Delineation Of Gross Tumor Volume Research Articles

Saliency-Guided Deep Learning Network for Automatic Target Delineation in Post-Operative Stereotactic Partial Breast Irradiation

<h3>Purpose/Objective(s)</h3> To accommodate an efficient clinical workflow in partial breast irradiation (PBI), fast, accurate and automated target delineation is desired. In this study, we develop a saliency-based deep learning segmentation (SDL-Seg) algorithm by incorporating prior domain knowledge for automatic gross tumor volume (GTV) delineation in post-op breast irradiation. <h3>Materials/Methods</h3> Our approach incorporates saliency information into a deep learning model U-Net for target delineation. The level of saliency of image regions are described as how likely that region would attract physicians' visual attention. The visual saliency maps were generated using the surgical clip's location identified on CT images. A distance-transformation coupled with a Gaussian filter were then adopted to convert markers' locations to probability maps. The CT images and the corresponding probability maps form a two-channel input for the first convolution layer of the segmentation network. Such design forces the model to encode the location-related features guiding the network to focus on regions with high saliency levels and suppresses low saliency regions. The dataset used for model training, validation and testing (19:5:5) is comprised of 145 prone CT images from 29 post-operative breast cancer patients, who had implanted markers and received 5-fraction PBI regimen on GammaPod. We used the Dice similarity coefficient (DSC), 95 percentile Hausdorff distance (HD95) and average symmetric surface distance (ASD) to assess segmentation results by SDL-Seg and compared it with those generated by basic U-Net. <h3>Results</h3> Our model achieves mean (standard deviation) of 76.4% (2.7%), 6.76 (1.83) mm, and 1.9 (0.66) mm for DSC, HD95, and ASD, respectively, outperforming basic U-Net by 13.8%, 1.63 mm, and 0.9 mm. For all 5 testing cases, the saliency-guided U-Net showed increased DSC compared to basic U-Net. Table1, demonstrates the DSC results for 5 test cases using our SDL-Seg and basic U-Net. <h3>Conclusion</h3> We developed a deep learning model integrating visual saliency information into the network for GTV delineation. Results demonstrate that SDL-Seg outperforms basic U-Net and is a promising approach for efficient and accurate target delineation in PBI. Such real-time delineation tool is highly desired by the on-line treatment planning workflow, such as GammaPod.

P29.05 Gross Tumor Volume Contouring Variations in Radiation Therapy of Non-Small Cell Lung Cancer

Accurate delineation of gross tumor volume (GTV) is utmost important for precision radiation therapy and quality ensure of GTV compliance with the protocol definition is essential for multi-center clinical trials. This work aimed to exam GTV delineation by multicenter experts and quantifies the differences in the same one patient with stage III non-small cell lung cancer (NSCLC).

Prognostic Relevance of 18F-FDG-PET/CT-Guided Target Volume Delineation in Loco-Regionally Advanced Nasopharyngeal Carcinomas: A Comparative Study.

IntroductionAn optimal approach to define tumor volume in locoregionally advanced nasopharyngeal carcinoma (NPC) using 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) remains unclear. This retrospective study aimed at comparing the outcomes and toxicities of different FDG-PET/CT-guided techniques for primary tumor volume delineation in locoregionally advanced NPC.MethodsFrom August 2015 to February 2018, 292 patients with stage III-IVB NPC received FDG-PET/CT-guided IMRT. Three PET/CT-based techniques were used to determine the gross tumor volume (GTV) as follows: visual criteria (group A; n = 98), a standard uptake value (SUV) threshold of 2.5 (group B; n = 95), and a threshold of 50% maximal intensity (group C, n = 99) combined with a dose-painting technique.ResultsIn groups A, B, and C, the 5-year LRFS rates were 89.4%, 90.0%, and 97.8%, respectively (p = 0.043). The 5-year DMFS rates were 75.1%, 76.0%, and 87.7%, respectively (p = 0.043). The 5-year DFS rates were 70.9%, 70.3%, and 82.2%, respectively (p = 0.048). The 5-year OS rates were 73.5%, 73.9%, and 84.9%, respectively (p = 0.038). Group C showed significantly higher 5-year LRFS, LRRFS, DMFS, DFS, and OS than those in groups A and B (p < 0.05). No statistically significant differences were observed between the three study groups in the cumulative incidences of grade 3-4 acute and late toxicities. Multivariate analyses showed that the PET/CT-guided technique for target volume delineation was an independent prognostic factor for 5-year LRFS, DFS, DMFS, and OS (p = 0.039, p = 0.030, p = 0.035 and p = 0.028, respectively), and was marginally significant in predicting LRRFS (p = 0.080).ConclusionsThe 50% SUVmax threshold regimen for GTV delineation with dose-painting appeared to be superior to the visual criteria or SUV2.5 threshold in locoregionally advanced NPC, and there was no increased toxicity.

Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck tumor segmentation

Background Manual delineation of gross tumor volume (GTV) is essential for radiotherapy treatment planning, but it is time-consuming and suffers inter-observer variability (IOV). In clinics, CT, PET, and MRI are used to inform delineation accuracy due to their different complementary characteristics. This study aimed to investigate deep learning to assist GTV delineation in head and neck squamous cell carcinoma (HNSCC) by comparing various modality combinations. Materials and methods This retrospective study had 153 patients with multiple sites of HNSCC including their planning CT, PET, and MRI (T1-weighted and T2-weighted). Clinical delineations of gross tumor volume (GTV-T) and involved lymph nodes (GTV-N) were collected as the ground truth. The dataset was randomly divided into 92 patients for training, 31 for validation, and 30 for testing. We applied a residual 3 D UNet as the deep learning architecture. We independently trained the UNet with four different modality combinations (CT-PET-MRI, CT-MRI, CT-PET, and PET-MRI). Additionally, analogical to post-processing, an average fusion of three bi-modality combinations (CT-PET, CT-MRI, and PET-MRI) was produced as an ensemble. Segmentation accuracy was evaluated on the test set, using Dice similarity coefficient (Dice), Hausdorff Distance 95 percentile (HD95), and Mean Surface Distance (MSD). Results All imaging combinations including PET provided similar average scores in range of Dice: 0.72-0.74, HD95: 8.8-9.5 mm, MSD: 2.6-2.8 mm. Only CT-MRI had a lower score with Dice: 0.58, HD95: 12.9 mm, MSD: 3.7 mm. The average of three bi-modality combinations reached Dice: 0.74, HD95: 7.9 mm, MSD: 2.4 mm. Conclusion Multimodal deep learning-based auto segmentation of HNSCC GTV was demonstrated and inclusion of the PET image was shown to be crucial. Training on combined MRI, PET, and CT data provided limited improvements over CT-PET and PET-MRI. However, when combining three bimodal trained networks into an ensemble, promising improvements were shown.

Fully Automated Gross Tumor Volume Delineation From PET in Head and Neck Cancer Using Deep Learning Algorithms.

The availability of automated, accurate, and robust gross tumor volume (GTV) segmentation algorithms is critical for the management of head and neck cancer (HNC) patients. In this work, we evaluated 3 state-of-the-art deep learning algorithms combined with 8 different loss functions for PET image segmentation using a comprehensive training set and evaluated its performance on an external validation set of HNC patients. 18F-FDG PET/CT images of 470 patients presenting with HNC on which manually defined GTVs serving as standard of reference were used for training (340 patients), evaluation (30 patients), and testing (100 patients from different centers) of these algorithms. PET image intensity was converted to SUVs and normalized in the range (0-1) using the SUVmax of the whole data set. PET images were cropped to 12 × 12 × 12 cm3 subvolumes using isotropic voxel spacing of 3 × 3 × 3 mm3 containing the whole tumor and neighboring background including lymph nodes. We used different approaches for data augmentation, including rotation (-15 degrees, +15 degrees), scaling (-20%, 20%), random flipping (3 axes), and elastic deformation (sigma = 1 and proportion to deform = 0.7) to increase the number of training sets. Three state-of-the-art networks, including Dense-VNet, NN-UNet, and Res-Net, with 8 different loss functions, including Dice, generalized Wasserstein Dice loss, Dice plus XEnt loss, generalized Dice loss, cross-entropy, sensitivity-specificity, and Tversky, were used. Overall, 28 different networks were built. Standard image segmentation metrics, including Dice similarity, image-derived PET metrics, first-order, and shape radiomic features, were used for performance assessment of these algorithms. The best results in terms of Dice coefficient (mean ± SD) were achieved by cross-entropy for Res-Net (0.86 ± 0.05; 95% confidence interval [CI], 0.85-0.87), Dense-VNet (0.85 ± 0.058; 95% CI, 0.84-0.86), and Dice plus XEnt for NN-UNet (0.87 ± 0.05; 95% CI, 0.86-0.88). The difference between the 3 networks was not statistically significant (P > 0.05). The percent relative error (RE%) of SUVmax quantification was less than 5% in networks with a Dice coefficient more than 0.84, whereas a lower RE% (0.41%) was achieved by Res-Net with cross-entropy loss. For maximum 3-dimensional diameter and sphericity shape features, all networks achieved a RE ≤ 5% and ≤10%, respectively, reflecting a small variability. Deep learning algorithms exhibited promising performance for automated GTV delineation on HNC PET images. Different loss functions performed competitively when using different networks and cross-entropy for Res-Net, Dense-VNet, and Dice plus XEnt for NN-UNet emerged as reliable networks for GTV delineation. Caution should be exercised for clinical deployment owing to the occurrence of outliers in deep learning-based algorithms.

Evaluation of Hybrid PET/MRI for Gross Tumor Volume (GTV) Delineation in Colorectal Cancer Liver Metastases Radiotherapy.

PurposeHybrid PET/MRI has been increasingly incorporated into the practice of radiation oncologists since it contains both anatomical and biological data and may bring about personalized radiation plans for each patient. The objective of this study was to evaluate the feasibility of GTV delineation from hybrid PET/MRI compared with that from current-practice MRI during radiotherapy planning in patients with colorectal liver metastases.Patients and MethodsTwenty-four patients (thirty lesions) with colorectal liver metastases were prospectively enrolled in this study. Three physicians delineated the target volume with the most popular delineating methods—the visual method. First of all, differences among the three observers were assessed. The difference and correlation of GTV values obtained by MRI, PET, and hybrid PET/MRI were subjected to statistical analysis afterwards. Finally, the dice similarity coefficient (DSC) was calculated to assess the spatial overlap. Based on the value of DSC, we also evaluate the correlation between DSC and tumor size. GTV-MRI was set as a reference.ResultsThere was no significant difference among observers in GTV-MRI (F=0.118, p=0.889), GTV-PET (F=0.070, p=0.933) and GTV-PET/MRI (F=0.40, p=0.961). 83.33% of GTV-PET/MRI and 63.33% of GTV-PET were larger than the reference GTV-MRI. Statistical analysis revealed that GTV-PET/MRI (p<0.001) and GTV-PET (p<0.05) diverged statistically significantly from GTV-MRI. GTV-PET (r=0.992, p<0.001) and GTV-PET/MRI (r=0.997, p<0.001) were significantly related to GTV-MRI. The average DSC value between GTV-MRI and GTV-PET was 0.51 (range 0–0.90) and that between GTV-MRI and GTV-PET/MRI was 0.72 (range 0.42–0.90). There was a positive correlation between the DSC and GTV-MRI (r=0.851, p<0.05).ConclusionWith the database used, there is good agreement among observers. Hybrid PET/MRI in colorectal liver metastases radiotherapy may affect the GTV delineation. Moreover, the overlap degree between GTV-MRI and GTV-PET/MRI is higher and increases with volume.

A comparison of methods for fully automatic segmentation of tumors and involved nodes in PET/CT of head and neck cancers

Target volume delineation is a vital but time-consuming and challenging part of radiotherapy, where the goal is to deliver sufficient dose to the target while reducing risks of side effects. For head and neck cancer (HNC) this is complicated by the complex anatomy of the head and neck region and the proximity of target volumes to organs at risk. The purpose of this study was to compare and evaluate conventional PET thresholding methods, six classical machine learning algorithms and a 2D U-Net convolutional neural network (CNN) for automatic gross tumor volume (GTV) segmentation of HNC in PET/CT images. For the latter two approaches the impact of single versus multimodality input on segmentation quality was also assessed. 197 patients were included in the study. The cohort was split into training and test sets (157 and 40 patients, respectively). Five-fold cross-validation was used on the training set for model comparison and selection. Manual GTV delineations represented the ground truth. Tresholding, classical machine learning and CNN segmentation models were ranked separately according to the cross-validation Sørensen–Dice similarity coefficient (Dice). PET thresholding gave a maximum mean Dice of 0.62, whereas classical machine learning resulted in maximum mean Dice scores of 0.24 (CT) and 0.66 (PET; PET/CT). CNN models obtained maximum mean Dice scores of 0.66 (CT), 0.68 (PET) and 0.74 (PET/CT). The difference in cross-validation Dice between multimodality PET/CT and single modality CNN models was significant (p ≤ 0.0001). The top-ranked PET/CT-based CNN model outperformed the best-performing thresholding and classical machine learning models, giving significantly better segmentations in terms of cross-validation and test set Dice, true positive rate, positive predictive value and surface distance-based metrics (p ≤ 0.0001). Thus, deep learning based on multimodality PET/CT input resulted in superior target coverage and less inclusion of surrounding normal tissue.

Evaluation of interim MRI changes during limited-field radiation therapy for glioblastoma and implications for treatment planning

Background and purposeConsensus for defining gross tumor volume (GTV) and clinical target volume (CTV) for limited-field radiation therapy (LFRT) of GBM are not well established. We leveraged a department MRI simulator to image patients before and during LFRT to address these questions. Materials and methodsSupratentorial GBM patients receiving LFRT (46 Gy + boost to 60 Gy) underwent baseline MRI (MRI1) and interim MRI during RT (MRI2). GTV1 was defined as T1 enhancement + surgical cavity on MRI1 without routine inclusion of T2 abnormality (unless tumor did not enhance). The initial CTV margin was 15 mm from GTV1, and the boost CTV margin was 5–7 mm. The GTV1 characteristics were categorized into three groups: identical T1 and T2 abnormality (Group A), T1 only with larger T2 abnormality not included (Group B), and T2 abnormality when tumor lacked enhancement (Group C). GTV2 was contoured on MRI2 and compared with GTV1 plus 5–15 mm expansions. ResultsAmong 120 patients treated from 2014-2019, 29 patients (24%) underwent replanning based on MRI2. On MRI2, 84% of GTV2 were covered by GTV1 + 5 mm, 93% by GTV1 + 7 mm, and 98% by GTV1 + 15 mm. On MRI1, 43% of GTV1 could be categorized into Group A, 39% Group B, and 18% Group C. Group B’s patterns of failure, local control, or progression-free survival were similar to Group A/C. ConclusionsInitial CTV margin of 15 mm followed by a boost CTV margin of 7 mm is a reasonable approach for LFRT of GBM. Omitting routine inclusion of T2 abnormality from GTV delineation may not jeopardize disease control.

Inter-observer agreement of computed tomography and magnetic resonance imaging on gross tumor volume delineation of intrahepatic cholangiocarcinoma: an initial study.

Intrahepatic cholangiocarcinoma (ICC) is the second most common primary liver tumor, and local radiotherapy has a positive effect on patients with an unresectable tumor. Accurate delineation of gross tumor volume (GTV) is crucial to improve the efficacy of radiotherapy. The purpose of this article was to evaluate the consistency of CT, diffusion weighted imaging (DWI) and Gadoxetic acid disodium (Gd-EOB-DTPA)-enhanced MRI on GTV delineation of ICC. Fourteen patients with ICC underwent CT (Plain and Portal, CT scans before and 70 s after the injection of Omnipaque, respectively), DWI, and Gd-EOB-DTPA-enhanced MRI (EOB 70 s and EOB 15 min, mDIXON scans at 70 s and 15 min after the injection of Gd-EOB-DTPA, respectively) examinations before radiotherapy. Volumes of GTV delineation on CT and MRI images were recorded. Dice similarity coefficient (DSC) was calculated to evaluate the spatial overlap. Tumor volume on DWI and EOB 15 min were larger than that on EOB 70 s significantly (both P=0.004). DSC of DWI was significantly larger than that of other CT and MRI sequences (all P≤0.002). DSC of EOB 15 min tended to be larger than that of other CT sequences and EOB 70 s, however, without significances (all P>0.005). Significant correlation was found between DSC and tumor volume (R=0.35, P=0.003). DWI had significantly higher agreement on GTV delineation of ICC. GTV delineations of ICC on Gd-EOB-DTPA-enhanced MRI showed excellent inter-observer agreement. Fusion of CT and MRI images should be considered to improve the accuracy of GTV delineation.

Volumetric and dosimetric impact of MRI in delineation of gross tumor volume of non-spinal vertebral metastases treated with stereotactic ablative radiation therapy

PurposeTo investigate the Gross Tumor Volumes (GTV) and its dosimetric impact of magnetic resonance imaging (MRI) assisted contouring for non-spinal metastasis treated with stereotactic ablative body radiotherapy (SABR). Material and methodsFive observer contours on CT (GTVCT) and CT+MR (GTVCT+MR) were evaluated against expert team contours (GTVEC) for 14 selected cases. Dice Similarity Index (DSC) and Geographical Miss Index (GMI) quantify observer variation. We also analyze the maximum dose (Dmax) and dose received by 0.35cc (D0.35cc) of the spinal cord (SC) for GTVCT and GTVCT+MR, where optimization parameters and priorities were unchanged. Percent rank function is also evaluated for SC doses. ResultsThe mean DSC and GMI scores for the CT-only dataset are 0.6974 and 0.2851 and for CT+MR dataset is 0.7764 and 0.1907 respectively. Statistically, significant results were found for mean GTV volumes between GTVEC versus GTVCT and GTVCT versus GTVCT+MR (P<0.001). Dosimetric analysis of Dmax and D0.35cc exceeded 84.2% and 88.5% of times its respective threshold doses for CT-only dataset, whereas for the CT+MR dataset, it exceeded only by 18% and 15.7% times. ‘Percent rank’ function analysis for SC doses also indicates the same. ConclusionThis study supports MRI fusion for GTV and OAR delineation for non-spinal metastasis. Our study showed that the dosimetric analysis is vital for observer variation studies and the addition of the MR data set is significant to improve the confidence of Stereotactic treatments.

Optimal Standardized Uptake Value Threshold for Auto contouring of Gross Tumor Volume using Positron Emission Tomography/Computed Tomography in Patients with Operable Nonsmall-Cell Lung Cancer: Comparison with Pathological Tumor Size.

Purpose:Incorporating 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG-PET/CT) for gross tumor volume (GTV) delineation is challenging due to varying tumor edge based on the set threshold of the standardized uptake value (SUV). This study aims to determine an optimal SUV threshold that correlates best with the pathological tumor size.Materials and Methods:From January 2013 to July 2014, 25 consecutive patients of operable nonsmall-cell lung cancer (NSCLC) who underwent staging18F-FDG-PET/CT before surgical resection were included in the test cohort and 12 patients in the validation cohort. GTVs were delineated on the staging PET/CT by automatic delineation using various percentage threshold of maximum SUV (SUVmax) and absolute SUV. The maximum pathological tumor diameter was then matched with the maximum auto-delineated tumor diameter with varying SUV thresholds. First-order linear regression and Bland–Altman plots were used to obtain an optimal SUV threshold for each patient. Three radiation oncologists with varying degrees of experiences also delineated GTVs with the visual aid of PET/CT to assess interobserver variation in delineation.Results:In the test set, the mean optimal percentage threshold for GTV was SUVmax of 35.6%±18.6% and absolute SUV of 4.35 ± 1.7. In the validation set, the mean optimal percentage threshold SUV and absolute SUV were 36.9 ± 16.9 and 4.1 ± 1.6, respectively. After a combined analysis of all 37 patients, the mean optimal threshold was 36% ± 17.9% and 4.27 ± 1.7, respectively. Using Bland–Altman plots, auto-contouring with 40% SUVmax and SUV 4 was in greater agreement with the pathological tumor diameter.Conclusion:Automatic GTV delineation on PETCT in NSCLC with percentage threshold SUV of 40% and absolute SUV of 4 correlated best with pathological tumor size. Auto-contouring using these thresholds will increase the precision of radiotherapy contouring of GTV and will save time.

Radiomics AI prediction for head and neck squamous cell carcinoma (HNSCC) prognosis and recurrence with target volume approach.

Objectives:To evaluate the performance of radiomics features extracted from planning target volume (PTV) and gross tumor volume (GTV) in the prediction of the death prognosis and cancer recurrence rate for head and neck squamous cell carcinoma (HNSCC).Methods:188 HNSCC patients’ planning CT images with radiotherapy structures sets were acquired from Cancer Imaging Archive (TCIA). The 3D slicer (v. 4.10.2) with the PyRadiomics extension (Computational Imaging and Bioinformatics Lab, Harvard medical School) was used to extract radiomics features from the radiotherapy planning images. An in-house developed deep learning artificial neural networks (DL-ANN) model was used to predict death prognosis and cancer recurrence rate based on the features extracted from GTV and PTV of the CT images.Results:The PTV radiomics features with DL-ANN model could achieve 77.7% accuracy with overall AUC equal to 0.934 and 0.932 when predicting HNSCC-related death prognosis and cancer recurrence respectively. Furthermore, the DL-ANN model can achieve an accuracy of 74.3% with AUC equal to 0.947 and 0.956 for the HNSCC-related death prognosis and cancer recurrence respectively using GTV features.Conclusion:Using both GTV and PTV radiomics features in the DL-ANN model, can aid in predicting HNSCC-related death prognosis and cancer recurrence. Clinicians may find it helpful in formulating different treatment regimens and facilitate personized medicine based on the predicted outcome when performing GTV and PTV delineation.Advances in knowledge:Radiomics features of GTV and PTV are reliable prognosis and recurrence predicting tools, which may help clinicians in GTV and PTV delineation to facilitate delivery of personalized treatment.

Automated gross tumor volume contour generation for large-scale analysis of early-stage lung cancer patients planned with 4D-CT.

PurposePatients with early‐stage lung cancer undergoing stereotactic ablative radiotherapy receive four‐dimensional computed tomography (4D‐CT) for treatment planning. Often, an internal gross target volume (iGTV), which approximates the motion envelope of a tumor over the breathing cycle, is delineated without defining a gross tumor volume (GTV). However, the GTV volume and shape are important parameters for prognostic and dose modelling, and there is interest in radiomic features extracted from the GTV and surrounding tissue. We demonstrate and validate a method to generate the GTV from an iGTV contour to aid retrospective analysis on routine data.MethodIt is possible to reconstruct the geometry of a tumor with knowledge of tumor motion and the motion envelope formed during respiration. To demonstrate this, the tumor motion path was estimated with local rigid registration, and the iGTV positioned incrementally at stations along the reverse path. It is shown that the tumor volume is the largest set common to the intersection of the iGTV at these positions, hence can be derived. This was implemented for 521 lung lesions on 4D‐CT. Eleven patients with a GTV delineation performed by a radiation oncologist on a reference phase (50%) were used for validation. The generated GTV was compared to that delineated by the expert using distance‐to‐agreement (DTA), volume, and distance between centres of mass. An overall success rate was determined by detecting registration inaccuracy and performing a quality check on the routine iGTV. For successfully generated contours, GTV volume was compared to iGTV volume in a prognostic model for overall survival.ResultsFor the validation dataset, DTA mean (0.79 – 1.55 mm) and standard deviation (0.68 – 1.51 mm) were comparable to expected observer variation. Difference in volume was < 5 cm3, and average difference in position was 1.21 mm. Deviations in shape and position were mainly caused by observer differences in iGTV and GTV interpretation as opposed to algorithm performance. For the complete dataset, an acceptable contour was generated for 94% of patients using statistical and visual assessment to detect failures. Generated GTV volumes improved prognostic model performance over iGTV volumes.ConclusionA method to generate a GTV from an iGTV and 4D‐CT dataset was developed. This method facilitates data analysis of patients with early‐stage lung cancer treated in the routine setting, that is, data mining, prognostic modeling, and radiomics. Generation failure detection removes the need for visual assessment of all contours, reducing a time‐consuming aspect of big‐data analysis. Favorable prognostic performance of generated GTV volumes over iGTV ones demonstrates opportunities to use this methodology for future study.

Intraprostatic Tumor Segmentation on PSMA PET Images in Patients with Primary Prostate Cancer with a Convolutional Neural Network.

Accurate delineation of the intraprostatic gross tumor volume (GTV) is a prerequisite for treatment approaches in patients with primary prostate cancer (PCa). Prostate-specific membrane antigen PET (PSMA PET) may outperform MRI in GTV detection. However, visual GTV delineation underlies interobserver heterogeneity and is time consuming. The aim of this study was to develop a convolutional neural network (CNN) for automated segmentation of intraprostatic tumor (GTV-CNN) in PSMA PET. Methods: The CNN (3D U-Net) was trained on the 68Ga-PSMA PET images of 152 patients from 2 different institutions, and the training labels were generated manually using a validated technique. The CNN was tested on 2 independent internal (cohort 1: 68Ga-PSMA PET, n = 18 and cohort 2: 18F-PSMA PET, n = 19) and 1 external (cohort 3: 68Ga-PSMA PET, n = 20) test datasets. Accordance between manual contours and GTV-CNN was assessed with the Dice-Sørensen coefficient (DSC). Sensitivity and specificity were calculated for the 2 internal test datasets (cohort 1: n = 18, cohort 2: n = 11) using whole-mount histology. Results: The median DSCs for cohorts 1-3 were 0.84 (range: 0.32-0.95), 0.81 (range: 0.28-0.93), and 0.83 (range: 0.32-0.93), respectively. Sensitivities and specificities for the GTV-CNN were comparable with manual expert contours: 0.98 and 0.76 (cohort 1) and 1 and 0.57 (cohort 2), respectively. Computation time was around 6 s for a standard dataset. Conclusion: The application of a CNN for automated contouring of intraprostatic GTV in 68Ga-PSMA and 18F-PSMA PET images resulted in a high concordance with expert contours and in high sensitivities and specificities in comparison with histology as a reference. This robust, accurate and fast technique may be implemented for treatment concepts in primary prostate cancer. The trained model and the study's source code are available in an open source repository.

F18] FDG-PET/CT for manual or semiautomated GTV delineation of the primary tumor for radiation therapy planning in patients with esophageal cancer: is it useful?

BackgroundTarget volume definition of the primary tumor in esophageal cancer is usually based on computed tomography (CT) supported by endoscopy and/or endoscopic ultrasound and can be difficult given the low soft-tissue contrast of CT resulting in large interobserver variability. We evaluated the value of a dedicated planning [F18] FDG-Positron emission tomography/computer tomography (PET/CT) for harmonization of gross tumor volume (GTV) delineation and the feasibility of semiautomated structures for planning purposes in a large cohort.MethodsPatients receiving a dedicated planning [F18] FDG-PET/CT (06/2011–03/2016) were included. GTV was delineated on CT and on PET/CT (GTVCT and GTVPET/CT, respectively) by three independent radiation oncologists. Interobserver variability was evaluated by comparison of mean GTV and mean tumor lengths, and via Sørensen–Dice coefficients (DSC) for spatial overlap. Semiautomated volumes were constructed based on PET/CT using fixed standardized uptake values (SUV) thresholds (SUV30, 35, and 40) or background- and metabolically corrected PERCIST-TLG and Schaefer algorithms, and compared to manually delineated volumes.Results45 cases were evaluated. Mean GTVCT and GTVPET/CT were 59.2/58.0 ml, 65.4/64.1 ml, and 60.4/59.2 ml for observers A–C. No significant difference between CT- and PET/CT-based delineation was found comparing the mean volumes or lengths. Mean Dice coefficients on CT and PET/CT were 0.79/0.77, 0.81/0.78, and 0.8/0.78 for observer pairs AB, AC, and BC, respectively, with no significant differences. Mean GTV volumes delineated semiautomatically with SUV30/SUV35/SUV40/Schaefer’s and PERCIST-TLG threshold were 69.1/23.9/18.8/18.6 and 70.9 ml. The best concordance of a semiautomatically delineated structure with the manually delineated GTVCT/GTVPET/CT was observed for PERCIST-TLG.ConclusionWe were not able to show that the integration of PET/CT for GTV delineation of the primary tumor resulted in reduced interobserver variability. The PERCIST-TLG algorithm seemed most promising compared to other thresholds for further evaluation of semiautomated delineation of esophageal cancer.

Interfraction Tumor Change During Stereotactic Radiotherapy For Large Brain Metastases And Importance Of Treatment Plan Modification During Treatment Period

We aimed to evaluate the magnetic resonance imaging (MRI) appearance changes during stereotactic radiotherapy (SRT) for large sized brain metastases, and analyze the lesions necessitating treatment plan modification. A total of 23 patients (27 lesions, >2 cm in tumor diameter) underwent SRT and all lesions were evaluated the appearance changes which had the necessity of the treatment plan modification. The prescribed dose and fraction were chosen based on the size of brain metastasis: for lesions between 2.1 and 3 cm or 5.1 and 10 cc, the total dose was 35 Gy in 5 fractions, and between 3.1 and 4 cm or 10.1 and 30 cc, the total dose was 40 Gy in 8 fractions. The dose was prescribed with the 80% isodose line covering the planning target volume (PTV). Usually, our plans were normalized so that PTV D95 or D98 was equal to the prescribed dose, and gross tumor volume (GTV) D99 (dose that covers 99% of the GTV) was planned to be more than 110% of the prescribed dose. The appearance change of tumor during SRT was evaluated using gadolinium-enhanced MRI. Usually, we conducted Gd-MRI for the evaluation and modification before or after 4th treatment. The reasons of the modification were classified into tumor reduction, tumor enlargement, displacement, and shape change. Tumor reduction was defined as a ≥1 mm reduction in the maximum tumor diameter and ≥10% reduction in the tumor volume on T1-weighted MRI during treatment period. Tumor enlargement was defined as a ≥1 mm enlargement in the tumor diameter in each direction and ≥10% enlargement in the tumor volume on T1-weighted MRI. Displacement was defined as a ≥1 mm shift of center of PTV except tumor reduction and tumor enlargement. Shape change was defined as a slightly change of GTV delineation that caused the decreased GTV D99 except the cases of tumor reduction, tumor enlargement, and displacement. Univariate analyses using the χ2 test were performed to determine the statistical significance of differences between lesions with and those without the modification. Among the 27 lesions, 55.6% required the treatment plan modification. The reasons were tumor reduction in 6 lesions, tumor enlargement in 3 lesions, displacement in 3 lesions, and shape change in 3 lesions. The planning target volume (PTV) size changed up to 43.0% and the shift of center of PTV was a maximum of 1.7 mm. The pathological status (adenocarcinoma vs others) and timing of steroid administration (prior vs after SRT start) were the predictive factors of tumor changes required the modification. As tumor changes might occur even during short period of SRT, the treatment plan evaluation and modification were important in SRT for large brain metastases.

Exploring MRI based radiomics analysis of intratumoral spatial heterogeneity in locally advanced nasopharyngeal carcinoma treated with intensity modulated radiotherapy.

BackgroundWe hypothesized that spatial heterogeneity exists between recurrent and non-recurrent regions within a tumor. The aim of this study was to determine if there is a difference between radiomics features derived from recurrent versus non recurrent regions within the tumor based on pre-treatment MRI.MethodsA total of 14 T4NxM0 NPC patients with histologically proven “in field” recurrence in the post nasal space following curative intent IMRT were included in this study. Pretreatment MRI were co-registered with MRI at the time of recurrence for the delineation of gross tumor volume at diagnosis(GTV) and at recurrence(GTVr). A total of 7 histogram features and 40 texture features were computed from the recurrent(GTVr) and non-recurrent region(GTV-GTVr). Paired t-tests and Wilcoxon signed-rank tests were carried out on the 47 quantified radiomics features.ResultsA total of 7 features were significantly different between recurrent and non-recurrent regions. Other than the variance from intensity-based histogram, the remaining six significant features were either from the gray-level size zone matrix (GLSZM) or the neighbourhood gray-tone difference matrix (NGTDM).ConclusionsThe radiomic features extracted from pre-treatment MRI can potentially reflect the difference between recurrent and non-recurrent regions within a tumor and has a potential role in pre-treatment identification of intra-tumoral radio-resistance for selective dose escalation.

Role of clip markers placed by endoscopic ultrasonography in contouring gross tumor volume for thoracic esophageal squamous cell carcinoma: one prospective study.

BackgroundWe aimed to analyze the value of metal clip markers guided and placed by endoscopic ultrasonography (EUS) in the delineation of gross tumor volume (GTV) for thoracic esophageal squamous cell carcinoma.MethodsFrom September 2016 to September 2018, patients with thoracic esophageal squamous cell carcinoma in Tianjin Medical University Cancer Institute and Hospital were recruited in the prospective trial, NCT02959385. They underwent titanium clips placement on tumor superior and inferior boundaries under EUS by a single expert endosonographer before radiotherapy computed tomography (CT) simulation. According to the clip markers, the reference GTVs were contoured by one experienced radiation oncologist. With the help of the Eclipse treatment planning system, clip markers on CT were concealed. Afterward, two other radiation oncologists with expertise in esophageal cancer delineated GTVs, defined as conventional GTVs, based on endoscopy and barium radiography findings. The two GTVs were compared and analyzed. Subgroup analysis was conducted in different T stage [early (T1 + T2) vs. advanced (T3 + T4)], focus location (upper vs. middle vs. lower segment), and tumor length (<5 vs. >5 cm) groups.ResultsThe trial recruited 55 patients with 60 thoracic esophageal cancer foci. A total of 111 titanium clips were guided and implanted by EUS. Before CT simulation, two titanium clips at two foci fell off. After the procedure, no case of intolerable esophageal pain, hemorrhage, or perforation occurred. Compared to reference GTVs’, discrepancies of conventional GTVs’ superior borders were 0.91±0.82 cm (P<0.001), while differences of inferior borders were 0.74±0.63 cm (P<0.001). On the contrary, conventional GTVs’ lengths were not significantly different from reference GTVs’ with discrepancies 0.08±1.30 cm (P=0.64). Regardless of T stage, tumor location, and tumor length, conventional GTVs’ superior and inferior borders were significantly different from reference GTVs’, while GTVs’ lengths differed insignificantly.ConclusionsThis study confirmed that EUS-placed titanium clips could correct contouring of GTVs in thoracic esophageal cancer in different T stages, tumor locations, and lengths.

Gross tumour volume delineation in anal cancer on T2-weighted and diffusion-weighted MRI – Reproducibility between radiologists and radiation oncologists and impact of reader experience level and DWI image quality

PurposeTo assess how gross tumour volume (GTV) delineation in anal cancer is affected by interobserver variations between radiologists and radiation oncologists, expertise level, and use of T2-weighted MRI (T2W-MRI) vs. diffusion-weighted imaging (DWI), and to explore effects of DWI quality. Methods and materialsWe retrospectively analyzed the MRIs (T2W-MRI and b800-DWI) of 25 anal cancer patients. Four readers (Senior and Junior Radiologist; Senior and Junior Radiation Oncologist) independently delineated GTVs, first on T2W-MRI only and then on DWI (with reference to T2W-MRI). Maximum Tumour Diameter (MTD) was calculated from each GTV. Mean GTVs/MTDs were compared between readers and between T2W-MRI vs. DWI. Interobserver agreement was calculated as Intraclass Correlation Coefficient (ICC), Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD). DWI image quality was assessed using a 5-point artefact scale. ResultsInterobserver agreement between radiologists vs. radiation oncologists and between junior vs. senior readers was good–excellent, with similar agreement for T2W-MRI and DWI (e.g. ICCs 0.72–0.94 for T2W-MRI and 0.68–0.89 for DWI). There was a trend towards smaller GTVs on DWI, but only for the radiologists (P = 0.03–0.07). Moderate-severe DWI-artefacts were observed in 11/25 (44%) cases. Agreement tended to be lower in these cases. ConclusionOverall interobserver agreement for anal cancer GTV delineation on MRI is good for both radiologists and radiation oncologists, regardless of experience level. Use of DWI did not improve agreement. DWI artefacts affecting GTV delineation occurred in almost half of the patients, which may severely limit the use of DWI for radiotherapy planning if no steps are undertaken to avoid them.

Dosimetric impact of positron emission tomography-based gross tumour volume (GTV) delineation over conventional CT-based GTV delineation for carcinoma oesophagus

AbstractAim:The aim of the study was to find the dosimetric impact of positron emission tomography (PET)-based gross tumour volume (GTV) delineation over computed tomography (CT)-based GTV delineation for carcinoma oesophagus.Methods:Fifteen patients with carcinoma oesophagus were retrospectively selected. Two sets of GTVs in CT plain images were generated, one with the help of intravenous and oral contrast (GTV CT) and the other with only using PET uptake with the standardised uptake value (simple way of determining the activity in PET) (SUV) &gt; 2.5 (GTV PET). Corresponding PTVs were generated. For all patients, rapid arc plans were generated. Changes in target volumes and critical structure doses were evaluated. The Wilcoxon signed-rank test was used for statistical analysis, and p value &lt; 0.05 was assumed as statistically significant.Results:Mean reduction in GTV was 5.76 ± 19.35 cc. Mean reduction in PTV 45 Gy was 42.40 ± 76.39 cc. Mean reduction in heart mean dose was 1.53 ± 2.16 Gy. Mean reductions in left lung V20% and V10% were 2.43 ± 4.28 and 3.25 ± 5.09 Gy, respectively. Mean reductions in right lung V20% and V10% were 3.11 ± 4.91 and 2.80 ± 4.51 Gy, respectively. Mean reduction in total lung mean dose was 1.00 ± 1.19 Gy.Finding:PET-based GTV contouring reduces the treatment volume and critical structure doses significantly over CT-based GTV contouring for carcinoma oesophagus.