Volume Delineation Research Articles

Nanoparticles Targeted to Fibroblast Activation Protein Outperform PSMA for MRI Delineation of Primary Prostate Tumors.

Accurate delineation of gross tumor volumes remains a barrier to radiotherapy dose escalation and boost dosing in the treatment of solid tumors, such as prostate cancer.Magneticresonance imaging (MRI)of tumor targets has the power to enable focal dose boosting, particularly when combined with technological advances such as MRI-linearaccelerator. Fibroblast activation protein (FAP) is overexpressed in stromal components of >90% of epithelial carcinomas. Herein, the authors compare targeted MRI of prostatespecificmembraneantigen (PSMA) with FAP in the delineation of orthotopic prostate tumors. Control, FAP, and PSMA-targeting iron oxide nanoparticleswereprepared with modification of a lymphotropic MRI agent (FerroTrace, Ferronova). Mice with orthotopic LNCaP tumors underwent MRI 24 h after intravenous injection of nanoparticles. FAP and PSMA nanoparticles produced contrast enhancement on MRI when compared to control nanoparticles. FAP-targeted MRI increased the proportion of tumor contrast-enhancing black pixels by 13%, compared to PSMA. Analysis of changes in R2 values between healthy prostates and LNCaP tumors indicated an increase in contrast-enhancing pixels in the tumor border of 15% when targeting FAP, compared to PSMA. This study demonstrates the preclinical feasibility of PSMA and FAP-targeted MRI which can enable targeted image-guided focal therapy of localized prostate cancer.

Evaluation of auto-segmentation for brachytherapy of postoperative cervical cancer using deep learning-based workflow

Objective. The purpose of this study was to evaluate the accuracy of brachytherapy (BT) planning structures derived from Deep learning (DL) based auto-segmentation compared with standard manual delineation for postoperative cervical cancer. Approach. We introduced a convolutional neural networks (CNN) which was developed and presented for auto-segmentation in cervical cancer radiotherapy. The dataset of 60 patients received BT of postoperative cervical cancer was used to train and test this model for delineation of high-risk clinical target volume (HRCTV) and organs at risk (OARs). Dice similarity coefficient (DSC), 95% Hausdorff distance (95%HD), Jaccard coefficient (JC) and dose-volume index (DVI) were used to evaluate the accuracy. The correlation between geometric metrics and dosimetric difference was performed by Spearman’s correlation analysis. The radiation oncologists scored the auto-segmented contours by rating the lever of satisfaction (no edits, minor edits, major edits). Main results. The mean DSC values of DL based model were 0.87, 0.94, 0.86, 0.79 and 0.92 for HRCTV, bladder, rectum, sigmoid and small intestine, respectively. The Bland-Altman test obtained dose agreement for HRCTV_D90%, HRCTV_Dmean, bladder_D2cc, sigmoid_D2cc and small intestine_D2cc. Wilcoxon’s signed-rank test indicated significant dosimetric differences in bladder_D0.1cc, rectum_D0.1cc and rectum_D2cc (P < 0.05). A strong correlation between HRCTV_D90% with its DSC (R = −0.842, P = 0.002) and JC (R = −0.818, P = 0.004) were found in Spearman’s correlation analysis. From the physician review, 80% of HRCTVs and 72.5% of OARs in the test dataset were shown satisfaction (no edits). Significance. The proposed DL based model achieved a satisfied agreement between the auto-segmented and manually defined contours of HRCTV and OARs, although the clinical acceptance of small volume dose of OARs around the target was a concern. DL based auto-segmentation was an essential component in cervical cancer workflow which would generate the accurate contouring.

Delineation of recurrent glioblastoma by whole brain spectroscopic magnetic resonance imaging

BackgroundGlioblastoma (GBM) cellularity correlates with whole brain spectroscopic MRI (sMRI) generated relative choline to N-Acetyl-Aspartate ratio (rChoNAA) mapping. In recurrent GBM (rGBM), tumor volume (TV) delineation is challenging and rChoNAA maps may assist with re-RT targeting.MethodsFourteen rGBM patients underwent sMRI in a prospective study. Whole brain sMRI was performed to generate rChoNAA maps. TVs were delineated by the union of rChoNAA ratio over 2 (rChoNAA > 2) on sMRI and T1PC. rChoNAA > 2 volumes were compared with multiparametric MRI sequences including T1PC, T2/FLAIR, diffusion-restriction on apparent diffusion coefficient (ADC) maps, and perfusion relative cerebral blood volume (rCBV).ResultsrChoNAA > 2 (mean 27.6 cc, range 6.6–79.1 cc) was different from other imaging modalities (P ≤ 0.05). Mean T1PC volumes were 10.7 cc (range 1.2–31.4 cc). The mean non-overlapping volume of rChoNAA > 2 and T1PC was 29.2 cm3. rChoNAA > 2 was 287% larger (range 23% smaller–873% larger) than T1PC. T2/FLAIR volumes (mean 111.7 cc, range 19.0–232.7 cc) were much larger than other modalities. rCBV volumes (mean 6.2 cc, range 0.2–19.1 cc) and ADC volumes were tiny (mean 0.8 cc, range 0–3.7 cc). Eight in-field failures were observed. Three patients failed outside T1PC but within rChoNAA > 2. No grade 3 toxicities attributable to re-RT were observed. Median progression-free and overall survival for re-RT patients were 6.5 and 7.1 months, respectively.ConclusionsTreatment of rGBM may be optimized by sMRI, and failure patterns suggest benefit for dose-escalation within sMRI-delineated volumes. Dose-escalation and radiologic-pathologic studies are underway to confirm the utility of sMRI in rGBM.

Benefits of automated gross tumor volume segmentation in head and neck cancer using multi-modality information

PurposeGross tumor volume (GTV) delineation for head and neck cancer (HNC) radiation therapy planning is time consuming and prone to interobserver variability (IOV). The aim of this study was (1) to develop an automated GTV delineation approach of primary tumor (GTVp) and pathologic lymph nodes (GTVn) based on a 3D convolutional neural network (CNN) exploiting multi-modality imaging input as required in clinical practice, and (2) to validate its accuracy, efficiency and IOV compared to manual delineation in a clinical setting. MethodsTwo datasets were retrospectively collected from 150 clinical cases. CNNs were trained for GTV delineation with consensus delineation as ground truth, with either single (CT) or co-registered multi-modal (CT + PET or CT + MRI) imaging data as input. For validation, GTVs were delineated on 20 new cases by two observers, once manually, once by correcting the delineations generated by the CNN. ResultsBoth multi-modality CNNs performed better than the single-modality CNN and were selected for clinical validation. Mean Dice Similarity Coefficient (DSC) for (GTVp, GTVn) respectively between automated and manual delineations was (69%, 79%) for CT + PET and (59%,71%) for CT + MRI. Mean DSC between automated and corrected delineations was (81%,89%) for CT + PET and (69%,77%) for CT + MRI. Mean DSC between observers was (76%,86%) for manual delineations and (95%,96%) for corrected delineations, indicating a significant decrease in IOV (p < 10−5), while efficiency increased significantly (48%, p < 10−5). ConclusionMulti-modality automated delineation of GTV of HNC was shown to be more efficient and consistent compared to manual delineation in a clinical setting and beneficial over a single-modality approach.

Biological target volume based on fluorine-18-fluorode-oxyglucose positron emission tomography/computed tomography imaging: a spurious proposition?

PurposeTo assess whether the high metabolic region of fluorine-18-fluorode-oxyglucose (18F-FDG) in the primary lesion is the crux for recurrence in patients with nasopharyngeal carcinoma (NPC), to assess the feasibility and rationale for use of biological target volume (BTV) based on 18F-FDG positron emission tomography/computed tomography (18F-FDG-PET/CT).MethodsThe retrospective study included 33 patients with NPC who underwent 18F-FDG-PET/CT at the time of initial diagnosis as well as the time of diagnosis of local recurrence. Paired 18F-FDG-PET/CT images for primary and recurrent lesion were matched by deformation coregistration method to determine the cross-failure rate between two lesions.ResultsThe median volume of the Vpri (primary tumor volume using the SUV thresholds of 2.5), the Vhigh (the volume of high FDG uptake using the SUV50%max isocontour), and the Vrecur (the recurrent tumor volume using the SUV thresholds of 2.5) were 22.85, 5.57, and 9.98 cm3, respectively. The cross-failure rate of Vrecur∩high showed that 82.82% (27/33) of local recurrent lesions had < 50% overlap volume with the region of high FDG uptake. The cross-failure rate of Vrecur∩pri showed that 96.97% (32/33) of local recurrent lesions had > 20% overlap volume with the primary tumor lesions and the median cross rate was up to 71.74%.Conclusion18F-FDG-PET/CT may be a powerful tool for automatic target volume delineation, but it may not be the optimal imaging modality for dose escalation radiotherapy based on applicable isocontour. The combination of other functional imaging could delineate the BTV more accurately.

Machine learning predictive performance evaluation of conventional and fuzzy radiomics in clinical cancer imaging cohorts

BackgroundHybrid imaging became an instrumental part of medical imaging, particularly cancer imaging processes in clinical routine. To date, several radiomic and machine learning studies investigated the feasibility of in vivo tumor characterization with variable outcomes. This study aims to investigate the effect of recently proposed fuzzy radiomics and compare its predictive performance to conventional radiomics in cancer imaging cohorts. In addition, lesion vs. lesion+surrounding fuzzy and conventional radiomic analysis was conducted.MethodsPreviously published 11C Methionine (MET) positron emission tomography (PET) glioma, 18F-FDG PET/computed tomography (CT) lung, and 68GA-PSMA-11 PET/magneto-resonance imaging (MRI) prostate cancer retrospective cohorts were included in the analysis to predict their respective clinical endpoints. Four delineation methods including manually defined reference binary (Ref-B), its smoothed, fuzzified version (Ref-F), as well as extended binary (Ext-B) and its fuzzified version (Ext-F) were incorporated to extract imaging biomarker standardization initiative (IBSI)-conform radiomic features from each cohort. Machine learning for the four delineation approaches was performed utilizing a Monte Carlo cross-validation scheme to estimate the predictive performance of the four delineation methods.ResultsReference fuzzy (Ref-F) delineation outperformed its binary delineation (Ref-B) counterpart in all cohorts within a volume range of 938–354987 mm3 with relative cross-validation area under the receiver operator characteristics curve (AUC) of +4.7–10.4. Compared to Ref-B, the highest AUC performance difference was observed by the Ref-F delineation in the glioma cohort (Ref-F: 0.74 vs. Ref-B: 0.70) and in the prostate cohort by Ref-F and Ext-F (Ref-F: 0.84, Ext-F: 0.86 vs. Ref-B: 0.80). In addition, fuzzy radiomics decreased feature redundancy by approx. 20%.ConclusionsFuzzy radiomics has the potential to increase predictive performance particularly in small lesion sizes compared to conventional binary radiomics in PET. We hypothesize that this effect is due to the ability of fuzzy radiomics to model partial volume effects and delineation uncertainties at small lesion boundaries. In addition, we consider that the lower redundancy of fuzzy radiomic features supports the identification of imaging biomarkers in future studies. Future studies shall consider systematically analyzing lesions and their surroundings with fuzzy and binary radiomics.

Advances in automatic delineation of target volume and cardiac substructure in breast cancer radiotherapy (Review).

Postoperative adjuvant radiotherapy plays an important role in the treatment of patients with breast cancer. With the continuous development of radiotherapeutic technologies, the requirements for radiotherapeutic accuracy are increasingly high. The accuracy of target volume and organ at risk delineation significantly affects the effect of radiotherapy. Automatic delineation software has been continuously developed for the automatic delineation of target areas and organs at risk. Automatic segmentation based on an atlas and deep learning is a hot topic in current clinical research. Automatic delineation can not only reduce the workload and delineation times, but also establish a uniform delineation standard and reduce inter-observer and intra-observer differences. In patients with breast cancer, especially in patients who undergo left breast radiotherapy, the protection of the heart is particularly important. Treating the whole heart as an organ at risk cannot meet the clinical needs, and it is necessary to limit the dose to specific cardiac substructures. The present review discusses the importance of automatic delineation of target volume and cardiac substructure in radiotherapy for patients with breast cancer.

United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration

Synthesizing abdominal contrast-enhanced computed tomography (CECT) images from non-enhanced CT (NECT) images is of great importance, in the delineation of radiotherapy target volumes, to reduce the risk of iodinated contrast agent and the registration error between NECT and CECT for transferring the delineations. NECT images contain structural information that can reflect the contrast difference between lesions and surrounding tissues. However, existing methods treat synthesis and registration as two separate tasks, which neglects the task collaborative and fails to address misalignment between images after the standard image pre-processing in training a CECT synthesis model. Thus, we propose an united multi-task learning (UMTL) for joint synthesis and deformable registration of abdominal CECT. Specifically, our UMTL is an end-to-end multi-task framework, which integrates a deformation field learning network for reducing the misalignment errors and a 3D generator for synthesizing CECT images. Furthermore, the learning of enhanced component images and the multi-loss function are adopted for enhancing the performance of synthetic CECT images. The proposed method is evaluated on two different resolution datasets and a separate test dataset from another center. The synthetic venous phase CECT images of the separate test dataset yield mean absolute error (MAE) of 32.78±7.27 HU, mean MAE of 24.15±5.12 HU on liver region, mean peak signal-to-noise rate (PSNR) of 27.59±2.45 dB, and mean structural similarity (SSIM) of 0.96±0.01. The Dice similarity coefficients of liver region between the true and synthetic venous phase CECT images are 0.96±0.05 (high-resolution) and 0.95±0.07 (low-resolution), respectively. The proposed method has great potential in aiding the delineation of radiotherapy target volumes.

Abstract TMP69: Random Rater Sampling For Deep Learning Algorithm To Segment Acute Ischemic Stroke On Non-contrast Computed Tomography

Introduction: The delineation of volume and location of acute ischemic brain tissue (AIBT) on Non-Contrast CT (NCCT) increases the efficiency of endovascular treatment decisions. However, the manual segmentation of the AIBT on NCCT is a challenging task and suffers from low inter-expert agreement. Whether supervised deep convolutional neural networks (CNN) are more accurate than expert raters remain to be determined, and the optimal ground truth segmentation of AIBT is unclear given the low inter-expert agreement. We hypothesized that randomly sampling ground truth segmentations of expert raters would enable the CNN to better approximate an accurate ground truth and increase performance. Methods: The data set consisted of 200 NCCT images (Figure 1a)) of acute ischemic stroke patients presenting within 6-16h and consenting to the DEFUSE3 trial. Three experienced neuroradiologists manually segmented the AIBT (Figure 1b)1.-3.). The aggregated validation sets of 5-fold-cross-validation were used to compare the (i) average inter-expert agreement, the average performance of (ii) three individual CNNs trained on each rater and (iii) one CNN trained with random rater sampling. Results: (iii) Random rater sampling (Figure 1c)) lead to a CNN performance superior to (ii) the average performance of individually trained CNNs. The reliability of a CNN goes beyond the human inter-expert agreement (i) (Surface Dice at Tolerance 5mm: 0.88 versus 0.68 and 0.67, respectively; Table 1). Conclusions: The volume and location of AIBT on NCCT can reliably be segmented by a CNN. The agreement between a randomly chosen rater and the CNN predictions surpasses the inter-expert agreement (Table 1).

Prognostic potential of a voxelwise invasion risk map of nasopharyngeal carcinoma based on a coordinate system of the nasopharynx.

Tumor invasion risk (TIR) is an important prognostic factor in nasopharyngeal carcinoma (NPC). We propose a novel prognostic analytic method for NPC based on a voxelwise analysis of TIR in a coordinate system of the nasopharynx. A stable nasopharynx coordinate system was constructed based on anatomical landmarks to obtain an accurate TIR profile for NPC. The coordinate system was validated by image registration of the lateral pterygoid muscle (LPM). The tumors were registered to the coordinate system through shift, scale, and rotation transformations. The voxelwise TIR map for NPC was obtained by superposition of all registered and mirrored tumor regions of interest. The minimum risk (MinR) point of the tumor region was used as an independent prognostic factor for NPC. The cutoff value was calculated with density plot and validated with restricted cubic splines (RCSs), and then the patients were divided into 2 groups for overall survival (OS) analysis. The first voxelwise TIR map of NPC was obtained based on 778 patients. The OS of patients with a low TIR was 76.8% and was 92.6% for patients with a high TIR [P<0.001; hazard ratio (HR) =1/0.45; 95% CI: 0.27-0.77; adjusted P=0.004]. Thus, patients with a low TIR had a poor prognosis, whereas patients with a high TIR had a good prognosis. The MinR may be better at grading the prognosis of patients compared to the American Joint Committee on Cancer (AJCC) staging or tumor/node (T/N) classification systems. The voxelwise TIR map provides a new method for the prognostic analysis of NPC. Potential clinical applications of voxelwise TIR mapping are clinical target volume (CTV) delineation and dose-painting for NPC.

The Impact of Interactive MRI-Based Radiologist Review on Radiotherapy Target Volume Delineation in Head and Neck Cancer.

Peer review of head and neck cancer radiation therapy target volumes by radiologists was introduced in our center to optimize target volume delineation. Our aim was to assess the impact of MR imaging-based radiologist peer review of head and neck radiation therapy gross tumor and nodal volumes, through qualitative and quantitative analysis. Cases undergoing radical radiation therapy with a coregistered MR imaging, between April 2019 and March 2020, were reviewed. The frequency and nature of volume changes were documented, with major changes classified as per the guidance of The Royal College of Radiologists. Volumetric alignment was assessed using the Dice similarity coefficient, Jaccard index, and Hausdorff distance. Fifty cases were reviewed between April 2019 and March 2020. The median age was 59 years (range, 29-83 years), and 72% were men. Seventy-six percent of gross tumor volumes and 41.5% of gross nodal volumes were altered, with 54.8% of gross tumor volume and 66.6% of gross nodal volume alterations classified as "major." Undercontouring of soft-tissue involvement and unidentified lymph nodes were predominant reasons for change. Radiologist review significantly altered the size of both the gross tumor volume (P = .034) and clinical target tumor volume (P = .003), but not gross nodal volume or clinical target nodal volume. The median conformity and surface distance metrics were the following: gross tumor volume Dice similarity coefficient = 0.93 (range, 0.82-0.96), Jaccard index = 0.87 (range, 0.7-0.94), Hausdorff distance = 7.45 mm (range, 5.6-11.7 mm); and gross nodular tumor volume Dice similarity coefficient = 0.95 (0.91-0.97), Jaccard index = 0.91 (0.83-0.95), and Hausdorff distance = 20.7 mm (range, 12.6-41.6). Conformity improved on gross tumor volume-to-clinical target tumor volume expansion (Dice similarity coefficient = 0.93 versus 0.95, P = .003). MR imaging-based radiologist review resulted in major changes to most radiotherapy target volumes and significant changes in volume size of both gross tumor volume and clinical target tumor volume, suggesting that this is a fundamental step in the radiotherapy workflow of patients with head and neck cancer.

U-Net Architectures for Prostate Cancer Radiation Therapy

Prostate Cancer (PCa) was first diagnosed in 1853 as cirrhosis of the prostate gland. Silently asymptomatic, PCa is usually diagnosed with Digital Rectal Examination (DRE) and Prostate Specific Antigen (PSA) levels. Since the first treatment of an advanced prostatic malignancy with X-rays by Imbert and Imbert in 1904, External Beam Radiation Therapy (EBRT) is now a curative option for localised and locally advanced disease and a palliative option for the metastatic low-volume disease. With the introduction of computers in EBRT and better imaging techniques, volume delineation is still a very time-consuming task. While Deep Learning methods are urged, EBRT systems still rely on manual or semi-automatic segmentation techniques. The U-Net architecture was specially designed for medical image segmentation presenting promising results. This literature review gathers work using U-Net architectures, outlining methods, techniques and obtained outcomes as a potential foundation for an automated segmentation framework for PCa.

Observation of the delineation of the target volume of radiotherapy in adult-type diffuse gliomas after temozolomide-based chemoradiotherapy: analysis of recurrence patterns and predictive factors

BackgroundRadiation therapy is the cornerstone of treatment for adult-type diffuse gliomas, but recurrences are inevitable. Our study assessed the prognosis and recurrence pattern of different radiotherapy volumes after temozolomide-based chemoradiation in our institution.MethodsThe treatment plans were classified into two groups, the plan 1 intentionally involved the entire edema area while plan 2 did not. Retrospectively investigate the differences in outcomes of 118 adult-type diffuse gliomas patients between these two treatment plans. Then, patients who underwent relapse were selected to analyze their recurrence patterns. Continuous dynamic magnetic resonance images (MRI) were collected to categorized the recurrence patterns into central, in-field, marginal, distant, and cerebrospinal fluid dissemination (CSF-d) recurrence. Finally, the clinical and molecular characteristics which influenced progression were analyzed.ResultsPlan 1 (n = 63) showed a median progression-free survival (PFS) and overall survival (OS) of 9.5 and 26.4 months while plan 2 (n = 55) showed a median PFS and OS of 9.4 and 36.5 months (p = 0.418; p = 0.388). Treatment target volume had no effect on the outcome in patients with adult-type diffuse gliomas. And there was no difference in radiation toxicity (p = 0.388). Among the 90 relapsed patients, a total of 58 (64.4%) patients had central recurrence, 10 (11.1%) patients had in-field recurrence, 3 (3.3%) patients had marginal recurrence, 11 (12.2.%) patients had distant recurrence, and 8 (8.9%) patients had CSF-d recurrence. By treatment plans, the recurrence patterns were similar and there was no significant difference in survival. Reclassifying the progression pattern into local and non-local groups, we observed that oligodendroglioma (n = 10) all relapsed in local and no difference in PFS and OS between the two groups (p > 0.05). Multivariable analysis showed that subventricular zone (SVZ) involvement was the independent risk factor for non-local recurrence in patients with GBM (p < 0.05).ConclusionIn our study, deliberately including or not the entire edema had no impact on prognosis and recurrence. Patients with varied recurrence patterns had diverse clinical and genetic features.

MRI-derived radiomics to guide post-operative management of glioblastoma: Implication for personalized radiation treatment volume delineation.

The glioblastoma's bad prognosis is primarily due to intra-tumor heterogeneity, demonstrated from several studies that collected molecular biology, cytogenetic data and more recently radiomic features for a better prognostic stratification. The GLIFA project (GLIoblastoma Feature Analysis) is a multicentric project planned to investigate the role of radiomic analysis in GB management, to verify if radiomic features in the tissue around the resection cavity may guide the radiation target volume delineation. We retrospectively analyze from three centers radiomic features extracted from 90 patients with total or near total resection, who completed the standard adjuvant treatment and for whom we had post-operative images available for features extraction. The Manual segmentation was performed on post gadolinium T1w MRI sequence by 2 radiation oncologists and reviewed by a neuroradiologist, both with at least 10 years of experience. The Regions of interest (ROI) considered for the analysis were: the surgical cavity ± post-surgical residual mass (CTV_cavity); the CTV a margin of 1.5 cm added to CTV_cavity and the volume resulting from subtracting the CTV_cavity from the CTV was defined as CTV_Ring. Radiomic analysis and modeling were conducted in RStudio. Z-score normalization was applied to each radiomic feature. A radiomic model was generated using features extracted from the Ring to perform a binary classification and predict the PFS at 6 months. A 3-fold cross-validation repeated five times was implemented for internal validation of the model. Two-hundred and seventy ROIs were contoured. The proposed radiomic model was given by the best fitting logistic regression model, and included the following 3 features: F_cm_merged.contrast, F_cm_merged.info.corr.2, F_rlm_merged.rlnu. A good agreement between model predicted probabilities and observed outcome probabilities was obtained (p-value of 0.49 by Hosmer and Lemeshow statistical test). The ROC curve of the model reported an AUC of 0.78 (95% CI: 0.68-0.88). This is the first hypothesis-generating study which applies a radiomic analysis focusing on healthy tissue ring around the surgical cavity on post-operative MRI. This study provides a preliminary model for a decision support tool for a customization of the radiation target volume in GB patients in order to achieve a margin reduction strategy.

Deep learning-based accurate delineation of primary gross tumor volume of nasopharyngeal carcinoma on heterogeneous magnetic resonance imaging: A large-scale and multi-center study

Background and purposeThe problem of obtaining accurate primary gross tumor volume (GTVp) segmentation for nasopharyngeal carcinoma (NPC) on heterogeneous magnetic resonance imaging (MRI) images with deep learning remains unsolved. Herein, we reported a new deep-learning method than can accurately delineate GTVp for NPC on multi-center MRI scans. Material and methodsWe collected 1057 patients with MRI images from five hospitals and randomly selected 600 patients from three hospitals to constitute a mixed training cohort for model development. The resting patients were used as internal (n = 259) and external (n = 198) testing cohorts for model evaluation. An augmentation-invariant strategy was proposed to delineate GTVp from multi-center MRI images, which encouraged networks to produce similar predictions for inputs with different augmentations to learn invariant anatomical structure features. The Dice similarity coefficient (DSC), 95 % Hausdorff distance (HD95), average surface distance (ASD), and relative absolute volume difference (RAVD) were used to measure segmentation performance. ResultsThe model-generated predictions had a high overlap ratio with the ground truth. For the internal testing cohorts, the average DSC, HD95, ASD, and RAVD were 0.88, 4.99 mm, 1.03 mm, and 0.13, respectively. For external testing cohorts, the average DSC, HD95, ASD, and RAVD were 0.88, 3.97 mm, 0.97 mm, and 0.10, respectively. No significant differences were found in DSC, HD95, and ASD for patients with different T categories, MRI thickness, or in-plane spacings. Moreover, the proposed augmentation-invariant strategy outperformed the widely-used nnUNet, which uses conventional data augmentation approaches. ConclusionOur proposed method showed a highly accurate GTVp segmentation for NPC on multi-center MRI images, suggesting that it has the potential to act as a generalized delineation solution for heterogeneous MRI images.

Overcoming inter-observer planning variability in target volume contouring and dose planning for high-risk neuroblastoma – a European multicenter effort of the SIOPEN radiotherapy committee

Background and purposeTo establish an international quality standard for contouring and planning for high-risk neuroblastoma within the prospective High-Risk Neuroblastoma Study 2 of SIOP-Europe-Neuroblastoma (SIOPEN HR-NBL2), which includes a randomized question on dose escalation for residual disease. Materials and methodsData on four patients with high-risk neuroblastoma were selected and distributed to the radiotherapy committee of the HR-NBL2 study for independent contouring and planning. Differences in contouring were analyzed using apparent and kappa-corrected agreement. Plans were analyzed regarding the dose-volume histogram metrics. Results were discussed among experts and agreement was obtained. ResultsSubstantial agreement was found for contouring of the heart (0.64), liver (0.70), left lung (0.74), and right lung (0.74). For contouring of the gastrointestinal tract (0.54), left kidney (0.60), and right kidney (0.59) moderate agreement was obtained. For target volume delineation, agreement for preoperative tumour extent was moderate (0.42), for CTV fair (0.35) and only low (0.06) for residual tumour, respectively. The dose planning strategies appeared to be relatively homogeneous among all experts. ConclusionConsiderable variability was found for the delineation of target volumes, particularly the boost volume, whereas the contouring of the organs at risk and the planning strategy were reasonably consistent. In order to obtain reliable results from the randomized HR-NBL2 trial, standardization of target volume delineation based on adequate imaging is crucial.

Initial clinical experience with magnetic resonance-guided radiotherapy in pediatric patients: Lessons learned from a single institution with proton therapy.

Magnetic resonance-guided radiotherapy (MRgRT) is increasingly used in a variety of adult cancers. To date, published experience regarding the use of MRgRT in pediatric patients is limited to two case reports. We report on the use of MRgRT for pediatric patients at our institution during a four-year period and describe important considerations in the selection and application of this technology in children. All patients treated with MRgRT since inception at our institution between 4/2018 and 4/2022 were retrospectively reviewed. We also evaluated all pediatric patients treated at our institution during the same period who received either imaging or treatment using our magnetic resonance-guided linear accelerator (MR Linac). We summarize four clinical cases where MRgRT was selected for treatment in our clinic, including disease outcomes and toxicities and describe our experience using the MR Linac for imaging before and during treatment for image fusion and tumor assessments. Between 4/2018 and 4/2022, 535 patients received MRgRT at our center, including 405 (75.7%) with stereotactic ablative radiotherapy (SABR). During this period, 347 distinct radiotherapy courses were delivered to pediatric patients, including 217 (62.5%) with proton therapy. Four pediatric patients received MRgRT. One received SABR for lung metastasis with daily adaptive replanning and a second was treated for liver metastasis using a non-adaptive workflow. Two patients received fractionated MRgRT for an ALK-rearranged non-small cell lung cancer and neuroblastoma. No Grade 2 or higher toxicities were observed or reported during MRgRT or subsequent follow-up. Twelve patients underwent MR imaging without contrast during treatment for brain tumors to assess for tumor/cystic changes. Two patients treated with other modalities underwent MR simulation for target volume delineation and organ at risk sparing due to anatomic changes during treatment or unexpected delays in obtaining diagnostic MR appointments. In four pediatric patients treated with MRgRT, treatment was well tolerated with no severe acute effects. At our center, most pediatric patients are treated with proton therapy, but the cases selected for MRgRT demonstrated significant organ at risk sparing compared to alternative modalities. In particular, MRgRT may provide advantages for thoracic/abdominal/pelvic targets using gated delivery and adaptive replanning, but selected patients treated with fractionated radiotherapy may also benefit MRgRT through superior organ at risk sparing.

Interobserver variation in clinical target volume (CTV) delineation for stereotactic radiotherapy to non-spinal bone metastases in prostate cancer: CT, MRI and PET/CT fusion

Background and purposeThe use of SBRT for the treatment of oligometastatic prostate cancer is increasing rapidly. While consensus guidelines are available for non-spinal bone metastases practice continues to vary widely. The aim of this study is to look at inter-observer variability in the contouring of prostate cancer non-spinal bone metastases with different imaging modalities. Materials and methods15 metastases from 13 patients treated at our centre were selected. 4 observers independently contoured clinical target volumes (CTV) on planning CT alone, planning CT with MRI fusion, planning CT with PET-CT fusion and planning CT with both MRI and PET-CT fusion combined. The mean inter-observer agreement on each modality was compared by measuring the delineated volume, generalized conformity index (CIgen), and the distance of the centre of mass (dCOM), calculated per metastasis and imaging modality. ResultsMean CTV volume delineated on planning CT with MRI and PET-CT fusion combined was significantly larger compared to other imaging modalities (p = 0.0001). CIgen showed marked variation between modalities with the highest agreement between planning CT + PET-CT (mean CIgen 0.55, range 0.32–0.73) and planning CT + MRI + PET-CT (mean CIgen 0.59, range 0.34–0.73). dCOM showed small variations between imaging modalities but a significantly shorter distance found on planning CT + PET-CT when compared with planning CT + PET-CT + MRI combined (p = 0.03). ConclusionsHighest consistency in CTV delineation between observers was seen with planning CT + PET-CT and planning CT + PET-CT + MRI combined.

Variability of radiotherapy volume delineation: PSMA PET/MRI and MRI based clinical target volume and lymph node target volume for high-risk prostate cancer

PurposeA comparative retrospective study to assess the impact of PSMA Ligand PET/MRI ([68 Ga]-Ga-PSMA-11 and [18F]-F-PSMA-1007 PET/MRI) as a new method of target delineation compared to conventional imaging on whole-pelvis radiotherapy for high-risk prostate cancer (PCa).Patients and methodsForty-nine patients with primary high-risk PCa completed the whole-pelvis radiotherapy plan based on PSMA PET/MRI and MRI. The primary endpoint compared the size and overlap of clinical target volume (CTV) and nodal gross tumour volume (GTVn) based on PSMA PET/MRI and MRI. The diagnostic performance of two methods for pelvic lymph node metastasis (PLNM) was evaluated.ResultsIn the radiotherapy planning for high-risk PCa patients, there was a significant correlation between MRI-CTV and PET/MRI-CTV (P = 0.005), as well as between MRI-GTVn and PET/MRI-GTVn (P < 0.001). There are non-significant differences in the CTV and GTVn based on MRI and PET/MRI images (P = 0.660, P = 0.650, respectively). The conformity index (CI), lesion coverage factor (LCF) and Dice similarity coefficient (DSC) of CTVs were 0.999, 0.953 and 0.954. The CI, LCF and DSC of GTVns were 0.927, 0.284, and 0.32. Based on pathological lymph node analysis of 463 lymph nodes from 37 patients, the sensitivity, specificity of PET/MRI in the diagnosis of PLNM were 77.78% and 99.76%, respectively, which were higher than those of MRI (P = 0.011). Eight high-risk PCa patients who finished PSMA PET/MRI changed their N or M stage.ConclusionThe CTV delineated based on PET/MRI and MRI differ little. The GTVn delineated based on PET/MRI encompasses metastatic pelvic lymph nodes more accurately than MRI and avoids covering pelvic lymph nodes without metastasis. We emphasize the utility of PET/MRI fusion images in GTVn delineation in whole pelvic radiotherapy for PCa. The use of PSMA PET/MRI aids in the realization of more individual and precise radiotherapy for PCa.

DWI-MR and PET-CT Functional Imaging for Boost Tumor Volume Delineation in Neoadjuvant Rectal Cancer Treatment.

T2 weighted magnetic resonance (MR) imaging is the gold standard for locally advanced rectal cancer (LARC) staging. The potential benefit of functional imaging, as diffusion-weighted MR (DWI) and positron emission tomography-computed tomography (PET-CT), could be considered for treatment intensification strategies. Dose intensification resulted in better pathological complete response (pCR) rates. This study evaluated the inter-observer agreement between two radiation oncologists, and the difference in gross tumor volume (GTV) delineation in simulation-CT, T2-MR, DWI-MR, and PET-CT in patients with LARC. Two radiation oncologists prospectively delineated GTVs of 24 patients on simul-CT (CTGTV), T2-weighted MR (T2GTV), echo planar b1000 DWI (DWIGTV) and PET-CT (PETGTV). Observers' agreement was assessed using Dice index. Kruskal-Wallis test assessed differences between methods. Mean CTGTV, T2GTV, DWIGTV, and PETGTV were 41.3±26.9 cc, 25.9±15.2 cc, 21±14.8 cc, and 37.7±27.7 cc for the first observer, and 42.2±27.9 cc, 27.6±16.9 cc, 19.9±14.9cc, and 34.8±24.3 cc for the second observer, respectively. Mean Dice index was 0.85 for CTGTV, 0.84 for T2GTV, 0.82 for DWIGTV, and 0.89 for PETGTV, representative of almost perfect agreement. Kruskal-Wallis test showed a statistically significant difference between methods (p=0.009). Dunn test showed there were differences between DWIGTV vs. PETGTV (p=0.040) and DWIGTV vs. CTGTV (p=0.008). DWI resulted in smaller volume delineation compared to CT, T2-MR, and PET-CT functional images. Almost perfect agreements were reported for each imaging modality between two observers. DWI-MR seems to remain the optimal strategy for boost volume delineation for dose escalation in patients with LARC.