3D Variation in delineation of head and neck organs at risk

Brouwer, Charlotte L.; Steenbakkers, Roel J.H.M.; Heuvel, Edwin van den; Duppen, J.; Navran, Arash; Bijl, H.P.; Chouvalova, O.; Burlage, Fred R.; Meertens, H.; Langendijk, Johannes A.; Veld, Aart A. van ‘t

doi:10.1186/1748-717x-7-32

Cited by 182 publications

(163 citation statements)

References 22 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…22,23 The intra-and interobserver variability is well known in literature. 8,14,15,18,22,23 Similar results were obtained in the publication by Song et al 15 Song et al compared the delineation process for the prostate on KVCT and MVCT. The uncertainty in prostate contouring (prostate has the HU value near the "soft tissue" and "muscles" in this study) was higher on MVCT vs. KVCT.…”

Section: Discussionsupporting

confidence: 76%

“…6,7 At the Greater Poland Cancer Centre, for accurate positioning of patients, the registration procedures of megavoltage (MV) CT scans on HT are performed every day and adjusted to the pre-treatment kilovoltage (KV) CT scans from the diagnostic CT. One of them is manual delineation which is timeconsuming and varies between the operators. 8 It is reasonable to expect the contouring variability in MVCT scans to be larger than in conventional KVCT scans because of increased noise and reduction of soft-tissue contrast associated with megavoltage beams used for image reconstruction. 9 In this study, the uncertainty of delineation process was evaluated and compared between kilovoltage and megavoltage scans.…”

Section: Introductionmentioning

confidence: 99%

“…That is why the variability of contours in MVCT is expected to be greater than in KVCT. 8 Additionally, the increased interest in the use of MVCT data for treatment planning requires knowledge of the electron density of the tissues and checking how the structures of different densities are delineated by different observers. 10 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Influence of the type of imaging on the delineation process during the treatment planning

Jackowiak

Bąk

Kowalik

et al. 2015

Reports of Practical Oncology & Radiotherapy

View full text Add to dashboard Cite

a b s t r a c tAim: The aim of this study was to compare the intra-and interobserver contouring variability for structures with density of organ at risk in two types of tomography: kilovoltage computed tomography (KVCT) versus megavoltage computed tomography (MVCT). The intraand interobserver differences were examined on both types of tomography for structures which simulate human tissue or organs. Materials and methods:Six structures with density of the liver, bone, trachea, lung, soft tissue and muscle were created and used. For the measurements, the special water phantom with all structures was designed. To evaluate interobserver variability, five observers delineated the structures in both types of computed tomography (CT).Results: Intraobserver variability was in the range of 1-14% and was the largest for the liver. (51.86 vs. 67.97), the volume on MVCT was smaller than KVCT. The statistically significant differences between observers were observed for structures with density of the liver, bone and soft tissue on KVCT and for the liver, lung and soft tissue on MVCT. For the structures with density of the trachea and muscles, there were no significant differences for both types of tomography.Conclusions: During the contouring process the interobserver and intraobserver contouring uncertainty was larger on MVCT, especially for structures with HU near 80, compared with KVCT.

show abstract

Section: Discussionsupporting

confidence: 76%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Influence of the type of imaging on the delineation process during the treatment planning

Jackowiak

Bąk

Kowalik

et al. 2015

Reports of Practical Oncology & Radiotherapy

View full text Add to dashboard Cite

show abstract

“…The estimate for the ICC is d ICC ¼ 0:61, as it was earlier reported. 1 However, a confidence interval on this estimate was not reported.…”

mentioning

confidence: 98%

“…To investigate this delineation process, an agreement study was conducted. 1 One aspect in this study was to assess the agreement among oncologists on measurements of organ volumes. Five oncologists observed each of six patients at two time points, at the beginning of treatment and approximately six months later.…”

Section: Introduction 1motivating Examplementioning

confidence: 99%

Confidence intervals for intraclass correlation coefficients in variance components models

Demetrashvili

Wit

Heuvel

2016

Stat Methods Med Res

View full text Add to dashboard Cite

Confidence intervals for intraclass correlation coefficients in agreement studies with continuous outcomes are model-specific and no generic approach exists. This paper provides two generic approaches for intraclass correlation coefficients of the form P Q q¼12 p Þ. The first approach uses Satterthwaite's approximation and an F-distribution. The second approach uses the first and second moments of the intraclass correlation coefficient estimate in combination with a Beta distribution. Both approaches are based on the restricted maximum likelihood estimates for the variance components involved. Simulation studies are conducted to examine the coverage probabilities of the confidence intervals for agreement studies with a mix of small sample sizes. Two different three-way variance components models and balanced and unbalanced one-way random effects models are investigated. The proposed approaches are compared with other approaches developed for these specific models. The approach based on the F-distribution provides acceptable coverage probabilities, but the approach based on the Beta distribution results in accurate coverages for most settings in both balanced and unbalanced designs. A real agreement study is provided to illustrate the approaches.

show abstract

Deep learning‐based classification and structure name standardization for organ at risk and target delineations in prostate cancer radiotherapy

Gustafsson

Lempart

Swärd

et al. 2021

J Applied Clin Med Phys

View full text Add to dashboard Cite

Radiotherapy (RT) datasets can suffer from variations in annotation of organ at risk (OAR) and target structures.Annotation standards exist,but their description for prostate targets is limited. This restricts the use of such data for supervised machine learning purposes as it requires properly annotated data. The aim of this work was to develop a modality independent deep learning (DL) model for automatic classification and annotation of prostate RT DICOM structures. Delineated prostate organs at risk (OAR), support-and target structures (gross tumor volume [GTV]/clinical target volume [CTV]/planning target volume [PTV]), along with or without separate vesicles and/or lymph nodes, were extracted as binary masks from 1854 patients. An image modality independent 2D Inception-ResNetV2 classification network was trained with varying amounts of training data using four image input channels. Channel 1-3 consisted of orthogonal 2D projections from each individual binary structure. The fourth channel contained a summation of the other available binary structure masks. Structure classification performance was assessed in independent CT (n = 200 pat) and magnetic resonance imaging (MRI) (n = 40 pat) test datasets and an external CT (n = 99 pat) dataset from another clinic. A weighted classification accuracy of 99.4% was achieved during training. The unweighted classification accuracy and the weighted average F1 score among different structures in the CT test dataset were 98.8% and 98.4% and 98.6% and 98.5% for the MRI test dataset, respectively. The external CT dataset yielded the corresponding results 98.4% and 98.7% when analyzed for trained structures only, and results from the full dataset yielded 79.6% and 75.2%. Most misclassifications in the external CT dataset occurred due to multiple CTVs and PTVs being fused together, which was not included in the training data. Our proposed DL-based method for automated renaming and standardization of prostate radiotherapy annotations shows great potential. Clinic specific contouring standards however need to be represented in the training data for successful use.

show abstract

3D Variation in delineation of head and neck organs at risk

Cited by 182 publications

References 22 publications

Influence of the type of imaging on the delineation process during the treatment planning

Influence of the type of imaging on the delineation process during the treatment planning

Confidence intervals for intraclass correlation coefficients in variance components models

Deep learning‐based classification and structure name standardization for organ at risk and target delineations in prostate cancer radiotherapy

Contact Info

Product

Resources

About