Quality assurance tool for organ at risk delineation in radiation therapy using a parametric statistical approach

Hui, Cheukkai; Nourzadeh, Hamidreza; Watkins, W.T.; Trifiletti, Daniel M.; Alonso, Clayton E.; Dutta, Sunil W.; Siebers, Jeffrey V.

doi:10.1002/mp.12835

Cited by 23 publications

(29 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are the main reasons that such methods in literature could not achieve a nearhuman-error-detection performance. 10,15,16 To address this intrinsic limitation, our quality control system narrows down the scope of error detection from the feature space to intraclass feature space by utilizing a bank of autoencoders for ROI classes. Our results suggest that the system model achieves a higher level of accuracy and specificity when compared to a classification-based anomaly detection approach.…”

Section: Discussionmentioning

confidence: 99%

Knowledge‐based quality control of organ delineations in radiation therapy

et al. 2022

Self Cite

View full text Add to dashboard Cite

To reduce the likelihood of errors in organ delineations used for radiotherapy treatment planning, a knowledge-based quality control (KBQC) system, which discriminates between valid and anomalous delineations is developed. Method and Materials:The KBQC is comprised of a group-wise inference system and anomaly detection modules trained using historical priors from 296 locally advanced lung and prostate cancer patient computational tomographies (CTs). The inference system discriminates different organs based on shape, relational, and intensity features. For a given delineated image set, the inference system solves a combinatorial optimization problem that results in an organ group whose relational features follow those of the training set considering the posterior probabilities obtained from support vector machine (SVM), discriminant subspace ensemble (DSE), and artificial neural network (ANN) classifiers. These classifiers are trained on nonrelational features with a 10-fold crossvalidation scheme. The anomaly detection module is a bank of ANN autoencoders, each corresponding with an organ, trained on nonrelational features. A heuristic rule detects anomalous organs that exceed predefined organ-specific tolerances for the feature reconstruction error and the classifier's posterior probabilities. Independent data sets with anomalous delineations were used to test the overall performance of the KBQC system. The anomalous delineations were manually manipulated, computer-generated, or propagated based on a transformation obtained by imperfect registrations. Both peer-review-based scoring system and shape similarity coefficient (DSC) were used to label regions of interest (ROIs) as normal or anomalous in two independent test cohorts. Results: The accuracy of the classifiers was ≥99.8%, and the minimum perclass F1-scores were 0.99, 0.99, and 0.98 for SVM, DSE, and ANN, respectively. The group-wise inference system reduced the miss-classification likelihood for the test data set with anomalous delineations compared to each individual classifier and a fused classifier that used the average posterior probability of all classifiers. For 15 independent locally advanced lung patients, the system detected >79% of the anomalous ROIs. For 1320 auto-segmented abdominopelvic organs, the anomaly detection system identified anomalous delineations, which also had low Dice similarity coefficient values with respect to manually delineated organs in the training data set. Conclusion:The KBQC system detected anomalous delineations with superior accuracy compared to classification methods that judge only based on posterior probabilities.

show abstract

Section: Discussionmentioning

confidence: 99%

Knowledge‐based quality control of organ delineations in radiation therapy

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence could also be used to develop computer-assisted peer review software. Hui et al (89) developed an algorithm that could be used to evaluate OARs in the thoracic region. In this study, the researchers simulated common delineation errors, including boundary deviations, missing slices, incorrect labelling, and craniocaudal over-extension for OARs in the thoracic region.…”

Section: Peer Reviewmentioning

confidence: 99%

Challenges in the target volume definition of lung cancer radiotherapy

Mercieca

Belderbos

Herk

2021

Transl Lung Cancer Res

View full text Add to dashboard Cite

Radiotherapy, with or without systemic treatment has an important role in the management of lung cancer. In order to deliver the treatment accurately, the clinician must precisely outline the gross tumour volume (GTV), mostly on computed tomography (CT) images. However, due to the limited contrast between tumour and non-malignant changes in the lung tissue, it can be difficult to distinguish the tumour boundaries on CT images leading to large interobserver variation and differences in interpretation.Therefore the definition of the GTV has often been described as the weakest link in radiotherapy with its inaccuracy potentially leading to missing the tumour or unnecessarily irradiating normal tissue. In this article, we review the various techniques that can be used to reduce delineation uncertainties in lung cancer.The findings of this review indicate that to date, it is still not possible to eliminate interobserver variation in the definition of GTV. Positron Emission Tomography (PET-CT) has an important role in improving the staging accuracy and the definition of the tumour. Various autosegmentation tools have also been proposed to fully or partially automate the delineation process. However, their development is currently hindered by the unavailability of absolute gold standards that can be used to train and validate these algorithms. Hence, manual delineation is still considered to be the gold standard. Nevertheless, auto-segmented contours can provide a good starting point, eventually reducing the delineation time and interobserver variation.Improvements in image quality can also reduce the delineation uncertainty in some cases. The main factor leading to interobserver variation is image interpretation differences between clinicians. Therefore, protocols, training and peer review checks of delineated contours are essential to address this challenge. The development of the MR-linac will also present new challenges and opportunities in optimising the definition of the target volume as well as in the development of adaptive radiotherapy strategies.

show abstract

“…According to Jungo et al medical image segmentation uncertainty can be evaluated at three levels: the voxelwise uncertainty, the uncertainty at the level of a segmented instance, the subject-level uncertainty [14]. Automatic quality assurance of autosegmentations has been investigated in the literature, evaluating ROI specific characteristics such as centroid, volume, shape and use statistical approaches to determine variations in contoured ROIs [15][16][17]. Court et al used the results of a primary segmentation algorithm and compare these to a secondary, independent, verification algorithm [18].…”

Section: Introductionmentioning

confidence: 99%

Radiomics classifier to quantify automatic segmentation quality of cardiac sub-structures for radiotherapy treatment planning

Maffei¹,

Manco²,

Aluisio³

et al. 2021

Physica Medica

View full text Add to dashboard Cite

A radiomics features classifier was implemented to evaluate segmentation quality of heart structures. A robust feature set sensitive to incorrect contouring would provide an ideal quantitative index to drive autocontouring optimization. Methods: Twenty-five cardiac sub-structures were contoured as regions of interest in 36 CTs. Radiomic features were extracted from manually-contoured (MC) and Hierarchical-Clustering automatic-contouring (AC) structures. A robust feature-set was identified from correctly contoured CT datasets. Features variation was analyzed over a MC/AC dataset. A supervised-learning approach was used to train an Artificial-Intelligence (AI) classifier; incorrect contouring cases were generated from the gold-standard MC datasets with translations, expansions and contractions. ROC curves and confusion matrices were used to evaluate the AI-classifier performance. Results: Twenty radiomics features, were found to be robust across structures, showing a good/excellent intraclass correlation coefficient (ICC) index comparing MC/AC. A significant correlation was obtained with quantitative indexes (Dice-Index, Hausdorff-distance). The trained AI-classifier detected correct contours (CC) and not correct contours (NCC) with an accuracy of 82.6% and AUC of 0.91. True positive rate (TPR) was 85.1% and 81.3% for CC and NCC. Detection of NCC at this point of the development still depended strongly on degree of contouring imperfection. Conclusions: A set of radiomics features, robust on "gold-standard" contour and sensitive to incorrect contouring was identified and implemented in an AI-workflow to quantify segmentation accuracy. This workflow permits an automatic assessment of segmentation quality and may accelerate expansion of an existing autocontouring atlas database as well as improve dosimetric analyses of large treatment plan databases.

show abstract

Quality assurance tool for organ at risk delineation in radiation therapy using a parametric statistical approach

Abstract: The QA tool assists users to detect potential delineation errors. QA tool integration into clinical procedures may reduce the frequency of inaccurate OAR delineation, and potentially improve safety and quality of radiation treatment planning.

Cited by 23 publications

References 18 publications

Knowledge‐based quality control of organ delineations in radiation therapy

Knowledge‐based quality control of organ delineations in radiation therapy

Challenges in the target volume definition of lung cancer radiotherapy

Radiomics classifier to quantify automatic segmentation quality of cardiac sub-structures for radiotherapy treatment planning

Contact Info

Product

Resources

About