The relevance of MRI for patient modeling in head and neck hyperthermia treatment planning: A comparison of CT and CT‐MRI based tissue segmentation on simulated temperature

Verhaart, René F.; Fortunati, Valerio; Verduijn, Gerda M.; Lugt, Aad van der; Walsum, Theo van; Veenland, Jifke F.; Paulides, Margarethus M.

doi:10.1118/1.4901270

Cited by 26 publications

(32 citation statements)

References 52 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A single atlas, however, cannot guarantee accurate segmentation results in the presence of pathologies and tumors when the morphology of OARs is not similar enough between the atlas and test image. Multiatlas segmentation is less sensitive to interpatient anatomy variability and produces more accurate segmentation results if a high number of atlas images are used . The registrations for all atlases are usually combined with simultaneous truth and performance level estimation (STAPLE), similarity and truth estimation (STEPS) and joint‐weighted voting techniques.…”

Section: Introductionmentioning

confidence: 99%

“…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%

“…Multiatlas segmentation is less sensitive to interpatient anatomy variability and produces more accurate segmentation results if a high number of atlas images are used. [13][14][15] The registrations for all atlases are usually combined with simultaneous truth and performance level estimation (STAPLE), 16 similarity and truth estimation (STEPS) 16 and joint-weighted voting 17 techniques. When validated on HaN muscles, lymph nodes, spinal cord, and brainstem, multiatlas segmentation was shown to be slower but more accurate than single atlas segmenation.…”

Section: Introductionmentioning

confidence: 99%

“…38,39 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. 21,24 The above mentioned algorithms covered the complete set of OARs in the HaN region including brainstem, 4,7-12,14,16-18,24-27,40,41 cerebellum, 9,13,14,17,25,41 spinal cord, 4,13,16,18,40,41 mandible, 4,10,18,24,[42][43][44][45] parotid glands, 4,7,10,11,15,16,18,21,24,33,40,44,46 submandibular glands, 4,24,46 pituitary gland, 9 thyroid, 13,41,47 eye globes, 9,13,14,17,31,40,41 eye lenses, 13,14,16,17,…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

2017

View full text Add to dashboard Cite

show abstract

“…Atlas can be chosen from training CT images [2,7], created from artificial CT images with expert annotations on anatomies [8], or probabilistic atlas calculated from training CT images [4,6,9]. Multi-atlas based registration methods in general lead to better performance because of increased capacity to represent variations of anatomies in test images [10][11][12]. In the inference phrase, different fusion methods can be used, such as simultaneous truth and performance level estimation (STAPLE) [13], similarity and truth estimation (STEPS) [13], and joint weighted voting [14].…”

Section: Introductionmentioning

confidence: 99%

AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation

Zhu

Huang

Tang

et al. 2018

Preprint

View full text Add to dashboard Cite

Purpose: Radiation therapy (RT) is a common treatment for head and neck (HaN) cancer where therapists are often required to manually delineate boundaries of the organs-at-risks (OARs). The radiation therapy planning is time-consuming as each computed tomography (CT) volumetric data set typically consists of hundreds to thousands of slices and needs to be individually inspected. Automated head and neck anatomical segmentation provides a way to speed up and improve the reproducibility of radiation therapy planning. Previous work on anatomical segmentation is primarily based on atlas registrations, which takes up to hours for one patient and requires sophisticated atlas creation. In this work, we propose the AnatomyNet, an end-to-end and atlas-free three dimensional squeeze-and-excitation U-Net (3D SE U-Net), for fast and fully automated whole-volume HaN anatomical segmentation.Methods: There are two main challenges for fully automated HaN OARs segmentation: 1) challenge in segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and 2) training model with inconsistent data annotations with missing ground truth for some anatomical structures because of different RT planning. We propose the AnatomyNet that has one down-sampling layer with the trade-off between GPU memory and feature representation capacity, and 3D SE residual blocks for effective feature learning to alleviate these challenges. Moreover, we design a hybrid loss function with the Dice loss and the focal loss. The Dice loss is a class level distribution loss that depends less on the number of voxels in the anatomy, and the focal loss is designed to deal with highly unbalanced segmentation. For missing annotations, we propose masked loss and weighted loss for accurate and balanced weights updating in the learning of the AnatomyNet.Results: We collect 261 HaN CT images to train the AnatomyNet, and use MICCAI Head and Neck Auto Segmentation Challenge 2015 as the benchmark dataset to evaluate the performance of the AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state-of-the-art methods for each anatomy from the MICCAI 2015 competition, the AnatomyNet increases Dice similarity coefficient (DSC) by 3.3% on average. The proposed AnatomyNet takes only 0.12 seconds on average to segment a whole-volume HaN CT image of an average dimension of 178 × 302 × 225. All the data and code will be available a .Conclusion: We propose an end-to-end, fast and fully automated deep convolutional network, AnatomyNet, for accurate and whole-volume HaN anatomical segmentation. The proposed AnatomyNet outperforms previous state-of-the-art methods on the benchmark dataset. Extensive experiments demonstrate the effectiveness and good generalization ability of the components in the AnatomyNet.

show abstract

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

Zhu

Huang

Zeng³

et al. 2018

Medical Physics

430

333

View full text Add to dashboard Cite

Purpose Radiation therapy (RT) is a common treatment option for head and neck (HaN) cancer. An important step involved in RT planning is the delineation of organs‐at‐risks (OARs) based on HaN computed tomography (CT). However, manually delineating OARs is time‐consuming as each slice of CT images needs to be individually examined and a typical CT consists of hundreds of slices. Automating OARs segmentation has the benefit of both reducing the time and improving the quality of RT planning. Existing anatomy autosegmentation algorithms use primarily atlas‐based methods, which require sophisticated atlas creation and cannot adequately account for anatomy variations among patients. In this work, we propose an end‐to‐end, atlas‐free three‐dimensional (3D) convolutional deep learning framework for fast and fully automated whole‐volume HaN anatomy segmentation. Methods Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end‐to‐end fashion, receiving whole‐volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U‐net architecture, but extends it in three important ways: (a) a new encoding scheme to allow autosegmentation on whole‐volume CT images instead of local patches or subsets of slices, (b) incorporating 3D squeeze‐and‐excitation residual blocks in encoding layers for better feature representation, and (c) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep learning‐based HaN segmentation: (a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and (b) training with inconsistent data annotations with missing ground truth for some anatomical structures. Results We collected 261 HaN CT images to train AnatomyNet and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state‐of‐the‐art results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 s to fully segment a head and neck CT image of dimension 178 × 302 × 225, significantly faster than previous methods. In addition, the model is able to process whole‐volume CT images and delineate all OARs in one pass, requiring little pre‐ or postprocessing. Conclusion Deep learning models offer a feasible solution to the problem of delineating OARs from CT images. We demonstrate that our proposed model can improve segmentation accuracy and simplify the autosegmentation pipeline. With this method, it is possible to delineate OARs of a head and neck CT within a fraction of a second.

show abstract

The relevance of MRI for patient modeling in head and neck hyperthermia treatment planning: A comparison of CT and CT‐MRI based tissue segmentation on simulated temperature

Cited by 26 publications

References 52 publications

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

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

AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

Contact Info

Product

Resources

About