Target Volume Delineation Research Articles

Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application.

Radiotherapy has been demonstrated to be one of the most significant treatments for cervical cancer, during which accurate and efficient delineation of target volumes is critical. To alleviate the data demand of deep learning and promote the establishment and promotion of auto-segmentation models in small and medium-sized oncology departments and single centres, we proposed an auto-segmentation algorithm to determine the cervical cancer target volume in small samples based on multi-decoder and semi-supervised learning (MDSSL), and we evaluated the accuracy via an independent test cohort. In this study, we retrospectively collected computed tomography (CT) datasets from 71 pelvic cervical cancer patients, and a 3:4 ratio was used for the training and testing sets. The clinical target volumes (CTVs) of the primary tumour area (CTV1) and pelvic lymph drainage area (CTV2) were delineated. For definitive radiotherapy (dRT), the primary gross target volume (GTVp) was simultaneously delineated. According to the data characteristics for small samples, the MDSSL network structure based on 3D U-Net was established to train the model by combining clinical anatomical information, which was compared with other segmentation methods, including supervised learning (SL) and transfer learning (TL). The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD) were used to evaluate the segmentation performance. The ability of the segmentation algorithm to improve the efficiency of online adaptive radiation therapy (ART) was assessed via geometric indicators and a subjective evaluation of radiation oncologists (ROs) in prospective clinical applications. Compared with the SL model and TL model, the proposed MDSSL model displayed the best DSC, HD95 and ASD overall, especially for the GTVp of dRT. We calculated the above geometric indicators in the range of the ground truth (head-foot direction). In the test set, the DSC, HD95 and ASD of the MDSSL model were 0.80/5.85mm/0.95mm for CTV1 of post-operative radiotherapy (pRT), 0.84/ 4.88mm/0.73mm for CTV2 of pRT, 0.84/6.58mm/0.89mm for GTVp of dRT, 0.85/5.36mm/1.35mm for CTV1 of dRT, and 0.84/4.09mm/0.73mm for CTV2 of dRT, respectively. In a prospective clinical study of online ART, the target volume modification time (MTime) was 3-5min for dRT and 2-4min for pRT, and the main duration of CTV1 modification was approximately 2min. The introduction of the MDSSL method successfully improved the accuracy of auto-segmentation for the cervical cancer target volume in small samples, showed good consistency with RO delineation and satisfied clinical requirements. In this prospective online ART study, the application of the segmentation model was demonstrated to be useful for reducing the target volume delineation time and improving the efficiency of the online ART workflow, which can contribute to the development and promotion of cervical cancer online ART.

Validation of different automated segmentation models for target volume contouring in postoperative radiotherapy for breast cancer and regional nodal irradiation

IntroductionTarget volume delineation is routinely performed in postoperative radiotherapy (RT) for breast cancer patients, but it is a time-consuming process. The aim of the present study was to validate the quality, clinical usability and institutional-specific implementation of different auto-segmentation tools into clinical routine. MethodsThree different commercially available, artificial intelligence-, ESTRO-guideline-based segmentation models (M1-3) were applied to fifty consecutive reference patients who received postoperative local RT including regional nodal irradiation for breast cancer for the delineation of clinical target volumes: the residual breast, implant or chestwall, axilla levels 1 and 2, the infra- and supraclavicular regions, the interpectoral and internal mammary nodes. Objective evaluation metrics of the created structures were conducted with the Dice similarity index (DICE) and the Hausdorff distance, and a manual evaluation of usability. ResultsThe resulting geometries of the segmentation models were compared to the reference volumes for each patient and required no or only minor corrections in 72 % (M1), 64 % (M2) and 78 % (M3) of the cases. The median DICE and Hausdorff values for the resulting planning target volumes were 0.87–0.88 and 2.96–3.55, respectively. Clinical usability was significantly correlated with the DICE index, with calculated cut-off values used to define no or minor adjustments of 0.82–0.86. Right or left sided target and breathing method (deep inspiration breath hold vs. free breathing) did not impact the quality of the resulting structures. ConclusionArtificial intelligence-based auto-segmentation programs showed high-quality accuracy and provided standardization and efficient support for guideline-based target volume contouring as a precondition for fully automated workflows in radiotherapy treatment planning.

Comment on FET PET-based target volume delineation for the radiotherapy of glioblastoma: A pictorial guide to help overcome methodological pitfalls

Comment on FET PET-based target volume delineation for the radiotherapy of glioblastoma: A pictorial guide to help overcome methodological pitfalls

Patterns of loco-regional progression and patient outcomes after definitive-dose radiation therapy for anaplastic thyroid cancer

BackgroundThe aim of this study is to characterize the patterns of loco-regional progression (LRP) and outcomes after definitive-dose intensity modulated radiation therapy (IMRT) for anaplastic thyroid cancer (ATC) with macroscopic neck disease at the time of IMRT. MethodsDisease/treatment characteristics and outcomes for patients with unresected or incompletely resected ATC who received IMRT (≥45 Gy) were retrospectively reviewed. For those with LRP after IMRT, progressive/recurrent gross tumor volumes (rGTV) were contoured on diagnostic CTs and co-registered with initial planning CTs using deformable image registration. rGTVs were classified based on established spatial/dosimetric criteria. ResultsForty patients treated between 2010–2020 formed the cohort. Median IMRT dose was 66 Gy (45–70 Gy); altered fractionation (AF) was used in 24 (60 %). All received concurrent chemotherapy. In addition to areas of gross disease, target volumes (TVs) commonly included: central compartment/upper mediastinum (levels VI/VII), neck levels II-V in an involved, and levels III-IV in an uninvolved lateral neck. Median overall survival was 7.1 m. Median progression free survival was 7.4 m for patients with locoregional disease and 1.8 m for patients with distant metastasis at the time of IMRT. Twenty-one patients (53 %) developed LRP at median of 10.9 m; freedom from LRP at 3 m and 12 m was 71 % (95 %CI 58–87 %) and 47 % (95 %CI 32–68 %). Forty-one individual rGTVs were identified and most occurred within the high dose (HD) TVs: Type A/central HD (n = 29, 71 %) and B/peripheral HD (n = 3, 7 %). ConclusionsDespite an intensive treatment schedule, including AF and concurrent chemotherapy, classic radio-resistant and rapid Type A failures predominated; isolated extraneous dose failures were rare. While these findings support the IMRT and TV delineation strategies described herein, they highlight the importance of identifying novel strategies to further improve LRC for patients with unresectable disease without targetable mutations for contemporary neo-adjuvant strategies.

3D target definition and initial results from the electroanatomic substrate-guided stereotactic ablative radiotherapy for refractory ventricular tachycardia (ELSTAR-VT)

Abstract Background/introduction Noninvasive stereotactic radiotherapy (STAR) is an emerging transmural ablative therapy for refractory ventricular tachycardia (VT). Delineation of the arrhythmogenic gross target volume (GTV) relies on electrical (exit and isthmus) VT characteristics and anatomical scar detailing. 17-AHA segmental approaches or eyeballing techniques are adopted to transfer the GTV to the treatment planning CT. An individualized 3D GTV delineated with ADAS3D based on the areas of interest of each modality could lead to a smaller GTV compared to 17-AHA segmental approaches. Purpose We investigated whether our workflow using ADAS3D for the delineating of the GTV renders smaller GTV compared to 17-AHA segmental approaches whilst remaining effective for VT treatment during follow-up. Methods We targeted 3D-personalized GTV with STAR in patients with refractory VT in structural heart disease. Electroanatomical detailing was achieved by combining high-resolution invasive and noninvasive (ECG imaging during noninvasive programmed stimulation) mapping, combined with wall thickness analyses by cardiac CT. After coregistration in ADAS3D, a 3D DICOM-radiation therapy file including the delineated target volume was generated and transferred into the free-breathing and respiration-corrected 4D CT scan. Standard STAR using a single-fraction of 20-25 Gy was applied. We compared conventional (17-AHA segmental approaches) versus 3D-based GTV demarcation, and assessed VT burden and procedural safety. Results From January 2023 to February 2024 STAR was successfully performed in three patients (all male, mean age 73±1 years, two ischemic cardiomyopathy, one laminopathy) with persistent VT despite ≥2 catheter-based (endocardial/epicardial) ablation procedures. The 3D-derived GTVs showed a statistical trend towards smaller volumes compared to conventional segmental delineation (11±4 versus 21±3 cm3, p=0.07). VT burden and ICD therapy was reduced by 100% over 9 patients-months (8-week blanking period). No acute or subacute adverse events occurred. One patient died of progressive heart failure. Conclusion 3D-individualized target volume annotation may hold promise for effective and safe STAR employment.ELSTAR workflow

Interobserver variability of clinical target volume delineation in patients undergoing breast-conserving surgery without surgical clips: a pilot study on preoperative magnetic resonance simulation

BackgroundIn patients undergoing breast-conserving therapy without surgical clip implantation, the accuracy of tumor bed identification and the consistency of clinical target volume (CTV) delineation under computed tomography (CT) simulation remain suboptimal. This study aimed to investigate the feasibility of implementing preoperative magnetic resonance (MR) simulation on delineations by assessing interobserver variability (IOV).MethodsPreoperative MR and postoperative CT simulations were performed in patients who underwent breast-conserving surgery with no surgical clips implanted. Custom immobilization pads were used to ensure the same supine position. Three radiation oncologists independently delineated the CTV of tumor bed on the images acquired from MR and CT simulation registration and CT simulation alone. Cavity visualization score (CVS) was assigned to each patient based on the clarity of the tumor bed on CT simulation images. IOV was indicated by generalized conformity index (CIgen), denoted as CIgen−CT and CIgen−MR/CT, and the distance between the centroid of mass (dCOM), denoted as dCOMCT and dCOMMR/CT. The variation of IOV in different CVS subgroups was analyzed.ResultsA total of 10 patients were enrolled in this study. The median and interquartile range (IQR) of maximum pathological diameter of the tumors in all patients were 1.55 (0.80–1.92) cm. No statistical significance was found between the volumes of CTVs on CT simulation and on MR/CT simulation registration images (p = 0.387). CIgen−MR/CT was significantly larger than CIgen−CT (p = 0.005). dCOMMR/CT was significantly smaller than dCOMCT (p = 0.037). The median and IQR of CVS in all patients were 2.34 (2.00–3.08). The difference of CIgen between CIgen−MR/CT and CIgen−CT was larger in the low CVS group (p = 0.016). The difference of dCOM showed a decreasing trend when CVS was lower, although it did not reach statistical significance (p = 0.095).ConclusionsFor patients who underwent breast-conserving surgery without surgical clip implantation, the use of preoperative MR simulation in delineating the CTV of tumor bed decreased the IOV among observers. The consistency of tumor bed identification was improved especially in cases where the margins of tumor bed were challenging to visualize on CT simulation images. The study findings offer potential benefits in reducing local recurrence and minimizing tissue irritation in the surrounding areas. Future investigation in a larger patient cohort to validate our results is warranted.

Artificial intelligence-assisted delineation for postoperative radiotherapy in patients with lung cancer: a prospective, multi-center, cohort study

BackgroundPostoperative radiotherapy (PORT) is an important treatment for lung cancer patients with poor prognostic features, but accurate delineation of the clinical target volume (CTV) and organs at risk (OARs) is challenging and time-consuming. Recently, deep learning-based artificial intelligent (AI) algorithms have shown promise in automating this process.ObjectiveTo evaluate the clinical utility of a deep learning-based auto-segmentation model for AI-assisted delineating CTV and OARs in patients undergoing PORT, and to compare its accuracy and efficiency with manual delineation by radiation oncology residents from different levels of medical institutions.MethodsWe previously developed an AI auto-segmentation model in 664 patients and validated its contouring performance in 149 patients. In this multi-center, validation trial, we prospectively involved 55 patients and compared the accuracy and efficiency of 3 contouring methods: (i) unmodified AI auto-segmentation, (ii) fully manual delineation by junior radiation oncology residents from different medical centers, and (iii) manual modifications based on AI segmentation model (AI-assisted delineation). The ground truth of CTV and OARs was delineated by 3 senior radiation oncologists. Contouring accuracy was evaluated by Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean distance of agreement (MDA). Inter-observer consistency was assessed by volume and coefficient of variation (CV).ResultsAI-assisted delineation achieved significantly higher accuracy compared to unmodified AI auto-contouring and fully manual delineation by radiation oncologists, with median HD, MDA, and DCS values of 20.03 vs. 21.55 mm, 2.57 vs. 3.06 mm, 0.745 vs. 0.703 (all P<0.05) for CTV, respectively. The results of OARs contours were similar. CV for OARs was reduced by approximately 50%. In addition to better contouring accuracy, the AI-assisted delineation significantly decreased the consuming time and improved the efficiency.ConclusionAI-assisted CTV and OARs delineation for PORT significantly improves the accuracy and efficiency in the real-world setting, compared with pure AI auto-segmentation or fully manual delineation by junior oncologists. AI-assisted approach has promising clinical potential to enhance the quality of radiotherapy planning and further improve treatment outcomes of patients with lung cancer.

PATTERNS OF RADIOTHERAPY PRACTICE FOR FUNCTIONING PITUITARY TUMOURS - A SURVEY OF UK CENTRES

Abstract AIMS Pituitary adenomas are benign tumours that are classified as functioning or non-functioning based on the production of excess pituitary hormones. Functioning adenomas (FA) typically present as hypersecretory syndromes including acromegaly and Cushing’s disease. In FA, radiotherapy is used when surgery fails to achieve hormone normalisation and/or when medical treatment does not control hormone excess. In the absence of prospective studies that clearly define the optimal radiotherapy technique in FA, it is expected that there will be variability in practice. A survey of UK neuro-oncology centres was undertaken, aiming to establish the extent of this variability in FA. METHOD A survey was distributed electronically to 20 neuro-oncology departments across the UK. Data were collected on patient numbers, radiotherapy indications, techniques, dosing, and target volume delineation. RESULTS Responses were received from eight centres (40% response rate), treating a total of approximately 32 FA per annum. There was variability in techniques employed to treat FA. While four centres treated most FA with IMRT, two treat most with stereotactic radiosurgery (SRS), and two with fractionated stereotactic radiotherapy (fSRT). The most common dose used for IMRT treatment was 45Gy in 25 fractions (n=7), with 50.4Gy in 28 fractions, 50Gy in 30 fractions and 54Gy in 30 fractions also reported. Use of margins around residual disease (n=5) and inclusion of involved cavernous sinuses and surgical tract (n=3) within clinical target volumes also varied. Most centres (n=7) would agree to a change in target volume delineation practices for the purpose of a clinical trial in FA. CONCLUSION This survey found that there is variability in radiotherapy dosing, technique, and target volume delineation practices for radiotherapy to FA across the UK. All centres but one would accept changes in their practice within the context of a prospective clinical trial of radiotherapy for FA.

Clinical target volume (CTV) automatic delineation using deep learning network for cervical cancer radiotherapy: A study with external validation.

To explore the accuracy and feasibility of a proposed deep learning (DL) algorithm for clinical target volume (CTV) delineation in cervical cancer radiotherapy and evaluate whether it can perform well in external cervical cancer and endometrial cancer cases for generalization validation. A total of 332 patients were enrolled in this study. A state-of-the-art network called ResCANet, which added the cascademulti-scale convolution in the skip connections to eliminate semantic differences between different feature layers based on ResNet-UNet. The atrous spatial pyramid pooling in the deepest feature layer combined the semantic information of different receptive fields without losing information. A total of 236 cervical cancer cases were randomly grouped into 5-fold cross-training (n=189) and validation (n=47) cohorts. External validations were performed ina separate cohort of 54 cervical cancer and 42 endometrial cancer cases. The performances of the proposed network were evaluated by dice similarity coefficient (DSC), sensitivity (SEN), positive predictive value (PPV), 95% Hausdorff distance (95HD), and oncologist clinical score when comparing them with manual delineation in validation cohorts. In internal validation cohorts, the mean DSC, SEN, PPV, 95HD for ResCANet achieved 74.8%, 81.5%, 73.5%, and 10.5mm. In external independent validation cohorts, ResCANet achieved 73.4%, 72.9%, 75.3%, 12.5mm for cervical cancer cases and 77.1%, 81.1%, 75.5%, 10.3mm for endometrial cancer cases, respectively. The clinical assessment score showed that minor and no revisions (delineation time was shortened to within 30min) accountedforabout 85% of all cases in DL-aided automatic delineation. We demonstrated the problem of model generalizability for DL-based automatic delineation. The proposed network can improve the performance of automatic delineation for cervical cancer and shorten manual delineation time at no expense to quality. The network showed excellent clinical viability, which can also be even generalized for endometrial cancer with excellent performance.

Investigation of the distribution of inguinal lymph nodes and delineation of the inguinal clinical target volume using 18F-FDG PET/CT

ObjectiveRadiotherapy is a crucial treatment modality for pelvic cancers, but uncertainties persist in defining the clinical target volume (CTV) for the inguinal lymphatic drainage region. Suboptimal CTV delineation may compromise treatment efficacy and result in subpar disease control. This study aimed to investigate and map the distribution of lymph node metastases (LNM) in the groin area to facilitate an improved and detailed CTV definition using 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT).MethodsInguinal LNM in patients with biopsy-proven pelvic malignancies were identified using 18F-FDG PET/CT scan. The longitudinally nearest axial plane was determined based on six typical bony landmarks, and the axial direction relative to the femoral artery of LNM was recorded. The distances from the LNM to the nearest edge of the femoral artery were measured on the axial plane. An optimal margin to cover 95% of LNM was estimated to develop contouring recommendations.ResultsIn this study, 500 positive LNM were identified by 18F-FDG PET/CT among 185 patients with primary pelvic malignancies. Relative to the femoral artery, lymph nodes were distributed laterally (10:00–11:00, n = 35), anteriorly (12:00–1:00, n = 213), and medially (2:00–4: 00, n = 252). For CTV delineation, the recommended distances from the femoral artery on the SFH were lateral 19 mm, anterior 19 mm, and medial 25 mm; on the SGT were lateral 26 mm, anterior 20 mm, and medial 25 mm; on the SPS were lateral 28 mm, anterior 29 mm, and medial 26 mm; on the IPS were anterior 29 mm and medial 28 mm; on the IIT were anterior 27 mm and medial 27 mm; on the ILT were anterior 25 mm and medial 23 mm. Use interpolation to contour the area between six axial slices, including any radiographically suspicious LNM.ConclusionsUsing 18F-FDG PET/CT, we investigated the distribution pattern of inguinal LNM and propose a more comprehensive guideline for inguinal CTV delineation.

Regularity and correlation analysis of regional lymph node metastasis in nonoperative patients with non-small cell lung cancer based on positron emission tomography/computed tomography images

BackgroundDefinitive concurrent chemoradiotherapy (CCRT) is the standard treatment for locally advanced, inoperable non-small cell lung cancer (NSCLC). Previous studies have mainly focused on examining local failure and recurrence patterns after surgery and the principles of lymph node metastasis (LNM) in surgical candidates with NSCLC. However, these studies were just only able to guide postoperative radiotherapy (PORT) and the patterns of LNM in patients with resected NSCLC was inadequate to represent that in locally advanced inoperable NSCLC patients for guiding target volume delineation of CCRT. In this study, we aimed to analyze the metastasis regularities and establish the correlations between different lymph node levels in NSCLC patients without any intervention using positron emission tomography/computed tomography (PET/CT) images.MethodsOverall, 358 patients with N1–N3 NSCLC admitted in our hospital between 2018 and 2022 were retrospectively analyzed. The diagnosis of metastatic lymph nodes was reviewed and determined using the European Organization for Research and Treatment of Cancer standard and the standardized value of the PET/CT examination. Univariate and multivariate analysis were performed to investigate the correlations between the different levels were evaluated by using of the chi-square test and logistic regression model.ResultsThe lymph nodes with the highest metastasis rates in patients with left lung cancer were in order as follows: 10L, 4L, 5, 4R, and 7; while in those with right lung cancer they were 10R, 4R, 7, 2R, and 1R. Notably, we found left lung patients were more likely to have contralateral hilar, mediastinal and supraclavicular lymph nodes involved, and the right lung group exhibited a higher propensity for ipsilateral mediastinum and supraclavicular lymph node invasion. Furthermore, correlation analysis revealed there were significant correlative patterns in the LNM across different levels.ConclusionsThis study elucidated the patterns of primary LNM in patients with NSCLC who had not undergone surgery (without any treatment interventions) and the correlations between lymph node levels. These findings were expected to provide useful reference for target volume delineation in definitive concurrent chemoradiotherapy in locally advanced NSCLC patients.

Delineation of target volume by radiation therapists during online adaptive radiation therapy: What authorization?

The evolution of radiation therapy techniques goes hand in hand with the evolution of the profession of radiation therapist. In the particular context of online adaptive radiotherapy based on cone beam computed tomography images, delegation of certain tasks from the physician to the radiation therapist is possible within the framework of a cooperation protocol. This delegation requires prior theoretical and practical training. It enriches the practice of radiation therapists by allowing them to acquire new skills and greater autonomy. It foreshadows access for radiation therapists to advanced practice.

ESTRO-EANO guideline on target delineation and radiotherapy for IDHmutant WHO CNS grade 2 and 3 diffuse glioma

PurposeThis guideline will discuss radiotherapeutic management of IDH mutant grade 2 and grade 3 diffuse glioma, using the latest 2021 WHO (5th) classification of brain tumours focusing on: imaging modalities, tumour volume delineation, irradiation dose and fractionation. MethodsThe ESTRO Guidelines Committee, CNS subgroup, nominated 15 European experts who identified questions for this guideline. Four working groups were established addressing specific questions concerning imaging, target volume delineation, radiation techniques and fractionation. A literature search was performed, and available literature was discussed. A modified two-step Delphi process was used with majority voting resulted in a decision or highlighting areas of uncertainty. ResultsKey issues identified and discussed included imaging needed to define target definition, target delineation and the size of margins, and technical aspects of treatment including different planning techniques such as proton therapy. ConclusionsThe GTV should include any residual tumour volume after surgery, as well as the resection cavity. Enhancing lesions on T1 imaging should be included if they are indicative of residual tumour. In grade 2 tumours, T2/FLAIR abnormalities should be included in the GTV. In grade 3 tumours, T2/FLAIR abnormalities should also be included, except areas that are considered to be oedema which should be omitted from the GTV. A GTV to CTV expansion of 10 mm is recommended in grade 2 tumours and 15 mm in grade 3 tumours. A treatment dose of 50.4 Gy in 28 fractions is recommended in grade 2 tumours and 59.4 Gy in 33 fractions in grade 3 tumours. Radiation techniques with IMRT are the preferred approach.

Adjuvant Radiotherapy in Bladder Cancers: A dosimetric study focusing on ileal conduit sparing

PurposeTo compare ileal conduit (IC) and other organ at risk (OAR) dosimetry between treatment techniques in a prospective cohort of patients planned for adjuvant radiotherapy (RT) after radical cystectomy and IC reconstruction. Methods and materialsCT datasets of twenty patients who underwent adjuvant RT were obtained and used prospectively for delineation of target volumes (primary and nodal) and organs at risk, including IC, uretero-ileal anastomosis and ileal stoma using a specified protocol for simulation including a delayed CT to identify IC. Three RT plans were generated for each patient for a dose of 54 gray (Gy) in 27 fractions (PTV V95% >95%): 3-dimensional conformal radiotherapy (3DCRT) with (3DCRT_S) and without (3DCRT_N) stoma shielding, and volumetric modulated arc therapy (VMAT), with OAR constraints specified for VMAT plans (IC: Dmax<54Gy, V50Gy<20cc). Constraints were given for other pelvic OARs (bowel, rectum, femur heads as per published literature.Plans were evaluated for target coverage as well as OAR doses; in particular, IC and stoma). ANOVA test was used to compare medians of achieveddoses, and a p-value <0.05 was statistically significant. ResultsThe median IC volume was 63.34 (55.29-82.93) cc. The cranial end of IC was at L5 or L4 vertebral level in 95% of patients and caudal level at S2 or S3 in 80% of patients. In contrast, the ileal stoma spanned from L4 or L5 vertebral level cranially (100%) toL5 level caudally (80%). PTV V95% was similar for 3DCRT_N and VMAT plans while it was significantly lower in 3DCRT_S in areas of ileal stoma shielding (99.95% vs 99.01% vs 96.29%, p<0.01). Median IC V50 Gy was comparable in 3DCRT_N (38.81 cc) and 3DCRT_S (35.62 cc) while it was significantly lower in the VMAT plan (17.05 cc, p<0.01). IC Dmax did not differ significantly between the 3 plans. On the other hand, when 3DCRT_N, 3DCRT_S, and VMAT plans were compared for ileal stoma doses, Dmean was comparable (11.93 Gy vs 7.41 Gy vs 9.54 Gy, p=0.06) while Dmax was significantly higher for 3DCRT_N plan and least for VMAT plan (35.32 Gy vs 27.57 Gy vs 24.22 Gy, p<0.01). VMAT plans fared significantly better for uretero-ileal anastomosis, bowel, and rectal dosimetry. ConclusionIleal stoma shielding in 3DCRT compromises PTV coverage but does not spare IC effectively. Sparing IC with VMAT is feasiblewithout compromising PTV coverage. Dosimetric gains with VMAT are expected to benefit patients needing higher pelvic RT doses and nodalRT by reducing the risk of anastomotic and mucosal complications. Clinical benefits should be evaluated in a prospective protocol.

On the trail of CBCT-guided adaptive rectal boost radiotherapy, does daily delineation require a radiation oncologist?

IntroductionDose-escalation radiotherapy for rectal tumours is increasingly considered as a non-operative approach, with online-adaptive radiotherapy (oART) supporting this approach by correcting inter-fraction tumour position errors. However, using cone-beam computed tomography (CBCT)-guided oART requires daily target volume delineation by different operators, leading to inter-operator delineation variability and potential dosimetric issues. This study aims to compare and quantify the inter-operator and inter-professional delineation variability of the rectal boost volume on CBCT, including volumes by an automatically delineated oART treatment planning system. Materials and methodsA rectal boost volume, defined as the primary tumour extended to the entire adjacent rectal wall, was delineated on 10 CBCTs from 5 patients by 15 operators: 4 expert radiation oncologists (ROs), 4 radiation therapists (RTTs) and 7 non-expert ROs. These contours were compared between the different professional groups. A comparison to the average volume of the group (ROs, RTTs, or non-expert ROs) with the lowest delineation variability was also performed for each individual volume including the volume automatically generated by an oART treatment planning system. ResultsDelineation variability was the highest in the superior (range: 2.3–6.0 mm), and inferior (2.3–12.4 mm) directions, compared to the left (0.2–4.4 mm), right (0.3–2.0 mm), anterior (0.1–2.9 mm), and posterior (0.5–4.0 mm) directions. Non-expert ROs, RTTs, and automatic oART volume showed similar ranges of delineation errors when compared to the expert ROs’ volume, which was chosen as reference volume since this professional group showed the lowest variability. DiscussionExpert ROs showed consistent results. Other professional groups exhibit similar variability, comparable to the automatic oART volume. Therefore, RTTs could safely perform the rectal boost delineation without non-expert ROs supervision in the absence of expert ROs during CBCT-based oART. Moreover, these findings provide quantitative data to compute accurate margins for the rectal boost planning target volume in a CBCT-guided oART workflow.

Neoadjuvant radiation target volume definition in esophageal squamous cell cancer: a multicenter recommendations from Chinese experts

BackgroundThis study aimed to establish a consensus on the delineation of target volumes for neoadjuvant radiation therapy (nRT) in esophageal squamous cell carcinoma (ESCC) within China.MethodsFrom February 2020 to June 2021, nine ESCC patients who received nRT were retrospectively selected from Sun Yat-sen University Cancer Center and Shandong Cancer Hospital. A panel from eight cancer radiotherapy centers performed two rounds of nRT target volume delineation for these patients: the first round for cases 1–6 and the second for cases 7–9. Online meetings were held after each delineation round to discuss findings. The consistency of delineations across centers was compared using mean undirected Hausdorff distances (Hmean), dice similarity coefficients (DSC), and total volumes, analyzed with the Mann-Whitney U test.ResultsThe second round of delineations showed improved consistency across centers (total clinical target volume (CTVtotal): mean DSC = 0.76–0.81; mean Hmean = 2.11–3.14 cm) compared to the first round (CTVtotal: mean DSC = 0.63–0.64; mean Hmean = 5.66–7.34 cm; DSC and Hmean: P < 0.050 between rounds), leading to the formation of a consensus and an atlas for ESCC nRT target volume delineation. A proposal was reached through evaluating target volume delineations, analyzing questionnaire survey outcomes, and reviewing pertinent literature.ConclusionsWe have developed guidelines and an atlas for target volume delineation in nRT therapy for ESCC in China. These resources are designed to facilitate more consistent delineation of target volumes in both clinical practice and clinical trials.

2603: Onet: Contrast-enhanced CT assisted automatic clinical target volume delineation of prostate cancer

2603: Onet: Contrast-enhanced CT assisted automatic clinical target volume delineation of prostate cancer

Impact of the Novel MRI Contrast Agent Gadopiclenol on Radiotherapy Decision Making in Patients With Brain Metastases.

The aim of this study was to assess the effect of gadopiclenol versus gadobenate dimeglumine contrast-enhanced magnetic resonance imaging (MRI) on decision-making between whole-brain radiotherapy (WBRT) and stereotactic radiosurgery (SRS) for treatment of brain metastases (BMs). Patients with BMs underwent 2 separate MRI examinations in a double-blind crossover phase IIb comparative study between the MRI contrast agents gadopiclenol and gadobenate dimeglumine, both administered at 0.1 mmol/kg. The imaging data of a single site using identical MRI scanners and protocols were included in this post hoc analysis. Patients with 1 or more BMs in any of both MRIs were subjected to target volume delineation for treatment planning. Two radiation oncologists contoured all visible lesions and decided upon SRS or WBRT, according to the number of metastases. For each patient, SRS or WBRT treatment plans were calculated for both MRIs, considering the gross target volume (GTV) as the contrast-enhancing aspects of the tumor. Mean GTVs and volume of healthy brain exposed to 12 Gy (V12), as well as Dice similarity coefficient scores, were obtained. The Spearman rank (ρ) correlation was additionally calculated for assessing linear differences. Three different expert radiation oncologists blindly rated the contrast enhancement for contouring purposes. Thirteen adult patients were included. Gadopiclenol depicted additional BM as compared with gadobenate dimeglumine in 7 patients (54%). Of a total of 63 identified metastatic lesions in both MRI sets, 3 subgroups could be defined: A, 48 (24 pairs) detected equal GTVs visible in both modalities; B, 13 GTVs only visible in the gadopiclenol set (mean ± SD, 0.16 ± 0.37 cm3); and C, 2 GTVs only visible in the gadobenate dimeglumine set (mean ± SD, 0.01 ± 0.01). Treatment indication was changed for 2 (15%) patients, 1 from no treatment to SRS and for 1 from SRS to WBRT. The mean GTVs and brain V12 were comparable between both agents (P = 0.694, P = 0.974). The mean Dice similarity coefficient was 0.70 ± 0.14 (ρ = 0.82). According to the readers, target volume definition was improved in 63.9% of cases (23 of 36 evaluations) with gadopiclenol and 22.2% with gadobenate dimeglumine (8 of 36), whereas equivalence was obtained in 13.9% (5 of 36). Gadopiclenol-enhanced MRI improved BM detection and characterization, with a direct impact on radiotherapy treatment decision between WBRT and SRS. Additionally, a more exact target delineation and planning could be performed with gadopiclenol. A prospective evaluation in a larger cohort of patients is required to confirm these findings.

517 Delineation of Clinical Target Volumes (CTV) for Nasopharyngeal Carcinoma – Revisited

517 Delineation of Clinical Target Volumes (CTV) for Nasopharyngeal Carcinoma – Revisited

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.