Delineation Of Gross Tumor Volume Research Articles

Amide proton transfer-weighted CEST MRI for radiotherapy target delineation of glioblastoma: a prospective pilot study

BackgroundExtensive glioblastoma infiltration justifies a 15-mm margin around the gross tumor volume (GTV) to define the radiotherapy clinical target volume (CTV). Amide proton transfer (APT)-weighted imaging could enable visualization of tumor infiltration, allowing more accurate GTV delineation. We quantified the impact of integrating APT-weighted imaging into GTV delineation of glioblastoma and compared two APT-weighted quantification methods—magnetization transfer ratio asymmetry (MTRasym) and Lorentzian difference (LD) analysis—for target delineation.MethodsNine glioblastoma patients underwent an extended imaging protocol prior to radiotherapy, yielding APT-weighted MTRasym and LD maps. From both maps, biological tumor volumes were generated (BTVMTRasym and BTVLD) and added to the conventional GTV to generate biological GTVs (GTVbio,MTRasym and GTVbio,LD). Wilcoxon signed-rank tests were performed for comparisons.ResultsThe GTVbio,MTRasym and GTVbio,LD were significantly larger than the conventional GTV (p ≤ 0.022), with a median volume increase of 9.3% and 2.1%, respectively. The GTVbio,MTRasym and GTVbio,LD were significantly smaller than the CTV (p = 0.004), with a median volume reduction of 72.1% and 70.9%, respectively. There was no significant volume difference between the BTVMTRasym and BTVLD (p = 0.074). In three patients, BTVMTRasym delineation was affected by elevated signals at the brain periphery due to residual motion artifacts; this elevation was absent on the APT-weighted LD maps.ConclusionLarger biological GTVs compared to the conventional GTV highlight the potential of APT-weighted imaging for radiotherapy target delineation of glioblastoma. APT-weighted LD mapping may be advantageous for target delineation as it may be more robust against motion artifacts.Relevance statementThe introduction of APT-weighted imaging may, ultimately, enhance visualization of tumor infiltration and eliminate the need for the substantial 15-mm safety margin for target delineation of glioblastoma. This could reduce the risk of radiation toxicity while still effectively irradiating the tumor.Trial registrationNCT05970757 (ClinicalTrials.gov).Key PointsIntegration of APT-weighted imaging into target delineation for radiotherapy is feasible.The integration of APT-weighted imaging yields larger GTVs in glioblastoma.APT-weighted LD mapping may be more robust against motion artifacts than APT-weighted MTRasym.Graphical

Intra-prostatic recurrences after radiotherapy with focal boost: Location and dose mapping in the FLAME trial

IntroductionThe FLAME trial demonstrated that the dose to the gross tumor volume (GTV) is associated with tumour control in prostate cancer patients. This raises the question if dose de-escalation to the remaining prostate gland can be considered. Therefore, we investigated if intraprostatic recurrences occur at the location of the GTV and which dose was delivered at that location. Materials and methodsFor FLAME trial patients with an intra-prostatic recurrence, we collected pre-treatment images, GTV delineations, dose distributions and post-recurrence images. Pre-treatment images were registered to the post-recurrence images (PSMA-PET CT). An overlap between GTV and PSMA-PET activity was considered an intra-prostatic recurrence at the location of the primary tumor. ResultsTwenty eight out of 535 patients in the FLAME trial had an intra-prostatic recurrence. Its location could be determined for 24 patients. One patient recurred in the prostate gland outside the GTV. The median D98% to the GTV was 76.5 Gy (range: 73.3–86.5 Gy). Only one patient with a recurrence in the GTV received a substantial focal boost of 86.5 Gy. The D98% of all remaining patients was < 81 Gy. ConclusionIntra-prostatic recurrences of intermediate- and high-risk prostate cancer patients treated with radiotherapy appeared predominantly at the location of the primary tumor. All but one patient did not receive a high dose to the GTV. Intra-prostatic failure is likely a consequence of the undertreatment of the primary tumor rather than the undertreatment of the remaining prostate gland.

Autodelineation of Treatment Target Volume for Radiation Therapy Using Large Language Model-Aided Multimodal Learning

PurposeArtificial intelligence (AI)-aided methods have made significant progress in the auto-delineation of normal tissues. However, these approaches struggle with the auto-contouring of radiotherapy target volume. Our goal is to model the delineation of target volume as a clinical decision-making problem, resolved by leveraging large language model-aided multimodal learning approaches. Methods and MaterialsA vision-language model, termed Medformer, has been developed, employing the hierarchical vision transformer as its backbone, and incorporating large language models to extract text-rich features. The contextually embedded linguistic features are seamlessly integrated into visual features for language-aware visual encoding through the visual language attention module. Metrics, including Dice similarity coefficient (DSC), intersection over union (IOU), and 95th percentile Hausdorff distance (HD95), were used to quantitatively evaluate the performance of our model. The evaluation was conducted on an in-house prostate cancer dataset and a public oropharyngeal carcinoma (OPC) dataset, totaling 668 subjects. ResultsOur Medformer achieved a DSC of 0.81 ± 0.10 versus 0.72 ± 0.10, IOU of 0.73 ± 0.12 versus 0.65 ± 0.09, and HD95 of 9.86 ± 9.77 mm versus 19.13 ± 12.96 mm for delineation of gross tumor volume (GTV) on the prostate cancer dataset. Similarly, on the OPC dataset, it achieved a DSC of 0.77 ± 0.11 versus 0.72 ± 0.09, IOU of 0.70 ± 0.09 versus 0.65 ± 0.07, and HD95 of 7.52 ± 4.8 mm versus 13.63 ± 7.13 mm, representing significant improvements (p < 0.05). For delineating the clinical target volume (CTV), Medformer achieved a DSC of 0.91 ± 0.04, IOU of 0.85 ± 0.05, and HD95 of 2.98 ± 1.60 mm, comparable to other state-of-the-art algorithms. ConclusionsAuto-delineation of the treatment target based on multimodal learning outperforms conventional approaches that rely purely on visual features. Our method could be adopted into routine practice to rapidly contour CTV/GTV.

A comparison of target volumes drawn on arterial and venous phase scans during radiation therapy planning for patients with pancreatic cancer: the PANCRINJ study

BackgroundThe planification of radiation therapy (RT) for pancreatic cancer (PC) requires a dosimetric computed tomography (CT) scan to define the gross tumor volume (GTV). The main objective of this study was to compare the inter-observer variability in RT planning between the arterial and the venous phases following intravenous contrast.MethodsPANCRINJ was a prospective monocentric study that included twenty patients with non-metastatic PC. Patients underwent a pre-therapeutic CT scan at the arterial and venous phases. The delineation of the GTV was performed by one radiologist (gold standard) and two senior radiation oncologists (operators). The primary objective was to compare the Jaccard conformity index (JCI) for the GTVs computed between the GS (gold standard) and the operators between the arterial and the venous phases with a Wilcoxon signed rank test for paired samples. The secondary endpoints were the geographical miss index (GMI), the kappa index, the intra-operator variability, and the dose-volume histograms between the arterial and venous phases.ResultsThe median JCI for the arterial and venous phases were 0.50 (range, 0.17–0.64) and 0.41 (range, 0.23–0.61) (p = 0.10) respectively. The median GS-GTV was statistically significantly smaller compared to the operators at the arterial (p < 0.0001) and venous phases (p < 0.001), respectively. The GMI were low with few tumors missed for all patients with a median GMI of 0.07 (range, 0-0.79) and 0.05 (range, 0-0.39) at the arterial and venous phases, respectively (p = 0.15). There was a moderate agreement between the radiation oncologists with a median kappa index of 0.52 (range 0.38–0.57) on the arterial phase, and 0.52 (range 0.36–0.57) on the venous phase (p = 0.08). The intra-observer variability for GTV delineation was lower at the venous phase than at the arterial phase for the two operators. There was no significant difference between the arterial and the venous phases regarding the dose-volume histogram for the operators.ConclusionsOur results showed inter- and intra-observer variability in delineating GTV for PC without significant differences between the arterial and the venous phases. The use of both phases should be encouraged. Our findings suggest the need to provide training for radiation oncologists in pancreatic imaging and to collaborate within a multidisciplinary team.

Multi-modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers.

Head and neck (HN) gross tumor volume (GTV) auto-segmentation is challenging due to the morphological complexity and low image contrast of targets. Multi-modality images, including computed tomography (CT) and positron emission tomography (PET), are used in the routine clinic to assist radiation oncologists for accurate GTV delineation. However, the availability of PET imaging may not always be guaranteed. To develop a deep learning segmentation framework for automated GTV delineation of HN cancers using a combination of PET/CT images, while addressing the challenge of missing PET data. Two datasets were included for this study: Dataset I: 524 (training) and 359 (testing) oropharyngeal cancer patients from different institutions with their PET/CT pairs provided by the HECKTOR Challenge; Dataset II: 90 HN patients(testing) from a local institution with their planning CT, PET/CT pairs. To handle potentially missing PET images, a model training strategy named the "Blank Channel" method was implemented. To simulate the absence of a PET image, a blank array with the same dimensions as the CT image was generated to meet the dual-channel input requirement of the deep learning model. During the model training process, the model was randomly presented with either a real PET/CT pair or a blank/CT pair. This allowed the model to learn the relationship between the CT image and the corresponding GTV delineation based on available modalities. As a result, our model had the ability to handle flexible inputs during prediction, making it suitable for cases where PET images are missing. To evaluate the performance of our proposed model, we trained it using training patients from Dataset I and tested it with Dataset II. We compared our model (Model 1) with two other models which were trained for specific modality segmentations: Model 2 trained with only CT images, and Model 3 trained with real PET/CT pairs. The performance of the models was evaluated using quantitative metrics, including Dice similarity coefficient (DSC), mean surface distance (MSD), and 95% Hausdorff Distance (HD95). In addition, we evaluated our Model 1 and Model 3 using the 359 test cases in Dataset I. Our proposed model(Model 1) achieved promising results for GTV auto-segmentation using PET/CT images, with the flexibility of missing PET images. Specifically, when assessed with only CT images in Dataset II, Model 1 achieved DSC of 0.56±0.16, MSD of 3.4±2.1mm, and HD95 of 13.9±7.6mm. When the PET images were included, the performance of our model was improved to DSC of 0.62±0.14, MSD of 2.8±1.7mm, and HD95 of 10.5±6.5mm. These results are comparable to those achieved by Model 2 and Model 3, illustrating Model 1's effectiveness in utilizing flexible input modalities. Further analysis using the test dataset from Dataset I showed that Model 1 achieved an average DSC of 0.77, surpassing the overall average DSC of 0.72 among all participants in the HECKTOR Challenge. We successfully refined a multi-modal segmentation tool for accurate GTV delineation for HN cancer. Our method addressed the issue of missing PET images by allowing flexible data input, thereby providing a practical solution for clinical settings where access to PET imaging may be limited.

A novel LVPA-UNet network for target volume automatic delineation: An MRI case study of nasopharyngeal carcinoma

Accurate delineation of Gross Tumor Volume (GTV) is crucial for radiotherapy. Deep learning-driven GTV segmentation technologies excel in rapidly and accurately delineating GTV, providing a basis for radiologists in formulating radiation plans. The existing 2D and 3D segmentation models of GTV based on deep learning are limited by the loss of spatial features and anisotropy respectively, and are both affected by the variability of tumor characteristics, blurred boundaries, and background interference. All these factors seriously affect the segmentation performance. To address the above issues, a Layer-Volume Parallel Attention (LVPA)-UNet model based on 2D-3D architecture has been proposed in this study, in which three strategies are introduced. Firstly, 2D and 3D workflows are introduced in the LVPA-UNet. They work in parallel and can guide each other. Both the fine features of each slice of 2D MRI and the 3D anatomical structure and spatial features of the tumor can be extracted by them. Secondly, parallel multi-branch depth-wise strip convolutions adapt the model to tumors of varying shapes and sizes within slices and volumetric spaces, and achieve refined processing of blurred boundaries. Lastly, a Layer-Channel Attention mechanism is proposed to adaptively adjust the weights of slices and channels according to their different tumor information, and then to highlight slices and channels with tumor. The experiments by LVPA-UNet on 1010 nasopharyngeal carcinoma (NPC) MRI datasets from three centers show a DSC of 0.7907, precision of 0.7929, recall of 0.8025, and HD95 of 1.8702 mm, outperforming eight typical models. Compared to the baseline model, it improves DSC by 2.14 %, precision by 2.96 %, and recall by 1.01 %, while reducing HD95 by 0.5434 mm. Consequently, while ensuring the efficiency of segmentation through deep learning, LVPA-UNet is able to provide superior GTV delineation results for radiotherapy and offer technical support for precision medicine.

The role of 18F-FDG PET in minimizing variability in gross tumor volume delineation of soft tissue sarcomas

BackgroundAccurate gross tumor volume (GTV) delineation is a critical step in radiation therapy treatment planning. However, it is reader dependent and thus susceptible to intra- and inter-reader variability. GTV delineation of soft tissue sarcoma (STS) often relies on CT and MR images. PurposeThis study investigates the potential role of 18F-FDG PET in reducing intra- and inter-reader variability thereby improving reproducibility of GTV delineation in STS, without incurring additional costs or radiation exposure. Materials and MethodsThree readers performed independent GTV delineation of 61 patients with STS using first CT and MR followed by CT, MR, and 18F-FDG PET images. Each reader performed a total of six delineation trials, three trials per imaging modality group. Dice Similarity Coefficient (DSC) score and Hausdorff distance (HD) were used to assess both intra- and inter-reader variability using generated simultaneous truth and performance level estimation (STAPLE) GTVs as ground truth. Statistical analysis was performed using a Wilcoxon signed-ranked test. ResultsThere was a statistically significant decrease in both intra- and inter-reader variability in GTV delineation using CT, MR 18F-FDG PET images vs. CT and MR images. This was translated by an increase in the DSC score and a decrease in the HD for GTVs drawn from CT, MR and 18F-FDG PET images vs. GTVs drawn from CT and MR for all readers and across all three trials. ConclusionIncorporation of 18F-FDG PET into CT and MR images decreased intra- and inter-reader variability and subsequently increased reproducibility of GTV delineation in STS.

Clinical Evaluation of Deep Learning for Tumor Delineation on 18F-FDG PET/CT of Head and Neck Cancer.

Artificial intelligence (AI) may decrease 18F-FDG PET/CT-based gross tumor volume (GTV) delineation variability and automate tumor-volume-derived image biomarker extraction. Hence, we aimed to identify and evaluate promising state-of-the-art deep learning methods for head and neck cancer (HNC) PET GTV delineation. Methods: We trained and evaluated deep learning methods using retrospectively included scans of HNC patients referred for radiotherapy between January 2014 and December 2019 (ISRCTN16907234). We used 3 test datasets: an internal set to compare methods, another internal set to compare AI-to-expert variability and expert interobserver variability (IOV), and an external set to compare internal and external AI-to-expert variability. Expert PET GTVs were used as the reference standard. Our benchmark IOV was measured using the PET GTV of 6 experts. The primary outcome was the Dice similarity coefficient (DSC). ANOVA was used to compare methods, a paired t test was used to compare AI-to-expert variability and expert IOV, an unpaired t test was used to compare internal and external AI-to-expert variability, and post hoc Bland-Altman analysis was used to evaluate biomarker agreement. Results: In total, 1,220 18F-FDG PET/CT scans of 1,190 patients (mean age ± SD, 63 ± 10 y; 858 men) were included, and 5 deep learning methods were trained using 5-fold cross-validation (n = 805). The nnU-Net method achieved the highest similarity (DSC, 0.80 [95% CI, 0.77-0.86]; n = 196). We found no evidence of a difference between expert IOV and AI-to-expert variability (DSC, 0.78 for AI vs. 0.82 for experts; mean difference of 0.04 [95% CI, -0.01 to 0.09]; P = 0.12; n = 64). We found no evidence of a difference between the internal and external AI-to-expert variability (DSC, 0.80 internally vs. 0.81 externally; mean difference of 0.004 [95% CI, -0.05 to 0.04]; P = 0.87; n = 125). PET GTV-derived biomarkers of AI were in good agreement with experts. Conclusion: Deep learning can be used to automate 18F-FDG PET/CT tumor-volume-derived imaging biomarkers, and the deep-learning-based volumes have the potential to assist clinical tumor volume delineation in radiation oncology.

Clinical assessment of deep learning-based uncertainty maps in lung cancer segmentation.

Objective. Prior to radiation therapy planning, accurate delineation of gross tumour volume (GTVs) and organs at risk (OARs) is crucial. In the current clinical practice, tumour delineation is performed manually by radiation oncologists, which is time-consuming and prone to large inter-observer variability. With the advent of deep learning (DL) models, automated contouring has become possible, speeding up procedures and assisting clinicians. However, these tools are currently used in the clinic mostly for contouring OARs, since these systems are not reliable yet for contouring GTVs. To improve the reliability of these systems, researchers have started exploring the topic of probabilistic neural networks. However, there is still limited knowledge of the practical implementation of such networks in real clinical settings.Approach. In this work, we developed a 3D probabilistic system that generates DL-based uncertainty maps for lung cancer CT segmentations. We employed the Monte Carlo (MC) dropout technique to generate probabilistic and uncertainty maps, while the model calibration was evaluated by using reliability diagrams. A clinical validation was conducted in collaboration with a radiation oncologist to qualitatively assess the value of the uncertainty estimates. We also proposed two novel metrics, namely mean uncertainty (MU) and relative uncertainty volume (RUV), as potential indicators for clinicians to assess the need for independent visual checks of the DL-based segmentation. Main results. Our study showed that uncertainty mapping effectively identified cases of under or over-contouring. Although the overconfidence of the model, a strong correlation was observed between the clinical opinion and MU metric. Moreover, both MU and RUV revealed high AUC values in discretising between low and high uncertainty cases.Significance. Our study is one of the first attempts to clinically validate uncertainty estimates in DL-based contouring. The two proposed metrics exhibited promising potential as indicators for clinicians to independently assess the quality of tumour delineation.

Utility of 68Ga-DOTATATE PET-MRI for Gamma Knife® stereotactic radiosurgery treatment planning for meningioma.

To investigate the impact of adding 68Ga-DOTATATE PET/MRI to standard MRI for target volume delineation in Gamma Knife® stereotactic radiosurgery (GKSRS) for meningioma. Seventeen patients with 18 lesions undergoing GKSRS for WHO grade 1 meningioma were enrolled in a prospective study. All patients underwent pre-treatment 68Ga-DOTATATE PET/MRI examination in addition to standard procedures. Five clinicians independently contoured the gross tumour volume (GTV) based on standard MRI (GTVMRI) and PET/MRI (GTVPET/MRI) on separate occasions. Interobserver agreement was evaluated using Cohen's Kappa statistic (CKS), Dice similarity coefficient (DC), and Hausdorff distance (HD). Statistical analysis was performed with paired t-test and Wilcoxon signed rank test. The addition of PET/MRI significantly increased GTV contour volume (mean GTVPET/MRI 3.59 cm3 versus mean GTVMRI 3.18 cm3, P = .008). Using the treating clinician's pre-treatment GTVMRI as the reference, median CKS (87.2 vs 77.5, P = .006) and DC (87.2 vs 77.4, P = .006) were significantly lower, and median HD (25.2 vs 31.0, P = .001) was significantly higher with the addition of PET/MRI. No significant difference was observed in interobserver contouring reproducibility between GTVMRI and GTVPET/MRI. The addition of 68Ga-DOTATATE PET/MRI for target volume delineation in GKSRS for meningioma is associated with an increase in GTV volume and greater interobserver variation. PET/MRI did not affect interobserver contouring reproducibility. This study provides novel insights into the impact of 68Ga-DOTATATE PET/MRI on GTV delineation and interobserver agreement in meningioma GKSRS, highlighting its potential for improving GKSRS treatment accuracy.

Impact of attenuation correction of radiotherapy hardware for positron emission tomography-magnetic resonance in ano-rectal radiotherapy patients.

Positron Emission Tomography-Magnetic Resonance (PET-MR) scanners could improve ano-rectal radiotherapy planning through improved Gross Tumour Volume (GTV) delineation and enabling dose painting strategies using metabolic measurements. This requires accurate quantitative PET images acquired in the radiotherapy treatmentposition. This study aimed to evaluate the impact on GTV delineation and metabolic parameter measurement of using novel Attenuation Correction (AC) maps that included the radiotherapy flat couch, coil bridge and anterior coil to see if they werenecessary. Seventeen ano-rectal radiotherapy patients received a -FluoroDeoxyGlucose PET-MR scan in the radiotherapy position. PET images were reconstructed without ( ) and with ( ) the radiotherapy hardware included. Both AC maps used the same Computed Tomography image for patient AC. Semi-manual and threshold GTVs were delineated on both PET images, the volumes compared and the Dice coefficient calculated. Metabolic parameters: Standardized Uptake Values , and Total Lesion Glycolysis (TLG) were compared using paired t-tests with a Bonferroni corrected significance level of . Differences in semi-manual GTV volumes between and were approaching statistical significance (difference , ), with larger differences in low FDG-avid tumours ( ). The and GTVs were concordant with Dice coefficients (manual) and (threshold). Metabolic parameters were significantly different, with , and TLG differences of ( ), ( ) and ( ) respectively. The TLG difference resulted in 1/8 rectal cancer patients changing prognosis group, based on literature TLG cut-offs, when using rather than . This study suggests that using AC maps with the radiotherapy hardware included is feasible for patient imaging. The impact on tumour delineation was mixed and needs to be evaluated in larger cohorts. However using AC of the radiotherapy hardware is important for situations where accurate metabolic measurements are required, such as dose painting and treatmentprognostication.

Radiological Biomarkers in MRI directed Rectal Cancer Radiotherapy Volume Delineation.

Our study evaluated whether an MRI reporting system highlighting areas of contiguous and discontinuous extramural venous invasion (EMVI) can improve the accuracy of gross tumour volume (GTV) delineation. Initially, 27 consecutive patients with locally advanced rectal cancer treated between 2012 and 2014 were evaluated. We used an MRI reporting proforma that documented the position of the primary tumour, lymph nodes and EMVI. The new GTVs delineated were compared with historical radiotherapy treatment volumes to identify the frequency of GTV geographical miss. We observed that the delineation of involved nodes and areas of EMVI was more likely to represent sources of uncertainty wherein nodal GTV geographical miss was evident in 5 out of 27 patients (19%). Complete EMVI GTV geographical miss occurred in two patients (7%). We re-evaluated our radiotherapy practice in a further 27 patients after the implementation of a modified MRI reporting system. An improvement was seen; nodal miss was observed in two patients (7%) and partial EMVI miss in one patient (4%), although these areas were encompassed in the planning target volume (PTV). Our study shows that extramural venous invasion and involved nodes need to be highlighted on MRI to improve the accuracy of rectal cancer GTV delineation.

Towards deep-learning (DL) based fully automated target delineation for rectal cancer neoadjuvant radiotherapy using a divide-and-conquer strategy: a study with multicenter blind and randomized validation

PurposeManual clinical target volume (CTV) and gross tumor volume (GTV) delineation for rectal cancer neoadjuvant radiotherapy is pivotal but labor-intensive. This study aims to propose a deep learning (DL)-based workflow towards fully automated clinical target volume (CTV) and gross tumor volume (GTV) delineation for rectal cancer neoadjuvant radiotherapy.Materials & methodsWe retrospectively included 141 patients with Stage II-III mid-low rectal cancer and randomly grouped them into training (n = 121) and testing (n = 20) cohorts. We adopted a divide-and-conquer strategy to address CTV and GTV segmentation using two separate DL models with DpuUnet as backend-one model for CTV segmentation in the CT domain, and the other for GTV in the MRI domain. The workflow was validated using a three-level multicenter-involved blind and randomized evaluation scheme. Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) metrics were calculated in Level 1, four-grade expert scoring was performed in Level 2, and head-to-head Turing test in Level 3.ResultsFor the DL-based CTV contours over the testing cohort, the DSC and 95HD (mean ± SD) were 0.85 ± 0.06 and 7.75 ± 6.42 mm respectively, and 96.4% cases achieved clinical viable scores (≥ 2). The positive rate in the Turing test was 52.3%. For GTV, the DSC and 95HD were 0.87 ± 0.07 and 4.07 ± 1.67 mm respectively, and 100% of the DL-based contours achieved clinical viable scores (≥ 2). The positive rate in the Turing test was 52.0%.ConclusionThe proposed DL-based workflow exhibited promising accuracy and excellent clinical viability towards automated CTV and GTV delineation for rectal cancer neoadjuvant radiotherapy.

Deep Learning-Based Synthesis of Contrast-Enhanced MRI for Automated Delineation of Primary Gross Tumor Volume in Radiotherapy of Nasopharyngeal Carcinoma.

Contrast-enhanced MRIs are necessary to delineate the primary gross tumor volume (GTVp) in radiotherapy of nasopharyngeal carcinoma (NPC). However, using contrast agents to scan contrast-enhanced MRIs is not applicable to some patients due to metal implants or their allergy, and it increases the treatment cost of patients. To address these problems, this work aims at synthesizing contrast-enhance MRIs from unenhanced MRIs by implementing generative adversarial network (GAN). In this work, 324 MRI datasets of patients with NPC were retrospectively collected between September 2016 and September 2017 from a single institute. MRI examinations were performed with un-enhanced T1-weighted (T1) and T2-weighted (T2) sequences, and contrast-enhanced T1-weighted (T1C) and fat-suppressed T1-weighted (T1FSC) sequences. We designed and developed a modified pix2pix network to synthesize T1C (sT1C) and T1FSC (sT1FSC) from real T1. The end of the generator in this network was assembled with multiple heads (the classification head and gradient head) to learn more representation information and features from real images, the discriminator in this network distinguished whether the synthesized image is real and fake and supervised that the generator outputs more realistic synthesized image. We verified the performance of the synthesized images for automated delineation of GTVp. In an independent testing set of 11 patients, the synthesized sT1C and sT1FSC were inputted into the segmentation deep learning network along with their corresponding T1 and T2 sequences to generate GTVp contours. Delineation performance of the synthesized images and real images for automated delineation were evaluated by dice similarity coefficient (DSC), and average surface distance (ASD), using human expert contours as the ground truth. In automated contouring of GTVp for NPC, the segmentation deep learning network using one or two synthesized MRIs showed equivalent performance when compared with the automated contours which generated from four real MRI sequences. Mean DSCs between automated contours by sT1C-replaced or sT1C and sT1FSC-replaced network and ground truth contours were 0.726 ± 0.143 and 0.711 ± 0.157, respectively, slightly inferior to that of contours generated from four real MRI sequences (0.740 ± 0.154, both P >0.05). In terms of mean ASD, there was also no significant difference between automated contours generated from synthesized images and real images (3.056 ± 4.216 mm and 3.537 ± 4.793 mm vs. 3.124 ± 4.637 mm; both P > 0.05). We proposed an MRI-synthesis method based on GAN and the synthesized contrast-enhanced MRIs performed equivalent as the real contrast-enhanced MRIs in the automated delineation of gross tumor volume for radiotherapy of NPC.

Agreement among Radiation Oncologists and Radiologist in Contouring GTV on Planning and Mid-Treatment MRI for Locally Advanced Oropharynx Cancer

Over the 7-week radiotherapy course, patients with head and neck cancers undergo significant anatomical changes, including weight loss and tumor shrinkage (with complete response at mid-treatment in as high as 50% of patients). The current standard of care is to maintain the same plan for the entire treatment duration, unless major dosimetric deviations are suspected. The use of MRI for treatment adaptation has the advantage of increased soft tissue contrast and is being integrated into several clinical practices with the recent implementation of the MR-Linac technology. In this interim secondary analysis of a phase 2, randomized trial, we assessed inter-observer variability (IOV) in the delineation of GTV at planning and mid-treatment in locally advanced oropharynx cancer (OPC). Three expert radiation oncologists (RO) and 1 expert radiologist, with a minimum of 5 years' experience in MRI contouring, blinded to each other's volumes, were provided with planning and mid-treatment MRI (T1 gadolinium, T2-weighted and DWI) of 9 patients with locally advanced OPC. Primary gross tumor volume (GTV) was independently contoured by all 3 ROs and the radiologist. Contouring agreement was analyzed using the dice similarity coefficient (DSC) index and the average Hausdorff distance. Nine cases of locally advanced OPC were included. Fifty percent of the patients were stage 3 (AJCC 8th edition) and all were p16+ OPC. There was moderate IOV in the delineation of GTV on planning MRI as evidenced by mean DSC index and Hausdorff distance of 0.75 (range 0.53 - 0.87) and 0.30 cm (max 2.14 cm). At mid-treatment, the GTV IOV had a mean DSC index and Hausdorff distance of 0.30 (range 0.19 - 0.76) and 0.55 cm (max 2.83), respectively. The contours of the radiologist compared to RO shown a mean DSC index and Hausdorff distance on planning MRI 0.63 (range 0.53 - 0.69) and 0.41 cm (max 2.14 cm), and on mid-treatment MRI of 0.36 (range 0.19 - 0.59) and 0.68 cm (max 1.08 cm). Although this study demonstrates the presence of moderate IOV between 3 experienced head and neck ROs and one radiologist in an academic institution for the delineation of GTV on planning MRI, we observed a higher IOV between the 4 experts on mid-treatment MRI. We also experienced a higher IOV between the radiologist and RO on planning and mid-treatment images. These results show high degree of GTV volume variability on mid-treatment MRI. Therefore, peer review of contours is important and guidelines for MR adaptive tumor delineation are needed.

GTV Based Automatic Delineation of Clinical Target Volume for Cervical Cancer

The delineation of gross tumor volume (GTV) and clinical target volume (CTV) are two critical steps in the radiotherapy planning for cervical cancer. GTV defines the primary treatment region for the gross tumor, while CTV is the area surrounding GTV that includes a certain probability (5% to 10%) of subclinical lesions. In contrast to GTV, CTV delineation relies on predefined and judgment-based boundaries, and the high variability among users makes this task particularly challenging. In this study, we evaluated the potential relationship between GTV and CTV and developed an automatic CTV delineation algorithm for cervical cancer based on the fusion of GTV information. We introduced position and shape constraints of GTV to improve the accuracy of CTV delineation. The GTV-Net deep learning method was used to segment the CTV images of cervical cancer. The method aimed to use the delineation results of the GTV region for one-hot coding and add human anatomy experience in the clinical field to guide the CTV segmentation. This retrospective study included 545 cervical cancer patients who received radiation therapy from June 2017 to May 2019, including postoperative and radical treatment groups. The CTV and GTV regions were manually delineated by human experts. Numerous experiments were conducted to evaluate the performance of the network. First, compared with different network architectures, the Dice similarity coefficient (DSC) and 95% Hausdorff distance (95HD) of GTV-Net were both improved. Then, we compared the GTV-Net method with two resident physicians. Our GTV-Net method outperformed both resident physicians. In the postoperative group, our method improved the DSC by 4% compared to 3D-UNet, reaching 76.55%, and increased by about 2.57% compared to V-Net's 73.98%, with an improvement of approximately 1.23% compared to the two resident physicians. In the radical treatment group, compared to 3D-UNet's 78.76%, our method increased the DSC by about 3.25%, reaching 82%, and increased by approximately 2.08% compared to V-Net's 79.92%, with an improvement of about 1.35% compared to the two resident physicians. Compared with 3D-UNet, the average 95HD in the postoperative group decreased from 1.489 to 1.457, and in the radical treatment group, it decreased from 1.454 to 1.433. The results of 95HD also showed some improvement compared to V-Net. This study is the first to introduce GTV information for automatic segmentation of the clinical target area for cervical cancer. In this experiment, we observed a positive gain in CTV target automatic delineation guided by GTV information compared to solely performing CTV segmentation, with an improvement in Dice similarity of more than 4% and Hausdorff distance of more than 6% in the experimental dataset. In addition, GTV-guided CTV automatic delineation has also shown promising results on multicenter data, which will better serve the clinical field.

A Multicenter Study on Deep Learning for Glioblastoma Auto-Segmentation with Prior Knowledge in Multimodal Imaging

A precise radiotherapy plan is required to ensure accurate delineation of gross tumor volumes (GTV) and clinical target volumes (CTV1 and CTV2) of glioblastomas (GBMs). However, traditional manual delineation is labor intensive and highly dependent on oncologists' experience. To construct and evaluate a deep learning-based automatic delineation method using prior knowledge in multimodal medical imaging to automate precise GTV, CTV1 and CTV2 contouring in GBM patients. We retrospectively collected the CT and MRI scans of 55 eligible patients with histologically proven high-grade glioma (HGG) from an institute, these scans were performed with non-enhanced CT (CT), contrast-enhanced T1-weighted (T1C) and T2-FLAIR (T2F) sequences. We proposed a two-stage automatic segmentation framework (PKMI-Net) for GTV, CTV1 and CTV2 based on deep learning using prior knowledge in multimodal medical imaging, and its segmentation performance was evaluated with dice similarity coefficient (DSC), 95% Harsdorff distance (HD95), average surface distance (ASD) and relative volume difference (RVD). To further investigate the generalizability of our method, we designed and conducted two evaluation strategies (Mix and Cross) on four multicenter datasets (including 55 patients, 37 patients, 21 patients and 35 patients). The evaluation results with an 11-patient test set from the single institute were summarized in Table 1, the proposed method demonstrated the best accuracy in segmenting, respectively, GTV, CTV1 and CTV, achieving a DSC of 0.94, 0.95 and 0.92; HD95 of 2.07 mm, 1.18 mm and 3.80 mm; ASD of 0.69 mm, 0.39 mm and 1.13 mm and RVE of 5.50%, 3.97% and 9.68%. In the multicenter evaluation, the segmentation performance of our method implemented with the Cross strategy was comparable to that with the Mix strategy, demonstrating that our method had high and stable generalizability across multicenter datasets in automatically segmenting GTV, CTV1 and CTV2. Our proposed method achieved promising results in automatically segmenting gliomas across various datasets, which could improve the quality and efficiency of glioblastoma radiotherapy.

Failure Mode and Effects Analysis Prior to the Introduction of AI Generated GTVs for Brain Metastases in the Clinical Workflow

AI autosegmentation of organs-at-risk (OARs) is common practice at many radiotherapy clinics. Despite the abundance of gross tumor volume (GTV) autosegmentation algorithms, adoption in clinical care has been slow due to the high risk associated with errors in GTV delineation. Here we present a failure mode and effects analysis (FMEA) to evaluate the risk associated with introducing AI derived GTVs in patients treated with stereotactic radiosurgery (SRS). An AI GTV autosegmentation algorithm for brain metastases was developed in-house based on a V-Net 3D CNN. Registered CT and MR images and a contour of the brain are input into the software and all identified lesions are returned in a DICOM-RT structure set. Following algorithm evaluation, a workflow was developed to enable AI GTV autosegmentation to be introduced clinically for every SRS patient. The following steps were added to existing procedures: 1) workflow to send CT/MR and brain structure to external server, 2) autosegmentation run on the server, 3) AI GTV structures with a standard nomenclature added to existing OAR structure set, and 4) MD review, editing, and approval of AI GTVs. After successfully completing the physics evaluation testing of the new process, we formed a team of 10 faculty and staff including physicists, residents, physicians, and planners to perform the FMEA prior to clinical implementation. The team met to map the process, identify potential failure modes, and score their frequency of occurrence, severity, and detectability. A 3-point scale (1, 3, or 5) was used to simplify the scoring process. Occurrence was defined as rare, sometimes, or often; severity as low, medium, or high; and detectability as obvious, possible, or challenging. The risk probability numbers (RPNs) were calculated and the steps in the process with the highest RPNs were flagged for further discussion. The FMEA team completed their process map and analysis primarily in 4 meetings. The process map began with acquisition of the patients CT simulation scan and ended with physician approval of final volumes for treatment planning. We identified 17 process steps and 72 possible failure modes, of which 26 were associated with the new workflow. Eighteen failure modes had an RPN greater than 30 (highest risk score in at least one category) and were flagged to assess mitigation strategies. Five were unique to the new AI GTV workflow and mitigation strategies will be designed prior to clinical use. Those involved risks related to inaccurate AI GTV contours, false positives, and an incomplete review stemming from over-reliance by team members on AI. AI is increasingly being employed at every step of radiotherapy to automate and streamline processes. The FMEA analysis resulted in the identification of the riskiest parts of using AI GTV autosegmentation. This can be an effective tool in the development of checks to ensure that GTV autosegmentation methods can be safely introduced in support of patient care.

Interobserver Variation in Tumor Delineation of Liver Metastases using Magnetic Resonance Imaging

Magnetic Resonance (MR-) guided stereotactic body radiotherapy enables accurate treatment of liver metastases. Despite the accuracy of treatment delivery, one of the main uncertainties is the variation in tumor delineation, which requires additional treatment margins. The aim of this study was to quantify the interobserver variation (IOV) in MRI based delineation of the gross tumor volume (GTV) of liver metastases. A cohort of 20 liver metastases treated on a MR-Linac were consecutively selected per primary tumor (colorectal (6), breast (6) and lung (8)). Planning MRI scans (T1 weighted with IV-contrast) were collected and anonymized. GTV delineation guidelines and case-specific information were provided to 8 radiation oncologists from 8 institutions. All cases were quantitatively reviewed and delineations with major violations of the guidelines were marked as outliers (such as contours including a vein or excluding obvious parts of a tumor). IOV was quantified by comparing individual delineations with the median contour and calculating the standard deviation (SD) and 95th percentile Hausdorff distance (HD95). Analyses were conducted on all delineations and on a subgroup excluding outliers per case to distinguish between accuracy of delineation and individual guideline interpretation. Sphericity was calculated from the volume and surface area of all delineations. Correlation between SD and sphericity was determined using Spearman's rs. Differences in SD between primary tumors were analyzed using the Kruskal-Wallis test. The median volume of all metastases was 6.5 cc (IQR 3.7 - 29.8 cc) and sphericity was 0.84 (IQR 0.80 - 0.87) based on all contours (Table 1). The SD was 1.6 mm and the median HD95 was 2.7 mm. In the subgroup analysis, one (in 15 cases) or two (in 5 cases) delineations were excluded. Subgroup analyses showed a SD of 1.1 mm and median HD 95 of 2.6mm. The Kruskal-Wallis test showed no difference (p = 0.59) in SD between primary tumors. There was a significant negative correlation between IOV (SD) and sphericity (rs = -0.70; p = 0.008). Table 1: Overview of SD (mm), HD95 (mm) and volume (cc) of all observers and subgroup per primary tumor and in total CONCLUSION: MRI based GTV delineation variation of liver metastases is 1.1 - 1.6 mm, which is smaller than anticipated, although significant outliers (HD95 up to 3.9 mm) were present. Use of common delineation guidelines will ensure consistency in contouring and have the potential to decrease treatment margins when taking IOV into account.

Deep Learning and GAN-Synthesis for Auto-Segmentation of Pancreatic Cancer by Non-Enhanced CT for Adaptive Radiotherapy

In conventional adaptive radiotherapy (ART) for pancreatic cancer, contrast-enhanced CT (CECT) helps to more precisely delineate primary gross tumor volume (GTV) than non-enhanced CT (NECT). However, frequent use of contrast medium can damage kidneys and prolong treatment time. Moreover, traditional manual delineation is labor-intensive and highly dependent on the experience of oncologists. Currently, automatic delineation based on deep learning with Generative Adversarial Networks (GAN)-based CT synthesis is one of the most feasible solutions to these problems. A dataset of 35 pancreatic cancer patients was retrospectively collected from May 2021 to December 2022. All patients consist of a pair of NECT and CECT. We designed and developed an automatic delineation framework (Proposed) for GTV of pancreatic cancer based on Trans-cycleGAN and a modified 3D U-Net. TranscycleGAN can not only synthesize CECT from NECT, but can also augment the amount of CT images; then all real and synthesized CT images were used to train the modified 3D U-Net for automatic delineation of GTV; finally, our framework was able to automatically delineate GTV by NECT, but not only by CECT. Our framework was evaluated by dice similarity coefficient (DSC), 95% Harsdorff distance (95HD) and average surface distance (ASD) with oncologists' manual delineation ("gold standard"). The evaluation results were summarized in Table 1. The proposed framework achieved the best automatic delineation results by NECT, which was superior to that of CECT: 0.917 & 0.903 of DSC, 2.498mm & 3.029mm of HD95, 0.481mm & 0.534mm of ASD, p < 0.05 for DSC and HD95. Specifically, it is significantly superior to the automatic delineation results using U-Net by CECT 0.917 & 0.818 of DSC, 2.498mm & 13.228mm of HD95, 0.481mm & 3.633mm of ASD, p < 0.05 for DSC. We proposed an automatic delineation framework for contouring GTV in ART of pancreatic cancer based on deep learning and Trans-cycleGAN network. This framework could automatically delineate GTV and achieve better performance with NECT compared to CECT. Our method could not only reduce the use of contrast medium, but also increase the precision and effectiveness of tumor delineation, which could have a positive impact on precision radiotherapy.