The predictors of lymphopenia and its effects on survival in locally advanced esophageal squamous cell carcinoma.

To investigate the impact of the effective radiation dose to immune cells (EDIC) and gross tumor volume (GTV) on lymphopenia and survival in patients with locally advanced esophageal squamous cell carcinoma (LAESCC). Between January 2013 and December 2020, 272 LAESCC patients were treated with definitive radiotherapy in two institutions. Based on radiation doses to the lungs, heart, and body region scanned, EDIC was calculated as an equal uniform dose to the total blood considering blood flow and fraction effect. The radiotherapy plan was used to calculate the GTVs. Lymphopenia was graded based on the lowest lymphocyte count during RT. The overall survival (OS), progress-free survival (PFS), and local recurrence-free survival (LRFS) were analyzed statistically. The lowest lymphocyte count was significantly correlated with EDIC (r= -0.389, p < .001) and GTV (r= -0.211, p < .001). Lymphopenia, EDIC, and GTV are risk factors for patients with ESCC. In a Kaplan-Meier analysis with EDIC and GTV as stratification factors, lymphopenia was not associated with OS in the EDIC>12.9 Gy group (p = .294)and EDIC ≤ 12.9 Gy group, and it was also not associated with OS in GTV>68.8 cm3 group (p = .242) and GTV ≤ 68.8 cm3 group(p = .165). GTV and EDIC had an impact on the relationship between lymphopenia and OS in patients with LAESCC undergoing definitive RT. Poorer OS, PFS, and LRFS are correlated with lymphopenia, higher EDIC, and larger GTV.

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

BACKGROUND: 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. PURPOSE: 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. METHODS: 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. RESULTS: 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 ± 2.1 mm, and HD95 of 13.9 ± 7.6 mm. When the PET images were included, the performance of our model was improved to DSC of 0.62 ± 0.14, MSD of 2.8 ± 1.7 mm, and HD95 of 10.5 ± 6.5 mm. 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. CONCLUSIONS: 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.

Exploring habitats-based spatial distributions: improving predictions of lymphovascular invasion in invasive breast cancer.

RATIONALE AND OBJECTIVES: Accurate assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) plays a pivotal role in tailoring personalized treatment plans. This study aimed to investigate habitats-based spatial distributions to quantitatively measure tumor heterogeneity on multiparametric magnetic resonance imaging (MRI) scans and assess their predictive capability for LVI in patients with IBC. MATERIALS AND METHODS: In this retrospective cohort study, we consecutively enrolled 241 women diagnosed with IBC between July 2020 and July 2023 and who had 1.5 T/T1-weighted images, fat-suppressed T2-weighted images, and dynamic contrast-enhanced MRI. Habitats-based spatial distributions were derived from the gross tumor volume (GTV) and gross tumor volume plus peritumoral volume (GPTV). GTV_habitats and GPTV_habitats were generated through sub-region segmentation, and their performances were compared. Subsequently, a combined nomogram was developed by integrating relevant spatial distributions with the identified MR morphological characteristics. Diagnostic performance was compared using receiver operating characteristic curve analysis and decision curve analysis. Statistical significance was set at p < 0.05. RESULTS: GPTV_habitats exhibited superior performance compared to GTV_habitats. Consequently, the GPTV_habitats, diffusion-weighted imaging rim signs, and peritumoral edema were integrated to formulate the combined nomogram. This combined nomogram outperformed individual MR morphological characteristics and the GPTV_habitats index, achieving area under the curve values of 0.903 (0.847 -0.959), 0.770 (0.689 -0.852), and 0.843 (0.776 -0.910) in the training set and 0.931 (0.863 -0.999), 0.747 (0.613 -0.880), and 0.849 (0.759 -0.938) in the validation set. CONCLUSION: The combined nomogram incorporating the GPTV_habitats and identified MR morphological characteristics can effectively predict LVI in patients with IBC.

Predictive value of primary tumor volume change during concurrent chemoradiotherapy in patients with unresectable stage III non-small cell lung cancer.

BACKGROUND AND PURPOSE: No established early biomarkers currently exist to predict responses during concurrent chemoradiotherapy (CCRT) in patients with unresectable non-small cell lung cancer (NSCLC). This study investigated the potential of gross tumor volume (GTV) and its changes during CCRT as predictors of survival outcomes. MATERIALS AND METHODS: We identified 227 patients with unresectable stage III NSCLC who underwent definitive CCRT followed by durvalumab between November 2018 and December 2022. GTV was defined as the volume of the primary tumor, assessed at two time points: before starting CCRT for initial planning (GTV1), and at the fourth week of CCRT for adaptive planning (GTV2). Both relative and absolute regressions between GTV1 and GTV2 were calculated. RESULTS: The median GTV1 volume was 90 mL (range, 5-840 mL), and the median GTV2 volume was 64 mL (range, 1-520 mL), resulting in median absolute and relative regressions of 18.6 mL and 25.0 %, respectively. Among the GTV parameters, relative GTV regression exhibited the strongest predictive value, with an area under the curve (AUC) of 0.804 for in-field progression and 0.711 for overall progression. The 1-year progression-free survival rates for the high (>30 %), intermediate (0-30 %), and low (≤0%) relative regression groups were 88.0 %, 62.6 %, and 14.3 %, respectively (p = 0.006 for high vs. intermediate; p < 0.001 for intermediate vs. low). Additionally, GTV2 volume demonstrated stronger associations with survival outcomes than GTV1 volume. CONCLUSION: Relative GTV regression was identified as a promising early predictor for patients with unresectable stage III NSCLC. Further development of a multi-parametric predictive model is warranted to guide patient-tailored therapeutic approaches.

A transformer-guided cross-modality adaptive feature fusion framework for esophageal gross tumor volume segmentation.

BACKGROUND AND OBJECTIVE: Accurate segmentation of esophageal gross tumor volume (GTV) indirectly enhances the efficacy of radiotherapy for patients with esophagus cancer. In this domain, learning-based methods have been employed to fuse cross-modality positron emission tomography (PET) and computed tomography (CT) images, aiming to improve segmentation accuracy. This fusion is essential as it combines functional metabolic information from PET with anatomical information from CT, providing complementary information. While the existing three-dimensional (3D) segmentation method has achieved state-of-the-art (SOTA) performance, it typically relies on pure-convolution architectures, limiting its ability to capture long-range spatial dependencies due to convolution's confinement to a local receptive field. To address this limitation and further enhance esophageal GTV segmentation performance, this work proposes a transformer-guided cross-modality adaptive feature fusion network, referred to as TransAttPSNN, which is based on cross-modality PET/CT scans. METHODS: Specifically, we establish an attention progressive semantically-nested network (AttPSNN) by incorporating the convolutional attention mechanism into the progressive semantically-nested network (PSNN). Subsequently, we devise a plug-and-play transformer-guided cross-modality adaptive feature fusion model, which is inserted between the multi-scale feature counterparts of a two-stream AttPSNN backbone (one for the PET modality flow and another for the CT modality flow), resulting in the proposed TransAttPSNN architecture. RESULTS: Through extensive four-fold cross-validation experiments on the clinical PET/CT cohort. The proposed approach acquires a Dice similarity coefficient (DSC) of 0.76 ± 0.13, a Hausdorff distance (HD) of 9.38 ± 8.76 mm, and a Mean surface distance (MSD) of 1.13 ± 0.94 mm, outperforming the SOTA competing methods. The qualitative results show a satisfying consistency with the lesion areas. CONCLUSIONS: The devised transformer-guided cross-modality adaptive feature fusion module integrates the strengths of PET and CT, effectively enhancing the segmentation performance of esophageal GTV. The proposed TransAttPSNN has further advanced the research of esophageal GTV segmentation.

Improved brain metastases segmentation using generative adversarial network and conditional random field optimization mask R-CNN.

BACKGROUND: In radiotherapy, the delineation of the gross tumor volume (GTV) in brain metastases using computed tomography (CT) simulation localization is very important. However, despite the criticality of this process, a pronounced gap exists in the availability of tools tailored for the automatic segmentation of the GTV based on CT simulation localization images. PURPOSE: This study aims to fill this gap by devising an effective tool specifically for the automatic segmentation of the GTV using CT simulation localization images. METHODS: A dual-network generative adversarial network (GAN) architecture was developed, wherein the generator focused on refining CT images for more precise delineation, and the discriminator differentiated between real and augmented images. This architecture was coupled with the Mask R-CNN model to achieve meticulous GTV segmentation. An end-to-end training process facilitated the integration between the GAN and Mask R-CNN functionalities. Furthermore, a conditional random field (CRF) was incorporated to refine the initial masks generated by the Mask R-CNN model to ensure optimal segmentation accuracy. The performance was assessed using key metrics, namely, the Dice coefficient (DSC), intersection over union (IoU), accuracy, specificity, and sensitivity. RESULTS: The GAN+Mask R-CNN+CRF integration method in this study performs well in GTV segmentation. In particular, the model has an overall average DSC of 0.819 ± 0.102 and an IoU of 0.712 ± 0.111 in the internal validation. The overall average DSC in the external validation data is 0.726 ± 0.128 and the IoU is 0.640 ± 0.136. It demonstrates favorable generalization ability. CONCLUSION: The integration of the GAN, Mask R-CNN, and CRF optimization provides a pioneering tool for the sophisticated segmentation of the GTV in brain metastases using CT simulation localization images. The method proposed in this study can provide a robust automatic segmentation approach for brain metastases in the absence of MRI.

Dual-tracer PET/CT protocol with [18F]FDG and [68Ga]Ga-FAPI-46 outperforms single-tracer PET/CT with [18F]FDG in different cancer types, resulting in larger functional and gross tumor volume.

PURPOSE: Fibroblast activation protein (FAP) detected by positron-emission tomography (PET) using fibroblast activation protein inhibitor (FAPI) appears to be a promising target for cancer imaging, staging, and therapy, providing added value and strength as a complement to [18F]fluorodeoxyglucose (FDG) in cancer imaging. We recently introduced a combined single-session/dual-tracer protocol with [18F]FDG and [68Ga]Ga-FAPI for cancer imaging and staging. Malignant tissue visualization and target-to-background uptake ratios (TBRs) as well as functional tumor volume (FTV) and gross tumor volume (GTV) were assessed in the present study with single-tracer [18F]FDG PET/computed tomography (CT) and with dual-tracer [18F]FDG&[68Ga]Ga-FAPI-46 PET/CT. METHODS: A total of 19 patients with head and neck and gastrointestinal cancers received initial [18F]FDG-PET/CT followed by dual-tracer PET/CT after additional injection of [68Ga]Ga-FAPI-46 during the same medical appointment (on average 13.9 ± 12.3 min after injection of [18F]FDG). Two readers visually compared detection rate of malignant tissue, TBR, FTV, and GTV for tumor and metastatic tissue in single- and dual-tracer PET/CT. RESULTS: The diagnostic performance of dual-tracer compared to single-tracer PET/CT was equal in 13 patients and superior in 6 patients. The mean TBRs of tumors and metastases in dual-tracer PET/CTs were mostly higher compared to single-tracer PET/CT using maximal count rates (CRmax). GTV and FTV were significantly larger when measured on dual-tracer compared to single-tracer PET/CT. CONCLUSION: Dual-tracer PET/CT with [18F]FDG and [68Ga]Ga-FAPI-46 showed better visualization due to a generally higher TBR and larger FTV and GTV compared to [18F]FDG-PET/CT in several tumor entities, suggesting that [68Ga]Ga-FAPI-46 provides added value in pretherapeutic staging.

External validation of a lung cancer-based prediction model for two-year mortality in esophageal cancer patient cohorts.

PURPOSE/OBJECTIVE: Chemo-radiotherapy can improve the oncological outcome of esophageal cancer (EC) patients, but may cause long term radiation-induced toxicity, including an increased risk of non-cancer related death. For lung cancer patients, a model to predict 2-year total mortality using mean heart dose (MHD) and gross tumor volume (GTV) has previously been developed and validated. This project aimed to externally validate this model in EC patients. METHODS: Five EC patient cohorts from 3 different Dutch centres were used for model validation. External validity of the model was assessed separately in definitive (n = 170) and neo-adjuvant (n = 568) chemoradiotherapy (dCRT and nCRT) patients. External validity was assessed in terms of calibration by calibration plots, calibration-in-the-large (CITL) and calibration slope (CS), and discrimination by assessment of the c-statistic. If suboptimal model performance was observed, the model was further updated accordingly. RESULTS: For the dCRT patients, good calibration was found after adjustment of the intercept (CITL 0.00; CS 1.08). The c-statistic of the adjusted model was 0.67 (95%CI: 0.58 to 0.75). For nCRT patients the model needed adjustment of both the slope and the intercept because of initial miscalibration in the validation population (CITL 0.00; CS 1.72). After recalibration, the model showed perfect calibration (i.e., CITL 0, CS 1), as is common after recalibration. The c-statistic of the recalibrated model equaled 0.62 (95%CI: 0.57 to 0.67). CONCLUSION: The existing model for 2-year mortality prediction in lung cancer patients, based on the predictive factors MHD and GTV, showed good performance in EC patients after updating the intercept and/or slope of the original model.

Significance of radiologic extranodal extension in locoregionally advanced nasopharyngeal carcinoma with lymph node metastasis: a comprehensive nomogram.

OBJECTIVE: We aimed to assess the significance of rENE and creat a predictive tool (nomogram) for estimating Overall Survival (OS) in locoregionally advanced Nasopharyngeal Carcinoma (NPC) patients with Lymph Node Metastasis (LNM) based on their clinical characteristics and Radiologic Extranodal Extension (rENE). METHODS: Five hundred and sixty-nine NPC patients with LNM were randomly divided into training and validation groups. Significant factors were identified using univariate and multivariate analyses in the training cohort. Then, the nomogram based on the screening results was established to predict the Overall Survival (OS). Calibration curves and the Concordance index (C-index) gauged predictive accuracy and discrimination. Receiver Operating Characteristic (ROC) analysis assessed risk stratification, and clinical utility was measured using Decision Curve Analysis (DCA). The nomogram's performance was validated for discrimination and calibration in an independent validation cohort. RESULTS: A total of 360 (63.2%) patients were present with radiologic extranodal extension at initial diagnosis. Patients with rENE had significantly lower OS than other patients. Multivariate analysis identified the five factors, including rENE, for the nomogram model. The C-index was 0.75 (0.71-0.78) in the training cohort and 0.76 (0.69-0.83) in the validation cohort. Notably, the nomogram outperformed the 8th TNM staging system, as evident from the higher AUC values (0.77 vs. 0.60 for 2year and 0.75 vs. 0.65 for 3year) and well-calibrated calibration curves. Decision curve analysis indicated improved Net Benefit (NB) with the nomogram for predicting OS. The log-rank test confirmed significant survival distinctions between risk groups in both training and validation cohorts. CONCLUSIONS: We demonstrated the prognostic value of rENE in nasopharyngeal carcinoma and developed a nomogram based on rENE and other factors to provide individual prediction of OS for locoregionally advanced nasopharyngeal carcinoma with lymph node metastasis. LEVEL OF EVIDENCE: III.

Significance of radiologic extranodal extension in locoregionally advanced nasopharyngeal carcinoma with lymph node metastasis: a comprehensive nomogram

Abstract Objective We aimed to assess the significance of rENE and creat a predictive tool (nomogram) for estimating Overall Survival (OS) in locoregionally advanced Nasopharyngeal Carcinoma (NPC) patients with Lymph Node Metastasis (LNM) based on their clinical characteristics and Radiologic Extranodal Extension (rENE). Methods Five hundred and sixty-nine NPC patients with LNM were randomly divided into training and validation groups. Significant factors were identified using univariate and multivariate analyses in the training cohort. Then, the nomogram based on the screening results was established to predict the Overall Survival (OS). Calibration curves and the Concordance index (C-index) gauged predictive accuracy and discrimination. Receiver Operating Characteristic (ROC) analysis assessed risk stratification, and clinical utility was measured using Decision Curve Analysis (DCA). The nomogram's performance was validated for discrimination and calibration in an independent validation cohort. Results A total of 360 (63.2%) patients were present with radiologic extranodal extension at initial diagnosis. Patients with rENE had significantly lower OS than other patients. Multivariate analysis identified the five factors, including rENE, for the nomogram model. The C-index was 0.75 (0.71-0.78) in the training cohort and 0.76 (0.69-0.83) in the validation cohort. Notably, the nomogram outperformed the 8th TNM staging system, as evident from the higher AUC values (0.77 vs. 0.60 for 2 year and 0.75 vs. 0.65 for 3 year) and well-calibrated calibration curves. Decision curve analysis indicated improved Net Benefit (NB) with the nomogram for predicting OS. The log-rank test confirmed significant survival distinctions between risk groups in both training and validation cohorts. Conclusions We demonstrated the prognostic value of rENE in nasopharyngeal carcinoma and developed a nomogram based on rENE and other factors to provide individual prediction of OS for locoregionally advanced nasopharyngeal carcinoma with lymph node metastasis. Level of evidence: III.

Condition control training-based ConVMLP-ResU-Net for semantic segmentation of esophageal cancer in 18F-FDG PET/CT images.

The precise delineation of esophageal gross tumor volume (GTV) on medical images can promote the radiotherapy effect of esophagus cancer. This work is intended to explore effective learning-based methods to tackle the challenging auto-segmentation problem of esophageal GTV. By employing the progressive hierarchical reasoning mechanism (PHRM), we devised a simple yet effective two-stage deep framework, ConVMLP-ResU-Net. Thereinto, the front-end ConVMLP integrates convolution (ConV) and multi-layer perceptrons (MLP) to capture localized and long-range spatial information, thus making ConVMLP excel in the location and coarse shape prediction of esophageal GTV. According to the PHRM, the front-end ConVMLP should have a strong generalization ability to ensure that the back-end ResU-Net has correct and valid reasoning. Therefore, a condition control training algorithm was proposed to control the training process of ConVMLP for a robust front end. Afterward, the back-end ResU-Net benefits from the yielded mask by ConVMLP to conduct a finer expansive segmentation to output the final result. Extensive experiments were carried out on a clinical cohort, which included 1138 pairs of 18F-FDG positron emission tomography/computed tomography (PET/CT) images. We report the Dice similarity coefficient, Hausdorff distance, and Mean surface distance as 0.82 ± 0.13, 4.31 ± 7.91 mm, and 1.42 ± 3.69 mm, respectively. The predicted contours visually have good agreements with the ground truths. The devised ConVMLP is apt at locating the esophageal GTV with correct initial shape prediction and hence facilitates the finer segmentation of the back-end ResU-Net. Both the qualitative and quantitative results validate the effectiveness of the proposed method.

The Association of Gross Tumor Volume and Its Radiomics Features with Brain Metastases Development in Patients with Radically Treated Stage III Non-Small Cell Lung Cancer.

PURPOSE: To identify clinical risk factors, including gross tumor volume (GTV) and radiomics features, for developing brain metastases (BM) in patients with radically treated stage III non-small cell lung cancer (NSCLC). METHODS: Clinical data and planning CT scans for thoracic radiotherapy were retrieved from patients with radically treated stage III NSCLC. Radiomics features were extracted from the GTV, primary lung tumor (GTVp), and involved lymph nodes (GTVn), separately. Competing risk analysis was used to develop models (clinical, radiomics, and combined model). LASSO regression was performed to select radiomics features and train models. Area under the receiver operating characteristic curves (AUC-ROC) and calibration were performed to assess the models' performance. RESULTS: Three-hundred-ten patients were eligible and 52 (16.8%) developed BM. Three clinical variables (age, NSCLC subtype, and GTVn) and five radiomics features from each radiomics model were significantly associated with BM. Radiomic features measuring tumor heterogeneity were the most relevant. The AUCs and calibration curves of the models showed that the GTVn radiomics model had the best performance (AUC: 0.74; 95% CI: 0.71-0.86; sensitivity: 84%; specificity: 61%; positive predictive value [PPV]: 29%; negative predictive value [NPV]: 95%; accuracy: 65%). CONCLUSION: Age, NSCLC subtype, and GTVn were significant risk factors for BM. GTVn radiomics features provided higher predictive value than GTVp and GTV for BM development. GTVp and GTVn should be separated in clinical and research practice.

Five-Fraction Stereotactic Radiosurgery With Non-Contrast-Enhanced MRI-Based Target Definition and Moderate Dose Spillage Margin for Limited Brain Metastases With Impaired Renal Function.

In stereotactic radiosurgery (SRS) planning for brain metastases (BMs), the target volume is usually defined as an enhancing lesion based on contrast-enhanced (CE) magnetic resonance images (MRI) and/or computed tomography (CT) images. However, contrast media (CM) are unsuitable for certain patients with impaired renal function. Herein, we describe two limited BM cases not amenable to CM, which were treated with five-fraction (fr) SRS, without whole brain radiotherapy (WBRT), through a target definition based on non-CE-MRI. These included synchronous and partly symptomatic four BMs from esophageal squamous cell carcinoma (Case 1) and one presymptomatic regrowing lesion after WBRT for BMs from lung adenocarcinoma (Case 2). In both cases, all BMs were visualized as well-demarcated mass lesions almost distinguishable from the affected parenchyma on non-CE-MRI, particularly on T2-weighted images (WI). The gross tumor volume (GTV) was defined mainly based on T2-WI under a comprehensive comparison of non-CE-T1/T2-WIs and CT for SRS planning under image co-registration and fusion. Stereotactic radiosurgery was implemented with volumetric modulated arcs using a 5-mm leaf width multileaf collimator, for both of which 5 fr was selected, considering the maximum tumor volume and the effects from WBRT, respectively. Dose distribution was designed to ensure a moderate dose attenuation margin outside the GTV boundary and a concentrically-laminated steep dose increase inside the GTV boundary. Specifically, the peripheries of the GTV and 2 mm outside the GTV boundary were covered by ≥43 Gy with <70% isodose relative to the maximum dose and ≥31 Gy, respectively. The not-too-steep dose spillage margin can cover potentially invisible tumor invasion outside the GTV and other inherent uncertainties regarding target definition and irradiation accuracy. Post-SRS tumor responses were excellent clinically and/or radiographically with mild adverse radiation effects in Case 2. In limited BM cases unsuitable to CM, multi-fraction SRS with non-CE-MRI-based GTV definition and sufficient GTV dose along with moderate dose spillage margin would be a valuable treatment option for selected cases, with the entire GTV boundaries being almost visible on non-CE-MRI.

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning.

Background: Radiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task. Purpose: The purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC. Materials and methods: Contrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient (Dice), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs. Results: CNN models trained from scratch on canine data or by using transfer learning obtained mean test set Dice scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean Dice performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set Dice scores of 0.69 for both approaches. Conclusion: In conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients.

Feasibility of biology-guided radiotherapy for metastatic renal cell carcinoma driven by PSMA PET imaging.

Background: Biology-guided radiotherapy (BgRT) is a novel treatment where the detection of positron emission originating from a volume called the biological tracking zone (BTZ) initiates dose delivery. Prostate-specific membrane antigen (PSMA) positron emission tomography (PET) is a novel imaging technique that may improve patient selection for metastasis-directed therapy in renal cell carcinoma (RCC). This study aims to determine the feasibility of BgRT treatment for RCC. Material and methods: All consecutive patients that underwent PSMA PET/CT scan for RCC staging at our institution between 2014 and 2020 were retrospectively considered for inclusion. GTVs were contoured on the CT component of the PET/CT scan. The tumor-to-background ratio was quantified from the normalized standardized uptake value (nSUV), defined as the ratio between SUVmax inside the GTV and SUVmean inside the margin expansion. Tumors were classified suitable for BgRT if (1) nSUV was greater or equal to an nSUV threshold and (2) if the BTZ was free of any PET-avid region other than the tumor. Results: Out of this cohort of 83 patients, 47 had metastatic RCC and were included in this study. In total, 136 tumors were delineated, 1 to 22 tumors per patient, mostly in lung (40%). Using a margin expansion of 5 mm/10 mm/20 mm and nSUV threshold = 3, 66%/63%/41% of tumors were suitable for BgRT treatment. Uptake originating from another tumor, the kidney, or the liver was typically inside the BTZ in tumors judged unsuitable for BgRT. Conclusions: More than 60% of tumors were found to be suitable for BgRT in this cohort of patients with RCC. However, the proximity of PET-avid organs such as the liver or the kidney may affect BgRT delivery.

Dynamic tumor-tracking stereotactic body radiotherapy with real-time monitoring of liver tumors using a gimbal-mounted linac: A multi-institutional phase II study.

Background and purpose: This prospective multicenter phase II study aimed to evaluate the safety and efficacy of dynamic tumor tracking (DTT) stereotactic body radiotherapy (SBRT) with real-time monitoring of liver tumors using a gimbal-mounted system. Materials and methods: Patients with < 4 primary or metastatic liver tumors with diameters ≤ 50 mm and expected to have a respiratory motion of ≥ 10 mm were eligible. The prescribed dose was 40 Gy in five fractions. The primary endpoint was local control (LC) at 2 years. The secondary endpoints were overall survival (OS), progression-free survival (PFS), treatment-related toxicity, and tracking accuracy. Results: Between September 2015 and March 2019, 48 patients (48 lesions) with a median age of 74 years were enrolled from four institutions. Of these, 39 were diagnosed with hepatocellular carcinoma and nine with metastatic liver cancer. The median tumor diameter was 17.5 mm. DTT-SBRT was successfully performed in all patients; the median treatment time was 28 min/fraction. The median follow-up period was 36.5 months. The 2-year LC, OS, and PFS rates were 98.0 %, 88.8 %, and 55.1 %, respectively. Disease progression was observed in 33 (68.8 %) patients. One patient (0.2 %) had local recurrence, 31 (64.6 %) developed new hepatic lesions outside the irradiation field, and nine (18.8 %) had distant metastases (including overlap). Grade 3 late adverse events were observed in seven patients (14.5 %). No grade 4 or 5 treatment-related toxicity was observed. The median tracking accuracy was 2.9 mm. Conclusion: Employing DTT-SBRT to treat liver tumors results in excellent LC with acceptable adverse-event incidence.

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

PURPOSE: Gross 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. METHODS: Two 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. RESULTS: Both 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). CONCLUSION: Multi-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.

Evaluation of short-term gastrointestinal motion and its impact on dosimetric parameters in stereotactic body radiation therapy for pancreatic cancer.

Background: The aim of this study is to quantify the short-term motion of the gastrointestinal tract (GI-tract) and its impact on dosimetric parameters in stereotactic body radiation therapy (SBRT) for pancreatic cancer. Methods: The analyzed patients were eleven pancreatic cancer patients treated with SBRT or proton beam therapy. To ensure a fair analysis, the simulation SBRT plan was generated on the planning CT in all patients with the dose prescription of 40 Gy in 5 fractions. The GI-tract motion (stomach, duodenum, small and large intestine) was evaluated using three CT images scanned at spontaneous expiration. After fiducial-based rigid image registration, the contours in each CT image were generated and transferred to the planning CT, then the organ motion was evaluated. Planning at risk volumes (PRV) of each GI-tract were generated by adding 5 mm margins, and the volume receiving at least 33 Gy (V33) < 0.5 cm3 was evaluated as the dose constraint. Results: The median interval between the first and last CT scans was 736 s (interquartile range, IQR:624-986). To compensate for the GI-tract motion based on the planning CT, the necessary median margin was 8.0 mm (IQR: 8.0-10.0) for the duodenum and 14.0 mm (12.0-16.0) for the small intestine. Compared to the planned V33 with the worst case, the median V33 in the PRV of the duodenum significantly increased from 0.20 cm3 (IQR: 0.02-0.26) to 0.33 cm3 (0.10-0.59) at Wilcoxon signed-rank test (p = 0.031). Conclusion: The short-term motions of the GI-tract lead to high dose differences.

Selection of motion management in liver stereotactic body radiotherapy and its impact on treatment time.

Background and purpose: Reduction of respiratory tumour motion is important in liver stereotactic body radiation therapy (SBRT) to reduce side effects and improve tumour control probability. We have assessed the distribution of use of voluntary exhale breath hold (EBH), abdominal compression (AC), free breathing gating (gating) and free breathing (FB), and the impact of these on treatment time. Materials and Methods: We assessed all patients treated in a single institution with liver SBRT between September 2017 and September 2021. Data from pre-simulation motion management assessment using fluoroscopic assessment of liver dome position in repeat breath holds, and motion with and without AC, was reviewed to determine liver dome position consistency in EBH and the impact of AC on motion. Treatment time was assessed for all fractions as time from first image acquisition to last treatment beam off. Results: Of 136 patients treated with 145 courses of liver SBRT, 68 % were treated in EBH, 20 % with AC, 7 % in gating and 5 % in FB. AC resulted in motion reduction < 1 mm in 9/26 patients assessed. Median treatment time was higher using EBH (39 min) or gating (42 min) compared with AC (30 min) or FB (24 min) treatments. Conclusions: Motion management in liver SBRT needs to be assessed per-patient to ensure appropriate techniques are applied. Motion management significantly impacts treatment time therefore patient comfort must also be taken into account when selecting the technique for each patient.

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 PURPOSE: The 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 METHODS: We 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. RESULTS: The 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. CONCLUSION: Our 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.