Dataset Information

Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study.

ABSTRACT: Accurate organ-at-risk (OAR) segmentation is critical to reduce radiotherapy complications. Consensus guidelines recommend delineating over 40 OARs in the head-and-neck (H&N). However, prohibitive labor costs cause most institutions to delineate a substantially smaller subset of OARs, neglecting the dose distributions of other OARs. Here, we present an automated and highly effective stratified OAR segmentation (SOARS) system using deep learning that precisely delineates a comprehensive set of 42 H&N OARs. We train SOARS using 176 patients from an internal institution and independently evaluate it on 1327 external patients across six different institutions. It consistently outperforms other state-of-the-art methods by at least 3-5% in Dice score for each institutional evaluation (up to 36% relative distance error reduction). Crucially, multi-user studies demonstrate that 98% of SOARS predictions need only minor or no revisions to achieve clinical acceptance (reducing workloads by 90%). Moreover, segmentation and dosimetric accuracy are within or smaller than the inter-user variation.

SUBMITTER: Ye X

PROVIDER: S-EPMC9576793 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study.

Ye Xianghua X Guo Dazhou D Ge Jia J Yan Senxiang S Xin Yi Y Song Yuchen Y Yan Yongheng Y Huang Bing-Shen BS Hung Tsung-Min TM Zhu Zhuotun Z Peng Ling L Ren Yanping Y Liu Rui R Zhang Gong G Mao Mengyuan M Chen Xiaohua X Lu Zhongjie Z Li Wenxiang W Chen Yuzhen Y Huang Lingyun L Xiao Jing J Harrison Adam P AP Lu Le L Lin Chien-Yu CY Jin Dakai D Ho Tsung-Ying TY

Nature communications 20221017 1

Accurate organ-at-risk (OAR) segmentation is critical to reduce radiotherapy complications. Consensus guidelines recommend delineating over 40 OARs in the head-and-neck (H&N). However, prohibitive labor costs cause most institutions to delineate a substantially smaller subset of OARs, neglecting the dose distributions of other OARs. Here, we present an automated and highly effective stratified OAR segmentation (SOARS) system using deep learning that precisely delineates a comprehensive set of 42 ...[more]

PMID: 36253346

Similar Datasets

Project description:BackgroundIn radiotherapy inaccuracy in organ at risk (OAR) delineation can impact treatment plan optimisation and treatment plan evaluation. Brouwer et al. showed significant interobserver variability (IOV) in OAR delineation in head and neck cancer (HNC) and published international consensus guidelines (ICG) for OAR delineation in 2015. The aim of our study was to evaluate IOV in the presence of these guidelines.MethodsHNC radiation oncologists (RO) from each Belgian radiotherapy centre were invited to complete a survey and submit contours for 5 HNC cases. Reference contours (OARref) were obtained by a clinically validated artificial intelligence-tool trained using ICG. Dice similarity coefficients (DSC), mean surface distance (MSD) and 95% Hausdorff distances (HD95) were used for comparison.ResultsFourteen of twenty-two RO (64%) completed the survey and submitted delineations. Thirteen (93%) confirmed the use of delineation guidelines, of which six (43%) used the ICG. The OARs whose delineations agreed best with the OARref were mandible [median DSC 0.9, range (0.8-0.9); median MSD 1.1 mm, range (0.8-8.3), median HD95 3.4 mm, range (1.5-38.7)], brainstem [median DSC 0.9 (0.6-0.9); median MSD 1.5 mm (1.1-4.0), median HD95 4.0 mm (2.3-15.0)], submandibular glands [median DSC 0.8 (0.5-0.9); median MSD 1.2 mm (0.9-2.5), median HD95 3.1 mm (1.8-12.2)] and parotids [median DSC 0.9 (0.6-0.9); median MSD 1.9 mm (1.2-4.2), median HD95 5.1 mm (3.1-19.2)]. Oral cavity, cochleas, PCMs, supraglottic larynx and glottic area showed more variation. RO who used the consensus guidelines showed significantly less IOV (p = 0.008).ConclusionsAlthough ICG for delineation of OARs in HNC exist, they are only implemented by about half of RO participating in this study, which partly explains the delineation variability. However, this study highlights that guidelines alone do not suffice to eliminate IOV and that more effort needs to be done to accomplish further treatment standardisation, for example with artificial intelligence.

Project description:Background and purposeDysphagia is a common, severe and dose-limiting toxicity after oncological treatment of head and neck cancer (HNC). This study aims to investigate relationships between radiation doses to structures involved in normal swallowing and patient-reported as well as clinically measured swallowing function in HNC patients after curative (chemo-) radiation therapy (RT) with focus on late effects.Materials and methodsPatients (n = 90) with HNC curatively treated with RT ± chemotherapy in 2007-2015 were assessed for dysphagia post-treatment by telephone interview and videofluoroscopy (VFS). A study-specific symptom score was used to determine patient-reported dysphagia. The Penetration-Aspiration Scale (PAS) was applied to determine swallowing function by VFS (PAS ≥ 4/ ≥ 6 = moderate/severe dysphagia). Thirteen anatomical structures involved in normal swallowing were individually delineated on the patients' original planning CT scans and associated dose-volume histograms (DVHs) retrieved. Relationships between structure doses and late toxicity were investigated through univariable and multivariable logistic regression analysis (UVA/MVA) accounting for effects by relevant clinical factors.ResultsMedian assessment time was 7 months post-RT (range: 5-34 months). Mean dose to the contralateral parotid gland and supraglottic larynx as well as maximum dose to the contralateral anterior digastric muscle predicted patient-reported dysphagia (AUC = 0.64-0.67). Mean dose to the pharyngeal constrictor muscle, the larynx, the supraglottic larynx and the epiglottis, as well as maximum dose to the contralateral submandibular gland predicted moderate and severe dysphagia by VFS (AUC = 0.71-0.80).ConclusionThe patients in this cohort were consecutively identified pre-treatment, and were structurally approached and assessed for dysphagia after treatment at a specific time point. In addition to established dysphagia organs-at-risk (OARs), our data suggest that epiglottic and submandibular gland doses are important for swallowing function post-RT. Keeping DVH thresholds below V60 = 60% and V60 = 17%, respectively, may increase chances to reduce occurrence of severe late dysphagia. The results need to be externally validated in future studies.

Dataset Information

Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study.

Publications

Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets