CT-based delineation of organs at risk in the head and neck region: DAHANCA, EORTC, GORTEC, HKNPCSG, NCIC CTG, NCRI, NRG Oncology and TROG consensus guidelines

Brouwer, Charlotte L.; Steenbakkers, Roel J.H.M.; Bourhis, Jean; Budach, Wilfried; Grau, Cai; Grégoire, Vincent; Herk, Marcel van; Lee, Anne; Maingon, P.; Nutting, Chris; O’Sullivan, Brian; Porceddu, Sandro; Rosenthal, David I.; Sijtsema, Nanna M.; Langendijk, Johannes A.

doi:10.1016/j.radonc.2015.07.041

Cited by 440 publications

(271 citation statements)

References 23 publications

Supporting

Mentioning

268

Contrasting

Order By: Relevance

“…The contour data for the cases were previously created by the dosimetrists in the process of routine RT planning of these patients. Following published guidelines [1, 7] for H&N anatomic object definitions, we formulated detailed and precise computational definitions for specifying each object and for delineating its boundaries on axial CT slices and mended the contours to fit these strict definitions as much as possible.…”

Section: Methodsmentioning

confidence: 99%

“…In clinical practice, this delineation is done mostly manually by dosimetrists and radiation oncologists, which is time-consuming and suffers from intra- and inter- observer variations as well as protocol variability [1] from center to center. As an alternative, auto-contouring is a useful tool that could bring substantial time reduction even if post hoc manual editing is required [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Auto-contouring via automatic anatomy recognition of organs at risk in head and neck cancer on CT images

Udupa

Tong

et al. 2018

Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

Contouring of the organs at risk is a vital part of routine radiation therapy planning. For the head and neck (H&N) region, this is more challenging due to the complexity of anatomy, the presence of streak artifacts, and the variations of object appearance. In this paper, we describe the latest advances in our Automatic Anatomy Recognition (AAR) approach, which aims to automatically contour multiple objects in the head and neck region on planning CT images. Our method has three major steps: model building, object recognition, and object delineation. First, the better-quality images from our cohort of H&N CT studies are used to build fuzzy models and find the optimal hierarchy for arranging objects based on the relationship between objects. Then, the object recognition step exploits the rich prior anatomic information encoded in the hierarchy to derive the location and pose for each object, which leads to generalizable and robust methods and mitigation of object localization challenges. Finally, the delineation algorithms employ local features to contour the boundary based on object recognition results. We make several improvements within the AAR framework, including finding recognition-error-driven optimal hierarchy, modeling boundary relationships, combining texture and intensity, and evaluating object quality. Experiments were conducted on the largest ensemble of clinical data sets reported to date, including 216 planning CT studies and over 2,600 object samples. The preliminary results show that on data sets with minimal (<4 slices) streak artifacts and other deviations, overall recognition accuracy reaches 2 voxels, with overall delineation Dice coefficient close to 0.8 and Hausdorff Distance within 1 voxel.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Auto-contouring via automatic anatomy recognition of organs at risk in head and neck cancer on CT images

Udupa

Tong

et al. 2018

Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

show abstract

“…We developed precise definitions of 11 key organs at risk (OARs) [5], by extending object definitions from recent guidelines [3,4], and modified contour data to fulfill these definitions. This turned out to a very arduous task since adherence to definitions is loose and the guidelines had many gaps which prevented them from being used directly for computational modeling of objects which require precise definitions.…”

Section: Methodsmentioning

confidence: 99%

Image quality and segmentation

Pednekar

Udupa

McLaughlin

et al. 2018

Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

Algorithms for image segmentation (including object recognition and delineation) are influenced by the quality of object appearance in the image and overall image quality. However, the issue of how to perform segmentation evaluation as a function of these quality factors has not been addressed in the literature. In this paper, we present a solution to this problem. We devised a set of key quality criteria that influence segmentation (global and regional): posture deviations, image noise, beam hardening artifacts (streak artifacts), shape distortion, presence of pathology, object intensity deviation, and object contrast. A trained reader assigned a grade to each object for each criterion in each study. We developed algorithms based on logical predicates for determining a 1 to 10 numeric quality score for each object and each image from reader-assigned quality grades. We analyzed these object and image quality scores (OQS and IQS, respectively) in our data cohort by gender and age. We performed recognition and delineation of all objects using recent adaptations [8, 9] of our Automatic Anatomy Recognition (AAR) framework [6] and analyzed the accuracy of recognition and delineation of each object. We illustrate our method on 216 head & neck and 211 thoracic cancer computed tomography (CT) studies.

show abstract

“…Organs at risk will be delineated according to published international consensus guidelines [21]. Standardized naming of target volumes and organs at risk will facilitate inter-institutional data analysis in this multicenter trial [22].…”

Section: Methodsmentioning

confidence: 99%

Uniform FDG-PET guided GRAdient Dose prEscription to reduce late Radiation Toxicity (UPGRADE-RT): study protocol for a randomized clinical trial with dose reduction to the elective neck in head and neck squamous cell carcinoma

et al. 2017

View full text Add to dashboard Cite

BackgroundIn definitive radiation therapy for head and neck cancer, clinically uninvolved cervical lymph nodes are irradiated with a so-called ‘elective dose’ in order to achieve control of clinically occult metastases. As a consequence of high-resolution diagnostic imaging, occult tumor volume has significantly decreased in the last decades. Since the elective dose is dependent on occult tumor volume, the currently used elective dose may be higher than necessary.Because bilateral irradiation of the neck contributes to dysphagia, xerostomia and hypothyroidism in a dose dependent way, dose de-escalation to these regions can open a window of opportunity to reduce toxicity and improve quality of life after treatment.MethodsUPGRADE-RT is a multicenter, phase III, single-blinded, randomized controlled trial.Patients to be treated with definitive radiation therapy for a newly diagnosed stage T2-4 N0-2 M0 squamous cell carcinoma of the oropharynx, hypopharynx or larynx are eligible. Exclusion criteria are recurrent disease, oncologic surgery to the head and neck area, concomitant chemotherapy or epidermal growth factor receptor inhibitors.In total, 300 patients will be randomized in a 2:1 ratio to a treatment arm with or without de-escalation of the elective radiation dose and introduction of an intermediate dose-level for selected lymph nodes. Radiation therapy planning FDG-PET/CT-scans will be acquired to guide risk assessment of borderline-sized cervical nodes that can be treated with the intermediate dose level.Treatment will be given with intensity-modulated radiation therapy or volumetric arc therapy with simultaneous-integrated boost using an accelerated fractionation schedule, 33 fractions in 5 weeks. The primary endpoint is ‘normalcy of diet’ at 1 year after treatment (toxicity). The secondary endpoint is the actuarial rate of recurrence in electively irradiated lymph nodes at 2 years after treatment (safety).DiscussionThe objective of the UPGRADE-RT trial is to investigate whether de-escalation of elective radiation dose and the introduction of an intermediate dose-level for borderline sized lymph nodes in the treatment of head and neck cancer will result in less radiation sequelae and improved quality of life after treatment without compromising the recurrence rate in the electively treated neck.Trial registrationClinicalTrials.gov Identifier: NCT02442375.

show abstract

CT-based delineation of organs at risk in the head and neck region: DAHANCA, EORTC, GORTEC, HKNPCSG, NCIC CTG, NCRI, NRG Oncology and TROG consensus guidelines

Abstract: Consensus guidelines for head and neck OAR delineation were defined, aiming to decrease interobserver variability among clinicians and radiotherapy centers.

Cited by 440 publications

References 23 publications

Auto-contouring via automatic anatomy recognition of organs at risk in head and neck cancer on CT images

Auto-contouring via automatic anatomy recognition of organs at risk in head and neck cancer on CT images

Image quality and segmentation

Uniform FDG-PET guided GRAdient Dose prEscription to reduce late Radiation Toxicity (UPGRADE-RT): study protocol for a randomized clinical trial with dose reduction to the elective neck in head and neck squamous cell carcinoma

Contact Info

Product

Resources

About