instance referral process, the DSC at various uncertainty thresholds were examined.

Results

Both models behaved similarly in terms of the segmentation performance and uncertainty estimation. Specifically, the MC Dropout Ensemble had 0.776 DSC, 1.703 mm MSD, and 5.385 mm 95HD. The Deep Ensemble had 0.767 DSC, 1.717 mm MSD, and 5.477 mm 95HD. The uncertainty measure with the highest DSC correlation was structure predictive entropy with correlation coefficients of 0.699 and 0.692 for the MC Dropout Ensemble and the Deep Ensemble, respectively. The highest AvU value was 0.866 for both models. The best performing uncertainty measure for both models was the CV which had R-DSC AUC of 0.783 and 0.782 for the MC Dropout Ensemble and Deep Ensemble, respectively. With referring patients based on uncertainty thresholds from 0.85 validation DSC for all uncertainty measures, on average the DSC improved from the full dataset by 4.7% and 5.0% while referring 21.8% and 22% patients for MC Dropout Ensemble and Deep Ensemble, respectively.

Conclusion

We found that many of the investigated methods provide overall similar but distinct utility in terms of predicting segmentation quality and referral performance. These findings are a critical first-step towards more widespread implementation of uncertainty quantification in OPC GTVp segmentation.

Prospective imaging comparison of anatomic delineation with rapid kV cone beam CT on a novel ring gantry radiotherapy device

INTRODUCTION

A kV imager coupled to a novel, ring-gantry radiotherapy system offers improved on-board kV-cone-beam computed tomography (CBCT) acquisition time (17-40 seconds) and image quality, which may improve CT radiotherapy image-guidance and enable online adaptive radiotherapy. We evaluated whether inter-observer contour variability over various anatomic structures was non-inferior using a novel ring gantry kV-CBCT (RG-CBCT) imager as compared to diagnostic-quality simulation CT (simCT).

MATERIALS/METHODS

Seven patients undergoing radiotherapy were imaged with the RG-CBCT system at breath hold (BH) and/or free breathing (FB) for various disease sites on a prospective imaging study. Anatomy was independently contoured by seven radiation oncologists on: 1. SimCT 2. Standard C-arm kV-CBCT (CA-CBCT), and 3. Novel RG-CBCT at FB and BH. Inter-observer contour variability was evaluated by computing simultaneous truth and performance level estimation (STAPLE) consensus contours, then computing average symmetric surface distance (ASSD) and Dice similarity coefficient (DSC) between individual raters and consensus contours for comparison across image types.

RESULTS

Across 7 patients, 18 organs-at-risk (OARs) were evaluated on 27 image sets. Both BH and FB RG-CBCT were non-inferior to simCT for inter-observer delineation variability across all OARs and patients by ASSD analysis (p < 0.001), whereas CA-CBCT was not (p = 0.923). RG-CBCT (FB and BH) also remained non-inferior for abdomen and breast subsites compared to simCT on ASSD analysis (p < 0.025). On DSC comparison, neither RG-CBCT nor CA-CBCT were non-inferior to simCT for all sites (p > 0.025).

CONCLUSIONS

Inter-observer ability to delineate OARs using novel RG-CBCT images was non-inferior to simCT by the ASSD criterion but not DSC criterion.

Inter-Observer Variability in MR-Based Target Volume Delineation of Uveal Melanoma

Purpose

Several efforts are being undertaken toward MRI-based treatment planning for ocular proton therapy for uveal melanoma (UM). The interobserver variability of the gross target volume (GTV) on magnetic resonance imaging (MRI) is one of the important parameters to design safety margins for a reliable treatment. Therefore, this study assessed the interobserver variation in GTV delineation of UM on MRI.

Methods and Materials

Six observers delineated the GTV in 10 different patients using the Big Brother contouring software. Patients were scanned at 3T MRI with a surface coil, and tumors were delineated separately on contrast enhanced 3DT1 (T1gd) and 3DT2-weighted scans with an isotropic acquisition resolution of 0.8 mm. Volume difference and overall local variation (median standard deviation of the distance between the delineated contours and the median contour) were analyzed for each GTV. Additionally, the local variation was analyzed for 4 interfaces: sclera, vitreous, retinal detachment, and tumor-choroid interface.

Results

The average GTV was significantly larger on T1gd (0.57cm³) compared with T2 (0.51cm³, P = .01). A not significant higher interobserver variation was found on T1gd (0.41 mm) compared with T2 (0.35 mm). The largest variations were found at the tumor-choroid interface due to peritumoral enhancement (T1gd, 0.62 mm; T2, 0.52 mm). As a result, a larger part of this tumor-choroid interface appeared to be included on T1gd-based GTVs compared with T2, explaining the smaller volumes on T2.

Conclusions

The interobserver variation of 0.4 mm on MRI are low with respect to the voxel size of 0.8 mm, enabling small treatment margins. We recommend delineation based on the T1gd-weighted scans, as choroidal tumor extensions might be missed.

Integrating external beam and prostate seed implant dosimetry for intermediate and high-risk prostate cancer using biologically effective dose: Impact of image registration technique

PURPOSE

Combining external beam radiation therapy (EBRT) and prostate seed implant (PSI) is efficacious in treating intermediate- and high-risk prostate cancer at the cost of increased genitourinary toxicity. Accurate combined dosimetry remains elusive due to lack of registration between treatment plans and different biological effect. The current work proposes a method to convert physical dose to biological effective dose (BED) and spatially register the dose distributions for more accurate combined dosimetry.

METHODS AND MATERIALS

A PSI phantom was CT scanned with and without seeds under rigid and deformed transformations. The resulting CTs were registered using image-based rigid registration (RI), fiducial-based rigid registration (RF), or b-spline deformable image registration (DIR) to determine which was most accurate. Physical EBRT and PSI dose distributions from a sample of 91 previously-treated combined-modality prostate cancer patients were converted to BED and registered using RI, RF, and DIR. Forty-eight (48) previously-treated patients whose PSI occurred before EBRT were included as a "control" group due to inherent registration. Dose-volume histogram (DVH) parameters were compared for RI, RF, DIR, DICOM, and scalar addition of DVH parameters using ANOVA or independent Student's t tests (α = 0.05).

RESULTS

In the phantom study, DIR was the most accurate registration algorithm, especially in the case of deformation. In the patient study, dosimetry from RI was significantly different than the other registration algorithms, including the control group. Dosimetry from RF and DIR were not significantly different from the control group or each other.

CONCLUSIONS

Combined dosimetry with BED and image registration is feasible. Future work will utilize this method to correlate dosimetry with clinical outcomes.

Generation of synthetic megavoltage CT for MRI-only radiotherapy treatment planning using a 3D deep convolutional neural network

BACKGROUND

Megavoltage computed tomography (MVCT) has been implemented on many radiotherapy treatment machines for on-board anatomical visualization, localization, and adaptive dose calculation. Implementing an MR-only workflow by synthesizing MVCT from magnetic resonance imaging (MRI) would offer numerous advantages for treatment planning and online adaptation.

PURPOSE

In this work, we sought to synthesize MVCT (sMVCT) datasets from MRI using deep learning to demonstrate the feasibility of MRI-MVCT only treatment planning.

METHODS

MVCTs and T1-weighted MRIs for 120 patients treated for head-and-neck cancer were retrospectively acquired and co-registered. A deep neural network based on a fully-convolutional 3D U-Net architecture was implemented to map MRI intensity to MVCT HU. Input to the model were volumetric patches generated from paired MRI and MVCT datasets. The U-Net was initialized with random parameters and trained on a mean absolute error (MAE) objective function. Model accuracy was evaluated on 18 withheld test exams. sMVCTs were compared to respective MVCTs. Intensity-modulated volumetric radiotherapy (IMRT) plans were generated on MVCTs of four different disease sites and compared to plans calculated onto corresponding sMVCTs using the gamma metric and dose-volume-histograms (DVHs).

RESULTS

MAE values between sMVCT and MVCT datasets were 93.3 ± 27.5, 78.2 ± 27.5, and 138.0 ± 43.4 HU for whole body, soft tissue, and bone volumes, respectively. Overall, there was good agreement between sMVCT and MVCT, with bone and air posing the greatest challenges. The retrospective dataset introduced additional deviations due to sinus filling or tumor growth/shrinkage between scans, differences in external contours due to variability in patient positioning, or when immobilization devices were absent from diagnostic MRIs. Dose distributions of IMRT plans evaluated for four test cases showed close agreement between sMVCT and MVCT images when evaluated using DVHs and gamma dose metrics, which averaged to 98.9 ± 1.0% and 96.8 ± 2.6% analyzed at 3%/3 mm and 2%/2 mm, respectively.

CONCLUSIONS

MVCT datasets can be generated from T1-weighted MRI using a 3D deep convolutional neural network with dose calculation on a sample sMVCT in close agreement with the MVCT. These results demonstrate the feasibility of using MRI-derived sMVCT in an MR-only treatment planning workflow.

Impact of metal artifact reduction algorithm on gross tumor volume delineation in tonsillar cancer: reducing the interobserver variation

Background

Patients with tonsillar cancer (TC) often have dental fillings that can significantly degrade the quality of computed tomography (CT) simulator images due to metal artifacts. We evaluated whether the use of the metal artifact reduction (MAR) algorithm reduced the interobserver variation in delineating gross tumor volume (GTV) of TC.

Methods

Eighteen patients with TC with dental fillings were enrolled in this study. Contrast-enhanced CT simulator images were reconstructed using the conventional (CT_CONV) and MAR algorithm (CT_MAR). Four board-certified radiation oncologists delineated the GTV of primary tumors using routine clinical data first on CT_CONV image datasets (GTV_CONV), followed by CT_CONV and CT_MAR fused image datasets (GTV_MAR) at least 2 weeks apart. Intermodality differences in GTV values and Dice similarity coefficient (DSC) were compared using Wilcoxon’s signed-rank test.

Results

GTV_MAR was significantly smaller than GTV_CONV for three observers. The other observer showed no significant difference between GTV_CONV and GTV_MAR values. For all four observers, the mean GTV_CONV and GTV_MAR values were 14.0 (standard deviation [SD]: 7.4) cm³ and 12.1 (SD: 6.4) cm³, respectively, with the latter significantly lower than the former (p < 0.001). The mean DSC of GTV_CONV and GTV_MAR was 0.74 (SD: 0.10) and 0.77 (SD: 0.10), respectively, with the latter significantly higher than that of the former (p < 0.001).

Conclusions

The use of the MAR algorithm led to the delineation of smaller GTVs and reduced interobserver variations in delineating GTV of the primary tumors in patients with TC.

Head and Neck Cancer Primary Tumor Auto Segmentation Using Model Ensembling of Deep Learning in PET/CT Images

Auto-segmentation of primary tumors in oropharyngeal cancer using PET/CT images is an unmet need that has the potential to improve radiation oncology workflows. In this study, we develop a series of deep learning models based on a 3D Residual Unet (ResUnet) architecture that can segment oropharyngeal tumors with high performance as demonstrated through internal and external validation of large-scale datasets (training size = 224 patients, testing size = 101 patients) as part of the 2021 HECKTOR Challenge. Specifically, we leverage ResUNet models with either 256 or 512 bottleneck layer channels that demonstrate internal validation (10-fold cross-validation) mean Dice similarity coefficient (DSC) up to 0.771 and median 95% Hausdorff distance (95% HD) as low as 2.919 mm. We employ label fusion ensemble approaches, including Simultaneous Truth and Performance Level Estimation (STAPLE) and a voxel-level threshold approach based on majority voting (AVERAGE), to generate consensus segmentations on the test data by combining the segmentations produced through different trained cross-validation models. We demonstrate that our best performing ensembling approach (256 channels AVERAGE) achieves a mean DSC of 0.770 and median 95% HD of 3.143 mm through independent external validation on the test set. Our DSC and 95% HD test results are within 0.01 and 0.06 mm of the top ranked model in the competition, respectively. Concordance of internal and external validation results suggests our models are robust and can generalize well to unseen PET/CT data. We advocate that ResUNet models coupled to label fusion ensembling approaches are promising candidates for PET/CT oropharyngeal primary tumors auto-segmentation. Future investigations should target the ideal combination of channel combinations and label fusion strategies to maximize segmentation performance.

3D FULLY CONVOLUTIONAL NETWORK FOR THORAX MULTI-ORGANS SEMANTIC SEGMENTATION

Automatically delineating Organs-at-Risks (OARs) on computed tomography (CT) has the benefit of both reducing the time and improving the quality of radiotherapy (RT) planning. A 3D convolutional deep learning framework for multi-organs segmentation is proposed in this work; moreover, for the small volume OARs, a robust 3D squeeze-and-excitation (SE) feature extraction mechanism and a new Dice loss function are incorporated in the traditional 3D U-Net. We collected 60 thorax CT images set with annotations and expanded to 260 patients by the augmented method of randomly rotating [Formula: see text]6 degrees with a 1/3 probability and adding Gaussian noise. The objective is to segment five important organs: esophagus, spinal cord, heart, and bilateral lungs. Compared with 3D U-Net, 3D-2D U-Net proposed in our work increases the Dice similarity coefficient by 5% on average for the heart and bilateral lungs, and 3D Small Volume U-Net can further increase the Dice similarity coefficient to above 80% for the spinal cord. The experiment results demonstrate that the proposed model can improve the delineation accuracy of OARs from CT images.

Evaluation of deep learning-based multiparametric MRI oropharyngeal primary tumor auto-segmentation and investigation of input channel effects: Results from a prospective imaging registry

BACKGROUND/PURPOSE

Oropharyngeal cancer (OPC) primary gross tumor volume (GTVp) segmentation is crucial for radiotherapy. Multiparametric MRI (mpMRI) is increasingly used for OPC adaptive radiotherapy but relies on manual segmentation. Therefore, we constructed mpMRI deep learning (DL) OPC GTVp auto-segmentation models and determined the impact of input channels on segmentation performance.

MATERIALS/METHODS

GTVp ground truth segmentations were manually generated for 30 OPC patients from a clinical trial. We evaluated five mpMRI input channels (T2, T1, ADC, Ktrans, Ve). 3D Residual U-net models were developed and assessed using leave-one-out cross-validation. A baseline T2 model was compared to mpMRI models (T2 + T1, T2 + ADC, T2 + Ktrans, T2 + Ve, all five channels [ALL]) primarily using the Dice similarity coefficient (DSC). False-negative DSC (FND), false-positive DSC, sensitivity, positive predictive value, surface DSC, Hausdorff distance (HD), 95% HD, and mean surface distance were also assessed. For the best model, ground truth and DL-generated segmentations were compared through a blinded Turing test using three physician observers.

RESULTS

Models yielded mean DSCs from 0.71 ± 0.12 (ALL) to 0.73 ± 0.12 (T2 + T1). Compared to the T2 model, performance was significantly improved for FND, sensitivity, surface DSC, HD, and 95% HD for the T2 + T1 model (p < 0.05) and for FND for the T2 + Ve and ALL models (p < 0.05). No model demonstrated significant correlations between tumor size and DSC (p > 0.05). Most models demonstrated significant correlations between tumor size and HD or Surface DSC (p < 0.05), except those that included ADC or Ve as input channels (p > 0.05). On average, there were no significant differences between ground truth and DL-generated segmentations for all observers (p > 0.05).

CONCLUSION

DL using mpMRI provides reasonably accurate segmentations of OPC GTVp that may be comparable to ground truth segmentations generated by clinical experts. Incorporating additional mpMRI channels may increase the performance of FND, sensitivity, surface DSC, HD, and 95% HD, and improve model robustness to tumor size.

Reduction of GTV to high-risk CTV radiation margin in head and neck squamous cell carcinoma significantly reduced acute and late radiation-related toxicity with comparable outcomes

BACKGROUND AND PURPOSE

We aim to retrospectively investigate whether reducing GTV to high-risk CTV margin will significantly reduce acute and late toxicity without jeopardizing outcome in head-and-neck squamous cell carcinoma (HNSCC) treated with definitive (chemo)radiation.

MATERIALS AND METHODS

Between April 2015 and April 2019, 155 consecutive patients were treated with GTV to high-risk CTV margin of 10 mm and subsequently another 155 patients with 6 mm margin. The CTV-PTV margin was 3 mm for both groups. All patients were treated with volumetric-modulated arc therapy with daily image-guidance using cone-beam CT. End points of the study were acute and late toxicity and oncologic outcomes.

RESULTS

Overall acute grade 3 toxicity was significantly lower in 6 mm, compared to 10 mm group (48% vs. 67%, respectively, p < 0.01). The same was true for acute grade 3 mucositis (18% vs. 34%, p < 0.01) and grade ≥ 2 dysphagia (67% vs. 85%, p < 0.01). Also feeding tube-dependency at the end of treatment (25% vs. 37%, p = 0.02), at 3 months (12% and 25%, p < 0.01), and at 6 months (6% and 15%, p = 0.01) was significantly less in 6 mm group. The incidence of late grade 2 xerostomia was also significantly lower in the 6 mm group (32% vs. 50%, p < 0.01). The 2-year rates of loco-regional control, disease-free and overall survival were 78.7% vs. 73.1%, 70.6% vs. 61.4%, and 83.2% vs. 74.4% (p > 0.05, all).

CONCLUSION

The first study reporting on reduction of GTV to high-risk CTV margin from 10 to 6 mm showed significant reduction of the incidence and severity of radiation-related toxicity without reducing local-regional control and survival.

CT synthesis from MRI using multi-cycle GAN for head-and-neck radiation therapy

Magnetic Resonance Imaging (MRI) guided Radiation Therapy is a hot topic in the current studies of radiotherapy planning, which requires using MRI to generate synthetic Computed Tomography (sCT). Despite recent progress in image-to-image translation, it remains challenging to apply such techniques to generate high-quality medical images. This paper proposes a novel framework named Multi-Cycle GAN, which uses the Pseudo-Cycle Consistent module to control the consistency of generation and the domain control module to provide additional identical constraints. Besides, we design a new generator named Z-Net to improve the accuracy of anatomy details. Extensive experiments show that Multi-Cycle GAN outperforms state-of-the-art CT synthesis methods such as Cycle GAN, which improves MAE to 0.0416, ME to 0.0340, PSNR to 39.1053.

Standardization for oncologic head and neck surgery

The inherent variability in performing specific surgical procedures for head and neck cancer remains a barrier for accurately assessing treatment outcomes, particularly in clinical trials. While non-surgical modalities for cancer therapeutics have evolved to become far more uniform, there remains the challenge to standardize surgery. The purpose of this review is to identify the barriers in achieving uniformity and to highlight efforts by surgical groups to standardize selected operations and nomenclature. While further improvements in standardization will remain a challenge, we must encourage surgical groups to focus on strategies that provide such a level.

A review of deep learning based methods for medical image multi-organ segmentation

Deep learning has revolutionized image processing and achieved the-state-of-art performance in many medical image segmentation tasks. Many deep learning-based methods have been published to segment different parts of the body for different medical applications. It is necessary to summarize the current state of development for deep learning in the field of medical image segmentation. In this paper, we aim to provide a comprehensive review with a focus on multi-organ image segmentation, which is crucial for radiotherapy where the tumor and organs-at-risk need to be contoured for treatment planning. We grouped the surveyed methods into two broad categories which are 'pixel-wise classification' and 'end-to-end segmentation'. Each category was divided into subgroups according to their network design. For each type, we listed the surveyed works, highlighted important contributions and identified specific challenges. Following the detailed review, we discussed the achievements, shortcomings and future potentials of each category. To enable direct comparison, we listed the performance of the surveyed works that used thoracic and head-and-neck benchmark datasets.

Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax

PURPOSE

To propose a multi-output fully convolutional network (MOFCN) to segment bilateral lung, heart and spinal cord in the planning thoracic computed tomography (CT) slices automatically and simultaneously.

METHODS

The MOFCN includes two components: one main backbone and three branches. The main backbone extracts the features about lung, heart and spinal cord. The extracted features are transferred to three branches which correspond to three organs respectively. The longest branch to segment spinal cord is nine layers, including input and output layers. The MOFCN was evaluated on 19,277 CT slices from 966 patients with cancer in the thorax. In these slices, the organs at risk (OARs) were delineated and validated by experienced radiation oncologists, and served as ground truth for training and evaluation. The data from 61 randomly chosen patients were used for training and validation. The remaining 905 patients' slices were used for testing. The metric used to evaluate the similarity between the auto-segmented organs and their ground truth was Dice. Besides, we compared the MOFCN with other published models. To assess the distinct output design and the impact of layer number and dilated convolution, we compared MOFCN with a multi-label learning model and its variants. By analyzing the not good performances, we suggested possible solutions.

RESULTS

MOFCN achieved Dice of 0.95 ± 0.02 for lung, 0.91 ± 0.03 for heart and 0.87 ± 0.06 for spinal cord. Compared to other models, MOFCN could achieve a comparable accuracy with the least time cost.

CONCLUSION

The results demonstrated the MOFCN's effectiveness. It uses less parameters to delineate three OARs simultaneously and automatically, and thus shows a relatively low requirement for hardware and has potential for broad application.

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

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.

Positron emission tomography for radiotherapy planning in head and neck cancer: What impact?

PET-computed tomography (CT) plays a growing role to guide target volume delineation for head and neck cancer in radiation oncology. Pretherapeutic [18F]FDG PET-CT adds information to morphological imaging. First, as a whole-body imaging modality, it reveals regional or distant metastases that induce major therapeutic changes in more than 10% of the cases. Moreover, it allows better pathological lymph node selection which improves overall regional control and overall survival. Second, locally, it allows us to define the metabolic tumoral volume, which is a reliable prognostic feature for survival outcome. [18F]FDG PET-CT-based gross tumor volume (GTV) is on average significantly smaller than GTV based on CT. Nevertheless, the overlap is incomplete and more evaluation of composite GTV based on PET and GTV based on CT are needed. However, in clinical practice, the study showed that using GTV PET alone for treatment planning was similar to using GTVCT for local control and dose distribution was better as a dose to organs at risk significantly decreased. In addition to FDG, pretherapeutic PET could give access to different biological tumoral volumes - thanks to different tracers - guiding heterogeneous dose delivery (dose painting concept) to resistant subvolumes. During radiotherapy treatment, follow-up [18F]FDG PET-CT revealed an earlier and more important diminution of GTV than other imaging modality. It may be a valuable support for adaptative radiotherapy as a new treatment plan with a significant impact on dose distribution became possible. Finally, additional studies are required to prospectively validate long-term outcomes and lower toxicity resulting from the use of PET-CT in treatment planning.

Tumor Segmentation in Patients with Head and Neck Cancers Using Deep Learning Based-on Multi-modality PET/CT Images

Segmentation of head and neck cancer (HNC) primary tumors onmedical images is an essential, yet labor-intensive, aspect of radiotherapy.PET/CT imaging offers a unique ability to capture metabolic and anatomicinformation, which is invaluable for tumor detection and border definition. Anautomatic segmentation tool that could leverage the dual streams of informationfrom PET and CT imaging simultaneously, could substantially propel HNCradiotherapy workflows forward. Herein, we leverage a multi-institutionalPET/CT dataset of 201 HNC patients, as part of the MICCAI segmentationchallenge, to develop novel deep learning architectures for primary tumor auto-segmentation for HNC patients. We preprocess PET/CT images by normalizingintensities and applying data augmentation to mitigate overfitting. Both 2D and3D convolutional neural networks based on the U-net architecture, which wereoptimized with a model loss function based on a combination of dice similaritycoefficient (DSC) and binary cross entropy, were implemented. The median andmean DSC values comparing the predicted tumor segmentation with the groundtruth achieved by the models through 5-fold cross validation are 0.79 and 0.69for the 3D model, respectively, and 0.79 and 0.67 for the 2D model, respec-tively. These promising results show potential to provide an automatic, accurate,and efficient approach for primary tumor auto-segmentation to improve theclinical practice of HNC treatment.

Synthetic computed tomography data allows for accurate absorbed dose calculations in a magnetic resonance imaging only workflow for head and neck radiotherapy

•

The geometry of the synthetic CT is comparable to the CT in the H&N region.

•

Synthetic CT in the H&N region provides similar absorbed dose calculation as the CT.

•

Absorbed dose calculations in the dental region could benefit from using synthetic CT.

Background and purpose

Few studies on magnetic resonance imaging (MRI) only head and neck radiation treatment planning exist, and none using a generally available software. The aim of this study was to evaluate the accuracy of absorbed dose for head and neck synthetic computed tomography data (sCT) generated by a commercial convolutional neural network-based algorithm.

Materials and methods

For 44 head and neck cancer patients, sCT were generated and the geometry was validated against computed tomography data (CT). The clinical CT based treatment plan was transferred to the sCT and recalculated without re-optimization, and differences in relative absorbed dose were determined for dose-volume-histogram (DVH) parameters and the 3D volume.

Results

For overall body, the results of the geometric validation were (Mean ± 1sd): Mean error −5 ± 10 HU, mean absolute error 67 ± 14 HU, Dice similarity coefficient 0.98 ± 0.05, and Hausdorff distance difference 4.2 ± 1.7 mm. Water equivalent depth difference for region Th1-C7, mid mandible and mid nose were −0.3 ± 3.4, 1.1 ± 2.0 and 0.7 ± 3.8 mm respectively. The maximum mean deviation in absorbed dose for all DVH parameters was 0.30% (0.12 Gy). The absorbed doses were considered equivalent (p-value < 0.001) and the mean 3D gamma passing rate was 99.4 (range: 95.7–99.9%).

Conclusions

The convolutional neural network-based algorithm generates sCT which allows for accurate absorbed dose calculations for MRI-only head and neck radiation treatment planning. The sCT allows for statistically equivalent absorbed dose calculations compared to CT based radiotherapy.

Contour Variability in Thyroid Eye Disease with Compressive Optic Neuropathy Treated with Radiation Therapy

Purpose

Few studies have evaluated the methodology by which radiation therapy (RT) for thyroid eye disease and compressive optic neuropathy is performed. The objective of this study was to retrospectively review our experience from a radiation planning standpoint and to determine whether current treatment methods provide adequate dose to target and collateral structures.

Methods

A retrospective review of 52 patients (104 orbits) with bilateral thyroid eye disease and compressive optic neuropathy treated with RT (20 Gy in 10 fractions) at our institution. RT plans were analyzed for target volumes and doses. Visual fields, color plates, and visual acuity were assessed pretreatment and at last available follow-up post RT. A standardized, anatomic contour of the retro-orbital space was applied to these retrospective plans to determine dose to the entire space, rather than the self-selected target structure.

Results

Compared with the anatomic retro-orbital space, the original contour overlapped by only 68%. Maximum and mean dose was 2134 cGy and 1910 cGy to the anatomic retro-orbital space. Consequently, 39.8% of the orbits had a mean dose <19 Gy (<17 Gy 16.4%, <18 Gy 27.6% <19 Gy 37.8%, <20 Gy 59.2%, 20-21 Gy 35.8%, >21 Gy 5%). There was no significant association of improvement in color plates (P = .07), visual fields (P = .77), and visual acuity (P = .62), based on these dose differences. When beam placement was retrospectively adjusted to include a space of 0.5 cm between the lens and the anterior beam edge, there was a 39.4% and 20.3% decrease in max and mean dose to the lens.

Conclusions

Without a standardized protocol for contouring in thyroid eye disease, target delineation was found to be rather varied, even among the same practitioner. Differences in dose to the anatomic retro-orbital space did not affect outcomes in the follow-up period. Although precise contouring of the retro-orbital space may be of little clinical consequence overall, a >0.5 cm space from the lens may significantly reduce or delay cataractogenesis.

A Bioresorbable Fiducial for Head and Neck Cancer

We aim to evaluate a novel bioresorbable fiducial for marking tumor bed margins in head and neck cancers (HNCs) to improve upon current use of nonresorbable materials. A feasibility test was done placing the marker (L-lactide and ε-caprolactone) in an orange for computed tomography (CT) and applesauce for T1-, T2-, and PD-weighted magnetic resonance imaging (MRI) image acquisition, using routine clinical parameters. The resulting CT and MRI images showed excellent delineation of the marker with all of its margins well seen without adjacent artifact. The marker appeared similar to air on CT and MRI, surrounded by fluid-like appearance of the medium. Surgical bed appearance when radiotherapy is planned should not produce any artifact near the marker, and there should be no inherent marker-related artifact. These pilot CT and MR images show clinical utility for intraoperative marking of positive margins in the skull base or neck to guide future treatment and monitoring.

[Uncertainties in the current concept of radiotherapy planning target volume]

The planning target volume is an essential notion in radiotherapy, that requires a new conceptualization. Indeed, the variability and diversity of the uncertainties involved or improved with the development of the new modern technologies and devices in radiotherapy suggest that random and systematic errors cannot be currently generalized. This article attempts to discuss these various uncertainties and tries to demonstrate that a redefinition of the concept of planning target volume toward its personalization for each patient and the robustness notion are likely an improvement basis to take into account the radiotherapy uncertainties.

Dose accumulation to assess the validity of treatment plans with reduced margins in radiotherapy of head and neck cancer

BACKGROUND AND PURPOSE

Literature has reported reduced treatment toxicity in head-and-neck radiotherapy (HNRT) when reducing the planning target volume (PTV) margin from 5 to 3 mm but loco-regional control was not always preserved. This study used deformable image registration (DIR)-facilitated dose accumulation to assess clinical target volume (CTV) coverage in the presence of anatomical changes.

MATERIALS AND METHODS

VMAT plans for 12 patients were optimized using 3 or 5 mm PTV and planning risk volume (PRV) margins. The planning computed tomography (pCT) scan was registered to each daily cone beam CT (CBCT) using DIR. The inverse registration was used to reconstruct and accumulate dose (D acc ). CTV coverage was assessed using the dose-volume histogram (DVH) metric D 99 % acc and by individual voxel analysis. Both approaches included an uncertainty estimate using the 95% level of confidence.

RESULTS

D 99 % acc was less than 95% of the prescribed doseD presc for three cases including only one case where this was at the 95% level of confidence. However for many patients, the accumulated dose included a substantial volume of voxels receiving less than 95%D presc independent of margin expansion, which predominantly occurred in the subdermal region. Loss in target coverage was very patient specific but tightness of target volume coverage at planning was a common factor leading to underdosage.

CONCLUSION

This study agrees with previous literature that PTV/PRV margin reduction did not significantly reduce CTV coverage during treatment, but also highlighted that tight coverage of target volumes at planning increases the risk of clinically unacceptable dose delivery. Patient-specific verification of dose delivery to assess the dose delivered to each voxel is recommended.

Development of a hybrid magnetic resonance/computed tomography-compatible phantom for magnetic resonance guided radiotherapy

The purpose of the present study was to develop a hybrid magnetic resonance/computed tomography (MR/CT)-compatible phantom and tissue-equivalent materials for each MR and CT image. Therefore, the essential requirements necessary for the development of a hybrid MR/CT-compatible phantom were determined and the development process is described. A total of 12 different tissue-equivalent materials for each MR and CT image were developed from chemical components. The uniformity of each sample was calculated. The developed phantom was designed to use 14 plugs that contained various tissue-equivalent materials. Measurement using the developed phantom was performed using a 3.0-T scanner with 32 channels and a Somatom Sensation 64. The maximum percentage difference of the signal intensity (SI) value on MR images after adding K2CO3 was 3.31%. Additionally, the uniformity of each tissue was evaluated by calculating the percent image uniformity (%PIU) of the MR image, which was 82.18 ±1.87% with 83% acceptance, and the average circular-shaped regions of interest (ROIs) on CT images for all samples were within ±5 Hounsfield units (HU). Also, dosimetric evaluation was performed. The percentage differences of each tissue-equivalent sample for average dose ranged from -0.76 to 0.21%. A hybrid MR/CT-compatible phantom for MR and CT was investigated as the first trial in this field of radiation oncology and medical physics.

Dosimetric evaluation of MR-derived synthetic-CTs for MR-only proton treatment planning

PURPOSE

To evaluate proton dose calculation accuracy of optimized pencil beam scanning (PBS) plans on MR-derived synthetic-CTs for prostate patients.

MATERIAL AND METHODS

Ten patient datasets with both a CT and an MRI were planned with opposed lateral proton beams optimized to single field uniform dose under an IRB-approved study. The proton plans were created on CT datasets generated by a commercial synthetic CT-based software called MRCAT (MR for Calculating ATtenuation) routinely used in our clinic for photon-based MR-only planning. A standard prescription of 79.2 Gy (RBE) and 68.4 Gy (RBE) was used for intact prostate and prostate bed cases, respectively. Proton plans were first generated and optimized using the MRCAT synthetic-CT (syn-CT), and then recalculated on the planning CT rigidly aligned with the syn-CT (aligned-CT) and a deformed planning CT (deformed-CT), which was deformed to match outer contour between syn-CT and aligned-CT. The same beam arrangement, total MUs, MUs/spot, spot positions were used to recalculate dose on deformed-CT and aligned-CT without renormalization. DVH analysis was performed on aligned-CT, deformed-CT, and syn-CT to compare D_98%, V_100%, V_95% for PTV, PTVeval, and GTV as well as V_70Gy, V_50Gy for OARs.

RESULTS

The relative percentage dose difference between syn-CT and deformed-CT, were (0.17 ± 0.33 %) for PTVeval D_98% and (0.07 ± 0.1 %) for CTV D_98%. Rectum V_70Gy, V_50Gy, and Bladder V_70Gy were (2.76 ± 4.01 %), (11.6 ± 11.2 %), and (3.41 ± 2.86 %), respectively for the syn-CT, and (3.23 ± 3.63 %), (11.3 ± 8.18 %), and (3.29 ± 2.76 %), respectively for the deformed-CT, and (1.37 ± 1.84 %), (8.48 ± 6.67 %), and (4.91 ± 3.65 %), respectively for aligned-CT.

CONCLUSION

Dosimetric analysis shows that MR-only proton planning is feasible using syn-CT based on current clinical margins that account for a range uncertainty.

Intravenous contrast media in radiation therapy planning computed tomography scans - Current practice in Ireland

Introduction

While Computerised Tomography (CT) remains the gold standard in radiation therapy (RT) planning, inferior soft tissue definition remains a challenge. Intravenous contrast (IVC) use during CT planning can enhance soft tissue contrast optimising Target Volume (TV) and Organ at Risk visualisation and delineation. Despite this known benefit, there are no guidelines for when and how to use IVC in RT planning scans in Ireland.

Aim

The study aims to examine the patterns of practice in relation to the use of IVC in RT planning scans in Ireland and to determine the level of compliance with international guidelines. Radiation Therapists (RTT) IVC training will also be investigated.

Materials and methods

An anonymised online survey was designed based on previously-reported literature. This was distributed to all RT departments in Ireland. The survey contained open, closed and Likert scale questions that investigated IVC practices in each department.

Results

75% (n = 9/12) of Irish departments responded. All responding departments reported using IVC. RTTs cannulated patients in 67% (n = 6/9) of the departments and administration contrast in all departments. Variations from recommended guidelines were found in disease sites where IVC was routinely used and in the assessment of renal functioning prior to contrast administration. IVC training varied in duration and number of supervised procedures required to fulfill competencies.

Conclusion

IVC is used extensively in Irish RT departments. There are variations in IVC practice between departments and with international recommended guidelines.

Retrospective Validation and Clinical Implementation of Automated Contouring of Organs at Risk in the Head and Neck: A Step Toward Automated Radiation Treatment Planning for Low- and Middle-Income Countries

Purpose

We assessed automated contouring of normal structures for patients with head-and-neck cancer (HNC) using a multiatlas deformable-image-registration algorithm to better provide a fully automated radiation treatment planning solution for low- and middle-income countries, provide quantitative analysis, and determine acceptability worldwide.

Methods

Autocontours of eight normal structures (brain, brainstem, cochleae, eyes, lungs, mandible, parotid glands, and spinal cord) from 128 patients with HNC were retrospectively scored by a dedicated HNC radiation oncologist. Contours from a 10-patient subset were evaluated by five additional radiation oncologists from international partner institutions, and interphysician variability was assessed. Quantitative agreement of autocontours with independently physician-drawn structures was assessed using the Dice similarity coefficient and mean surface and Hausdorff distances. Automated contouring was then implemented clinically and has been used for 166 patients, and contours were quantitatively compared with the physician-edited autocontours using the same metrics.

Results

Retrospectively, 87% of normal structure contours were rated as acceptable for use in dose-volume-histogram–based planning without edit. Upon clinical implementation, 50% of contours were not edited for use in treatment planning. The mean (± standard deviation) Dice similarity coefficient of autocontours compared with physician-edited autocontours for parotid glands (0.92 ± 0.10), brainstem (0.95 ± 0.09), and spinal cord (0.92 ± 0.12) indicate that only minor edits were performed. The average mean surface and Hausdorff distances for all structures were less than 0.15 mm and 1.8 mm, respectively.

Conclusion

Automated contouring of normal structures generates reliable contours that require only minimal editing, as judged by retrospective ratings from multiple international centers and clinical integration. Autocontours are acceptable for treatment planning with no or, at most, minor edits, suggesting that automated contouring is feasible for clinical use and in the ongoing development of automated radiation treatment planning algorithms.

Synthetic MRI-aided multi-organ segmentation on male pelvic CT using cycle consistent deep attention network

BACKGROUND AND PURPOSE

Manual contouring is labor intensive, and subject to variations in operator knowledge, experience and technique. This work aims to develop an automated computed tomography (CT) multi-organ segmentation method for prostate cancer treatment planning.

METHODS AND MATERIALS

The proposed method exploits the superior soft-tissue information provided by synthetic MRI (sMRI) to aid the multi-organ segmentation on pelvic CT images. A cycle generative adversarial network (CycleGAN) was used to estimate sMRIs from CT images. A deep attention U-Net (DAUnet) was trained on sMRI and corresponding multi-organ contours for auto-segmentation. The deep attention strategy was introduced to identify the most relevant features to differentiate different organs. Deep supervision was incorporated into the DAUnet to enhance the features' discriminative ability. Segmented contours of a patient were obtained by feeding CT image into the trained CycleGAN to generate sMRI, which was then fed to the trained DAUnet to generate organ contours. We trained and evaluated our model with 140 datasets from prostate patients.

RESULTS

The Dice similarity coefficient and mean surface distance between our segmented and bladder, prostate, and rectum manual contours were 0.95 ± 0.03, 0.52 ± 0.22 mm; 0.87 ± 0.04, 0.93 ± 0.51 mm; and 0.89 ± 0.04, 0.92 ± 1.03 mm, respectively.

CONCLUSION

We proposed a sMRI-aided multi-organ automatic segmentation method on pelvic CT images. By integrating deep attention and deep supervision strategy, the proposed network provides accurate and consistent prostate, bladder and rectum segmentation, and has the potential to facilitate routine prostate-cancer radiotherapy treatment planning.

Imaging for Target Delineation and Treatment Planning in Radiation Oncology: Current and Emerging Techniques

Imaging in radiation oncology has a wide range of applications. It is necessary not only for tumor staging and treatment response assessment after therapy but also for the treatment planning process, including definition of target and organs at risk, as well as treatment plan calculation. This article provides a comprehensive overview of the main imaging modalities currently used for target delineation and treatment planning and gives insight into new and promising techniques.

MRI basics for radiation oncologists

•

Issues of MRI that are relevant for radiation oncologists are addressed.

•

Radiation oncology requires dedicated scan protocols.

•

Use of diagnostic protocols is not recommended for radiotherapy.

•

MR images must be made in treatment position with the standard positioning devices.

•

Safety screening prior to entering the MRI room is crucial.

MRI is increasingly used in radiation oncology to facilitate tumor and organ-at-risk delineation and image guidance. In this review, we address issues of MRI that are relevant for radiation oncologists when interpreting MR images offered for radiotherapy. Whether MRI is used in combination with CT or in an MRI-only workflow, it is generally necessary to ensure that MR images are acquired in treatment position, using the positioning and fixation devices that are commonly applied in radiotherapy. For target delineation, often a series of separate image sets are used with distinct image contrasts, acquired within a single exam. MR images can suffer from image distortions. While this can be avoided with dedicated scan protocols, in a diagnostic setting geometrical fidelity is less relevant and is therefore less accounted for. Since geometrical fidelity is of utmost importance in radiation oncology, it requires dedicated scan protocols. The strong magnetic field of an MRI scanner and the use of radiofrequency radiation can cause safety hazards if not properly addressed. Safety screening is crucial for every patient and every operator prior to entering the MRI room.

Does 5 + 5 Equal Better Radiation Treatment Plans in Head and Neck Cancers?

Purpose

Accurate contouring in head and neck cancer (HNC) is critical. International consensus guidelines recommend the 5 + 5 mm rule for expansions around the primary tumor, wherein high- and low-dose clinical target volumes (CTV-P1 and CTV-P2, respectively) are created using successive 5 mm expansions on the gross tumor volume. To our knowledge, the necessity of a low-dose CTV-P2 has never been assessed; therefore, we evaluated the dosimetric impact of adding a CTV-P2 expansion using the 5 + 5 mm rule compared with contouring with a high-dose CTV-P1 alone.

Methods and materials

A retrospective study of clinically delivered (chemo)radiation therapy treatment plans for HNC was conducted. All patients were treated with 70 Gy in 35 fractions using volumetric modulated arc therapy in a single phase. CTV-P2 was retrospectively contoured per guidelines as a 5 mm expansion on CTV-P1 from the clinical plan, carving off specified barriers to spread. We used a 5 mm planning target volume (PTV) expansion. Our primary outcome was whether 95% of the volume of the PTV for the CTV-P2 contour (ie, PTV-P2) received at least 56 Gy. To assess dose falloff, the coverage of a PTV ring structure was created by subtracting PTV-P1 from PTV-P2.

Results

Twenty-seven patients from 4 HNC subsites (base of tongue, tonsil, hypopharynx, and supraglottic larynx) were included. In all 108 treatment plans, at least 95% of the PTV-P2 structure received at least 56 Gy. The minimum volume of the PTV-P2 structure receiving at least 56 Gy was 97.4%. Eight of 108 treatment plans had borderline coverage of the PTV ring substructure alone.

Conclusions

Adding a CTV-P2 structure using the 5 + 5 mm rule had no dosimetric impact, adds contouring time, adds treatment planning complexity, and could potentially introduce errors. The 5 + 5 mm rule may have value in other settings, such as when smaller PTV margins are used, and warrants further evaluation with prospective or randomized studies.

Advances in Auto-Segmentation

Manual image segmentation is a time-consuming task routinely performed in radiotherapy to identify each patient's targets and anatomical structures. The efficacy and safety of the radiotherapy plan requires accurate segmentations as these regions of interest are generally used to optimize and assess the quality of the plan. However, reports have shown that this process can be subject to significant inter- and intraobserver variability. Furthermore, the quality of the radiotherapy treatment, and subsequent analyses (ie, radiomics, dosimetric), can be subject to the accuracy of these manual segmentations. Automatic segmentation (or auto-segmentation) of targets and normal tissues is, therefore, preferable as it would address these challenges. Previously, auto-segmentation techniques have been clustered into 3 generations of algorithms, with multiatlas based and hybrid techniques (third generation) being considered the state-of-the-art. More recently, however, the field of medical image segmentation has seen accelerated growth driven by advances in computer vision, particularly through the application of deep learning algorithms, suggesting we have entered the fourth generation of auto-segmentation algorithm development. In this paper, the authors review traditional (nondeep learning) algorithms particularly relevant for applications in radiotherapy. Concepts from deep learning are introduced focusing on convolutional neural networks and fully-convolutional networks which are generally used for segmentation tasks. Furthermore, the authors provide a summary of deep learning auto-segmentation radiotherapy applications reported in the literature. Lastly, considerations for clinical deployment (commissioning and QA) of auto-segmentation software are provided.

Automatic multiorgan segmentation in thorax CT images using U-net-GAN

PURPOSE

Accurate and timely organs-at-risk (OARs) segmentation is key to efficient and high-quality radiation therapy planning. The purpose of this work is to develop a deep learning-based method to automatically segment multiple thoracic OARs on chest computed tomography (CT) for radiotherapy treatment planning.

METHODS

We propose an adversarial training strategy to train deep neural networks for the segmentation of multiple organs on thoracic CT images. The proposed design of adversarial networks, called U-Net-generative adversarial network (U-Net-GAN), jointly trains a set of U-Nets as generators and fully convolutional networks (FCNs) as discriminators. Specifically, the generator, composed of U-Net, produces an image segmentation map of multiple organs by an end-to-end mapping learned from CT image to multiorgan-segmented OARs. The discriminator, structured as an FCN, discriminates between the ground truth and segmented OARs produced by the generator. The generator and discriminator compete against each other in an adversarial learning process to produce the optimal segmentation map of multiple organs. Our segmentation results were compared with manually segmented OARs (ground truth) for quantitative evaluations in geometric difference, as well as dosimetric performance by investigating the dose-volume histogram in 20 stereotactic body radiation therapy (SBRT) lung plans.

RESULTS

This segmentation technique was applied to delineate the left and right lungs, spinal cord, esophagus, and heart using 35 patients' chest CTs. The averaged dice similarity coefficient for the above five OARs are 0.97, 0.97, 0.90, 0.75, and 0.87, respectively. The mean surface distance of the five OARs obtained with proposed method ranges between 0.4 and 1.5 mm on average among all 35 patients. The mean dose differences on the 20 SBRT lung plans are -0.001 to 0.155 Gy for the five OARs.

CONCLUSION

We have investigated a novel deep learning-based approach with a GAN strategy to segment multiple OARs in the thorax using chest CT images and demonstrated its feasibility and reliability. This is a potentially valuable method for improving the efficiency of chest radiotherapy treatment planning.

Precision of T2 TSE MRI-CT-image fusions based on gold fiducials and repetitive T2 TSE MRI-MRI-fusions for adaptive IGRT of prostate cancer by using phantom and patient data

INTRODUCTION

To increase precision of radiation treatment (RT) delivery in prostate cancer, MRI-based RT as well as the use of fiducials like gold markers (GMs) have shown promising results. Their combined use is currently under investigation in clinical trials. Here, we aimed to evaluate a workflow of image registration based on GMs between CT and MRI as well as weekly MRI-MRI adaption based on T2 TSE sequence.

MATERIAL AND METHODS

A gel-phantom with two inserted GMs was scanned with CT and three different MR-scanners of 1.5 and 3 T (T2 TSE and T1 VIBE-Dixon, isotropic, voxel size 2 × 2 × 2 mm). After image fusion, deviations for fiducial and gel match were measured and artifacts were evaluated. Additionally, CT-MRI-match deviations and MRI-MRI-match deviations of 10 Patients from the M-basePro study using GMs were assessed.

RESULTS

GMs were visible in all imaging modalities. The outer gel contours were matched with <1 mm deviation, contour volumes varied between 0 and 1%. The deviations of the GMs were less than 2 mm in any direction of MRI/CT. Shifts of peripherally or centrally located GMs were randomly distributed. The average MRI-CT-match precision of 10 patients with GMs was 1.9 mm (range 1.1-3.1 mm).

CONCLUSIONS

Match inaccuracies for GMs between reference CT and voxel-isotropic T2-TSE sequences are small. Spatial deviations of CT- and MR-contoured fiducials were less than 2 mm, i.e., below SLT of the applied modalities. In patients, the average CT-MRI-match precision for GMs was 1.9 mm supporting their use in MR-guided high precision RT.

Monitoring anatomical changes of individual patients using statistical process control during head-and-neck radiotherapy

•

EWMA trends from DIR data enabled timely detection of anatomical changes.

•

The majority of the systematic trends occurred before the 4th week of treatment.

•

Using SPC control limits, only 24% of patient positioning trends could be confirmed.

•

Using a 2 mm threshold, 82% of patient positioning trends could be confirmed.

•

Using SPC control limits, 90% of the soft tissue changes could be confirmed.

Background and purpose

Reduced toxicity while maintaining loco-regional control rates have been reported after reducing planning target volume (PTV) margins for head-and-neck radiotherapy (HNRT). In this context, quantifying anatomical changes to monitor patient treatment is preferred. This retrospective feasibility study investigated the application of deformable image registration (DIR) and Exponentially Weighted Moving Average (EWMA) Statistical Process Control (SPC) charts for this purpose.

Materials and methods

DIR between the computed tomography for treatment planning (pCT) images of twelve patients and their daily on-treatment cone beam computed tomography (CBCT) images quantified anatomical changes during treatment. EWMA charts investigated corresponding trends. Uncertainty analysis provided 90% confidence limits which were used to confirm whether a trend previously breached a threshold.

Results

Trends in patient positioning reproducibility occurred before the end of treatment week four in 54% of cases. Using SPC process limits, only 24% of these were confirmed at a 90% confidence level before the end of treatment. Using an a priori clinical limit of 2 mm, absolute changes in patient pose were detected in 39% of cases, of which 82% were confirmed. Soft tissue trends outside SPC process limits occurring before the end of treatment week four were confirmed in 90% of cases.

Conclusion

Structure specific action thresholds enabled detection of systematic anatomical changes during the first four weeks of treatment. Investigation of the dosimetric impact of the observed deviations is needed to show the efficacy of SPC to timely indicate required treatment adaptation and provide a safety net for PTV margin reduction.