Investigating the potential of deep learning for patient-specific quality assurance of salivary gland contours using EORTC-1219-DAHANCA-29 clinical trial data

Nijhuis, H.; Rooij, Ward van; Grégoire, Vincent; Overgaard, Jens; Slotman, B.J.; Verbakel, Wilko F.A.R.; Dahele, Max

doi:10.1080/0284186x.2020.1863463

Cited by 7 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 8 provides a summary of studies reporting parotid gland segmentation. When the literature is examined, 8–30 it is seen that the parotid glands are generally segmented separately as left and right. At this point, the proposed system can segment both the left and right parotid glands.…”

Section: Resultsmentioning

confidence: 99%

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Sünnetci

Kaba

Çeliker

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Nowadays, artificial intelligence‐based medicine plays an important role in determining correlations not comprehensible to humans. In addition, the segmentation of organs at risk is a tedious and time‐consuming procedure. Segmentation of these organs or tissues is widely used in early diagnosis, treatment planning, and diagnosis. In this study, we trained semantic segmentation networks to segment healthy parotid glands using deep learning. The dataset we used in the study was obtained from Recep Tayyip Erdogan University Training and Research Hospital, and there were 72 T2‐weighted magnetic resonance (MR) images in this dataset. After these images were manually segmented by experts, masks of these images were obtained according to them and all images were cropped. Afterward, these cropped images and masks were rotated 45°, 120°, and 210°, quadrupling the number of images. We trained ResNet‐18/MobileNetV2‐based DeepLab v3+ without augmentation and ResNet‐18/MobileNetV2‐based DeepLab v3+ with augmentation using these datasets. Here, we set the training set and testing set sizes for all architectures to be 80% and 20%, respectively. We designed two different graphical user interface (GUI) applications so that users can easily segment their parotid glands by utilizing all of these deep learning‐based semantic segmentation networks. From the results, mean‐weighted dice values of MobileNetV2‐based DeepLab v3+ without augmentation and ResNet‐18‐based DeepLab v3+ with augmentation were equal to 0.90845–0.93931 and 0.93237–0.96960, respectively. We also noted that the sensitivity (%), specificity (%), F1 score (%) values of these models were equal to 83.21, 96.65, 85.04 and 89.81, 97.84, 87.80, respectively. As a result, these designed models were found to be clinically successful, and the user‐friendly GUI applications of these proposed systems can be used by clinicians. This study is competitive as it uses MR images, can automatically segment both parotid glands, the results are meaningful according to the literature and have software application.

show abstract

Section: Resultsmentioning

confidence: 99%

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Sünnetci

Kaba

Çeliker

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…A 0 black-box' model may help with detecting errors, but it does not provide information to help identify and solve the problems. Moreover, high false-positive rates could be a challenge [57,69], and these are inherent because of the probabilistic nature of most artificial intelligence models. A recent study [72] showed that users could lose trust and ignore results generated by the artificial intelligence model if falsepositive rates are too high.…”

Section: Discussionmentioning

confidence: 99%

“…An artificial intelligence model was also proposed to improve efficiency and reduce variability on contour quality assurance for clinical trials. Nijhuis et al [69] trained two CNNs for right parotid and submandibular glands using 735 clinically delineated computed tomography scans of head and neck patients to identify deliberate contour errors. Contours highlighted by the model as erroneous were visually inspected.…”

Section: Quality Assurance On Contoursmentioning

confidence: 99%

Improving the Quality of Care in Radiation Oncology using Artificial Intelligence

et al. 2022

View full text Add to dashboard Cite

“…The other type of workflow is to use deep learning (DL) based on convolutional neural networks (CNNs) which enable the features to be automatic learned from the training data instead of being hand-crafted. There have been a few previous studies using CNNs to perform automatic delineation QA (Chen et al 2020, Men et al 2020, Nijhuis et al 2021. Men et al (2020) adopted a deep active learning method for OAR segmentation, and built delineation evaluation criteria based on the Dice Similarity Coefficient (DSC) (Dice 1945) and Hausdorff distance (HD) (Huttenlocher et al 1993) between the manual and automatic delineations on lung CT. Chen et al (2020) proposed an automatic QA method using ResNet (He et al 2016) for breast cancer delineations automatically generated by a segmentation network on CT. Nijhuis et al (2021) proposed to perform QA by measuring the DSC and HD between 3D Unet generated segmentations and manual delineations on CT.…”

Section: Introductionmentioning

confidence: 99%

“…There have been a few previous studies using CNNs to perform automatic delineation QA (Chen et al 2020, Men et al 2020, Nijhuis et al 2021. Men et al (2020) adopted a deep active learning method for OAR segmentation, and built delineation evaluation criteria based on the Dice Similarity Coefficient (DSC) (Dice 1945) and Hausdorff distance (HD) (Huttenlocher et al 1993) between the manual and automatic delineations on lung CT. Chen et al (2020) proposed an automatic QA method using ResNet (He et al 2016) for breast cancer delineations automatically generated by a segmentation network on CT. Nijhuis et al (2021) proposed to perform QA by measuring the DSC and HD between 3D Unet generated segmentations and manual delineations on CT. However, both Men et al (2020) and Chen et al (2020) only processed 2D CT slices instead of 3D volumetric data and all three studies focused on delineation QA on treatment planning CT.…”

Section: Introductionmentioning

confidence: 99%

Automatic radiotherapy delineation quality assurance on prostate MRI with deep learning in a multicentre clinical trial

et al. 2021

View full text Add to dashboard Cite

Volume delineation quality assurance (QA) is particularly important in clinical trial settings where consistent protocol implementation is required, as outcomes will affect future as well current patients. Currently, where feasible, this is conducted manually, which is time consuming and resource intensive. Although previous studies mostly focused on automating delineation QA on CT, magnetic resonance imaging (MRI) is being increasingly used in radiotherapy treatment. In this work, we propose to perform automatic delineation QA on prostate MRI for both the clinical target volume (CTV) and organs-at-risk (OARs) by using delineations generated by 3D Unet variants as benchmarks for QA. These networks were trained on a small gold standard atlas set and applied on a multicentre radiotherapy clinical trial dataset to generate benchmark delineations. Then, a QA stage was designed to recommend ‘pass’, ‘minor correction’ and ‘major correction’ for each manual delineation in the trial set by thresholding its Dice similarity coefficient to the network generated delineation. Among all 3D Unet variants explored, the Unet with anatomical gates in an AtlasNet architecture performed the best in delineation QA, achieving an area under the receiver operating characteristics curve of 0.97, 0.92, 0.89 and 0.97 for identifying unacceptable (major correction) delineations with a sensitivity of 0.93, 0.73, 0.74 and 0.90 at a specificity of 0.93, 0.86, 0.86 and 0.95 for bladder, prostate CTV, rectum and gel spacer respectively. To the best of our knowledge, this is the first study to propose automated delineation QA for a multicentre radiotherapy clinical trial with treatment planning MRI. The methods proposed in this work can potentially improve the accuracy and consistency of CTV and OAR delineation in radiotherapy treatment planning.

show abstract

Investigating the potential of deep learning for patient-specific quality assurance of salivary gland contours using EORTC-1219-DAHANCA-29 clinical trial data

Cited by 7 publications

References 25 publications

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Improving the Quality of Care in Radiation Oncology using Artificial Intelligence

Automatic radiotherapy delineation quality assurance on prostate MRI with deep learning in a multicentre clinical trial

Contact Info

Product

Resources

About