Multi-subject atlas-based auto-segmentation reduces interobserver variation and improves dosimetric parameter consistency for organs at risk in nasopharyngeal carcinoma: A multi-institution clinical study

Tao, Changjuan; Yi, Junlin; Chen, Nian‐Yong; Ren, Wei; Cheng, Jason Chia‐Hsien; Tung, Stewart Y.; Kong, Lin; Shen, Lin; Pan, Jianji; Zhang, Guangshun; Hu, Jiang; Qi, Zhenyu; Ma, Jingfei; Lu, Jiade J.; Yan, Di; Sun, Yu

doi:10.1016/j.radonc.2015.05.012

Cited by 84 publications

(82 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For OHP, reported results are 0.4–0.6 and 1–1.25mm [16], 0.64 [17] and our results are 0.58 and 2.6mm. This object is very challenging due to lack of contrast with surrounding muscles.…”

Section: Resultssupporting

confidence: 63%

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: Resultssupporting

confidence: 63%

“…For LX, reported results are 0.86 [5], 0.5–0.62 and 2.0–6.0mm [16], 0.73 [17]. Our results are 0.74 and 4.0mm.…”

Section: Resultssupporting

confidence: 44%

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

“…Researchers also studied the performance of machine learning algorithms such as k‐nearest neighbors and support vector machines trained on intensity, gradient, texture contrast, texture homogeneity, texture energy, cluster tendency, Gabor and Sobel features . The above mentioned algorithms covered the complete set of OARs in the HaN region including brainstem, cerebellum, spinal cord, mandible, parotid glan‐ds, submandibular glands, pituitary gland, thyroid, eye globes, eye lenses, optic nerves, optic chiasm, larynx, pharyngeal constrictor muscle, pterygoid muscles, tongue muscles, and lymph nodes . Despite the considerable attention, the demonstrated results are still not satisfactory for the clinical usage and automated methods cannot accurately segment OARs in the presence of tumors and severe pathologies.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks

2017

View full text Add to dashboard Cite

Purpose Accurate segmentation of organs-at-risks (OARs) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning-based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state-of-the-art automated segmentation algorithms, commercial software and inter-observer variability. Methods Convolutional neural networks (CNNs) – a concept from the field of deep learning – were used to study consistent intensity patterns of OARs from training CT images and to segment the OAR in a previously unseen test CT image. For CNN training, we extracted a representative number of positive intensity patches around voxels that belong to the OAR of interest in training CT images, and negative intensity patches around voxels that belong to the surrounding structures. These patches then passed through a sequence of CNN layers that captured local image features such as corners, end-points and edges, and combined them into more complex high-order features that can efficiently describe the OAR. The trained network was applied to classify voxels in a region of interest in the test image where the corresponding OAR is expected to be located. We then smoothed the obtained classification results by using Markov random fields algorithm. We finally extracted the largest connected component of the smoothed voxels classified as the OAR by CNN, performed dilate-erode operations to remov cavities of the component, which resulted in segmentation of the OAR in the test image. Results The performance of CNNs was validated on segmentation of spinal cord, mandible, parotid glands, submandibular glands, larynx, pharynx, eye globes, optic nerves and optic chiasm using 50 CT images. The obtained segmentation results varied from 37.4% Dice coefficient (DSC) for chiasm to 89.5% DSC for mandible. We also analyzed the performance of state-of-the-art algorithms and commercial software reported in the literature, and observed that CNNs demonstrate similar or superior performance on segmentation of spinal cord, mandible, parotid glands, larynx, pharynx, eye globes and optic nerves, but inferior performance on segmentation of submandibular glands and optic chiasm. Conclusion We concluded that convolution neural networks can accurately segment most of OARs using a representative database of 50 HaN CT images. At the same time, inclusion of additional information, e.g. MR images, may be beneficial for some OARs with poorly-visible boundaries.

show abstract

“…The great discrepancy was confirmed by the percentage of intersection that ranged between 32 and 89 %, with a mean value of As previously said, the interobserver variability in OARs definition can be limited. Recently, Tao et al [34] conducted a study to assess whether consensus guideline-based atlas-based auto-segmentation (ABAS) reduces interobserver variation and improves dosimetric parameter consistency for OARs in nasopharyngeal carcinoma, showing a significant interobserver variation for all OARs in manual contouring. Edited ABAS reduced interobserver variation and improved dosimetric parameter consistency, particularly for some structures, such as larynx.…”

Section: Discussionmentioning

confidence: 99%

Delineation of the larynx as organ at risk in radiotherapy: a contouring course within “Rete Oncologica Piemonte-Valle d’Aosta” network to reduce inter- and intraobserver variability

et al. 2016

View full text Add to dashboard Cite

Mean percentage of intersection and DC strongly increased after the course, rising from 57.76 to 93.83 % and from 0.68 to 0.89, respectively. CI enhanced from 0.06 to 0.31. Conclusions This study shows an improvement in larynx definition after the contouring course with lower interobserver variability and major consistency compared to the reference volume. Other specific educational activities may further increase the quality of radiation therapy contouring in this setting.

show abstract

Multi-subject atlas-based auto-segmentation reduces interobserver variation and improves dosimetric parameter consistency for organs at risk in nasopharyngeal carcinoma: A multi-institution clinical study

Cited by 84 publications

References 19 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

Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks

Delineation of the larynx as organ at risk in radiotherapy: a contouring course within “Rete Oncologica Piemonte-Valle d’Aosta” network to reduce inter- and intraobserver variability

Contact Info

Product

Resources

About