Squeeze-and-Excitation Networks

Hu, Jie; Shen, Li; Albanie, Samuel; Sun, Gang; Wu, Enhua

doi:10.1109/tpami.2019.2913372

Cited by 9,073 publications

(9,452 citation statements)

References 56 publications

Supporting

Mentioning

9,388

Contrasting

Unclassified

Order By: Relevance

“…ResNet, published in 2015, consisted of modules with a shortcut process. Squeeze‐and‐Excitation Networks, published in 2017, induced Squeeze‐and‐Excitation Blocks, which are building blocks for convolutional neural networks that improve channel interdependencies. The AI used for image recognition is still being developed.…”

Section: Discussionmentioning

confidence: 99%

Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

Miyagi

Habara

Hirata

et al. 2019

Reprod Medicine & Biology

View full text Add to dashboard Cite

Purpose To identify artificial intelligence (AI) classifiers in images of blastocysts to predict the probability of achieving a live birth in patients classified by age. Results are compared to those obtained by conventional embryo (CE) evaluation. Methods A total of 5691 blastocysts were retrospectively enrolled. Images captured 115 hours after insemination (or 139 hours if not yet large enough) were classified according to maternal age as follows: <35, 35‐37, 38‐39, 40‐41, and ≥42 years. The classifiers for each category and a classifier for all ages were related to convolutional neural networks associated with deep learning. Then, the live birth functions predicted by the AI and the multivariate logistic model functions predicted by CE were tested. The feasibility of the AI was investigated. Results The accuracies of AI/CE for predicting live birth were 0.64/0.61, 0.71/0.70, 0.78/0.77, 0.81/0.83, 0.88/0.94, and 0.72/0.74 for the age categories <35, 35‐37, 38‐39, 40‐41, and ≥42 years and all ages, respectively. The sum value of the sensitivity and specificity revealed that AI performed better than CE ( P = 0.01). Conclusions AI classifiers categorized by age can predict the probability of live birth from an image of the blastocyst and produced better results than were achieved using CE.

show abstract

Section: Discussionmentioning

confidence: 99%

Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

Miyagi

Habara

Hirata

et al. 2019

Reprod Medicine & Biology

View full text Add to dashboard Cite

show abstract

“…In this experiment, 27 × 75 × 93 × 81 data were generated via the aforementioned preprocessing and data augmentation steps. In the first layer, we used 1 × 1 × 1 convolutional filters, which have been widely used in recent structural designs of convolutional neural networks (CNNs) because these filters increase nonlinearity without changing the receptive fields of the convolutional layer (Hu, Shen, & Sun, 2017;Iandola et al, 2016;Simonyan & Zisserman, 2014). These filters can generate temporal descriptors for each voxel of the volume of the fMRI, and their weights can be easily learnt by DNNs during training.…”

Section: Preparation Of Fmri Time Series For Deep Learningmentioning

confidence: 99%

Decoding and mapping task states of the human brain via deep learning

Wang

Liang

Jiang

et al. 2019

Human Brain Mapping

View full text Add to dashboard Cite

Support vector machine (SVM)‐based multivariate pattern analysis (MVPA) has delivered promising performance in decoding specific task states based on functional magnetic resonance imaging (fMRI) of the human brain. Conventionally, the SVM‐MVPA requires careful feature selection/extraction according to expert knowledge. In this study, we propose a deep neural network (DNN) for directly decoding multiple brain task states from fMRI signals of the brain without any burden for feature handcrafts. We trained and tested the DNN classifier using task fMRI data from the Human Connectome Project's S1200 dataset (N = 1,034). In tests to verify its performance, the proposed classification method identified seven tasks with an average accuracy of 93.7%. We also showed the general applicability of the DNN for transfer learning to small datasets (N = 43), a situation encountered in typical neuroscience research. The proposed method achieved an average accuracy of 89.0 and 94.7% on a working memory task and a motor classification task, respectively, higher than the accuracy of 69.2 and 68.6% obtained by the SVM‐MVPA. A network visualization analysis showed that the DNN automatically detected features from areas of the brain related to each task. Without incurring the burden of handcrafting the features, the proposed deep decoding method can classify brain task states highly accurately, and is a powerful tool for fMRI researchers.

show abstract

“…First, we extend the standard U-Net model for 3D HaN image segmentation by incorporating a new feature extraction component, based on squeeze-and-excitation (SE) residual blocks. 30 Second, we propose a new loss function for better segmenting small-volumed structures. 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.…”

Section: Introductionmentioning

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

402

316

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

Squeeze-and-Excitation Networks

Cited by 9,073 publications

References 56 publications

Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

Decoding and mapping task states of the human brain via deep learning

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

Contact Info

Product

Resources

About