Adversarial deep structured nets for mass segmentation from mammograms

Zhu, Wentao; Xiang, Xiang; Tran, Trac D.; Hager, Gregory D.; Xie, Xiaohui

doi:10.1109/isbi.2018.8363704

Cited by 116 publications

(67 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, AnatomyNet is roughly within the range of the best MICCAI 2015 challenge results on six of nine anatomies . Its performance on this metric can be improved by considering surface and shape priors into the model as discussed above …”

Section: Discussionmentioning

confidence: 63%

See 1 more Smart Citation

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

Zhu

Huang

Zeng³

et al. 2018

Medical Physics

Self Cite

440

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

Section: Discussionmentioning

confidence: 63%

“…4 Its performance on this metric can be improved by considering surface and shape priors into the model as discussed above. 44,45…”

Section: B Limitationsmentioning

confidence: 99%

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

Zhu

Huang

Zeng³

et al. 2018

Medical Physics

Self Cite

440

333

View full text Add to dashboard Cite

show abstract

“…Small volume segmentation suffers from the imbalanced data problem, where the number of voxels inside the small region is much smaller than those outside, leading to the difficulty of training. New classes of loss functions have been proposed to address this issue, including Tversky loss [32], generalized Dice coefficients [33,34], focal loss [35], adversarial loss [36], sparsity label assignment constrains [37], and exponential logarithm loss [38]. However, we found none of these solutions alone was adequate to solve the extremely data imbalanced problem (1/100,000) we face in segmenting small OARs, such as optic nerves and chiasm, from HaN images.…”

Section: Introductionmentioning

confidence: 93%

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

Zhu

Huang

Tang

et al. 2018

Preprint

Self Cite

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

“…Summary of hyper-parameters of different classification algorithms for conducting the 5-fold cross validation-based grid-search by using the Scikit-learn. k-Nearest Neighbours n_neighbors: [1,3,5,7,9,11,13,15,17,19,21,23,25,27,29] weights: ['uniform', 'distance']…”

Section: Pest Regions 12mentioning

confidence: 99%

“…Each network gets better and better at its task until an equilibrium is reached, where the generator can't make better samples, and the discriminator can't detect more synthetic samples. GANs have already shown outstanding performance on di↵erent machine learning tasks in the image processing field, such as image to image translation [14][15] [16], image segmentation [17] [18] [19] and image reconstruction [20] [21] [22]. In addition to handling image data, GANs have also performed well with other types of data, such as gene expression data and raw gene sequence data.…”

Section: Introductionmentioning

confidence: 99%

Improving protein function prediction with synthetic feature samples created by generative adversarial networks

Wan

Jones

2019

Preprint

View full text Add to dashboard Cite

Protein function prediction is a challenging but important task in bioinformatics. Many prediction methods have been developed, but are still limited by the bottleneck on training sample quantity. Therefore, it is valuable to develop a data augmentation method that can generate high-quality synthetic samples to further improve the accuracy of prediction methods. In this work, we propose a novel generative adversarial networks-based method, namely FFPred-GAN, to accurately learn the high-dimensional distributions of protein sequence-based biophysical features and also generate high-quality synthetic protein feature samples. The experimental results suggest that the synthetic protein feature samples are successful in improving the prediction accuracy for all three domains of the Gene Ontology through augmentation of the original training protein feature samples. AbstractAuthor summary

show abstract

Adversarial deep structured nets for mass segmentation from mammograms

Cited by 116 publications

References 15 publications

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

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

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

Improving protein function prediction with synthetic feature samples created by generative adversarial networks

Contact Info

Product

Resources

About