Searcharxiv⌕ Search

arXiv subjects

Dong Yang

Publications and source records attributed to Dong Yang.

At least 181 records · Page 10Linked to original sources
arXiv2019

Weakly supervised segmentation from extreme points

Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain. Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images. We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm. This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks. We show that the network's predictions can be refined through several iterations of training and prediction using the same weakly annotated data. Ultimately, our method has the potential to speed up the generation process of new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis.

cs.CV↗
arXiv2019

An Alarm System For Segmentation Algorithm Based On Shape Model

It is usually hard for a learning system to predict correctly on rare events that never occur in the training data, and there is no exception for segmentation algorithms. Meanwhile, manual inspection of each case to locate the failures becomes infeasible due to the trend of large data scale and limited human resource. Therefore, we build an alarm system that will set off alerts when the segmentation result is possibly unsatisfactory, assuming no corresponding ground truth mask is provided. One plausible solution is to project the segmentation results into a low dimensional feature space; then learn classifiers/regressors to predict their qualities. Motivated by this, in this paper, we learn a feature space using the shape information which is a strong prior shared among different datasets and robust to the appearance variation of input data.The shape feature is captured using a Variational Auto-Encoder (VAE) network that trained with only the ground truth masks. During testing, the segmentation results with bad shapes shall not fit the shape prior well, resulting in large loss values. Thus, the VAE is able to evaluate the quality of segmentation result on unseen data, without using ground truth. Finally, we learn a regressor in the one-dimensional feature space to predict the qualities of segmentation results. Our alarm system is evaluated on several recent state-of-art segmentation algorithms for 3D medical segmentation tasks. Compared with other standard quality assessment methods, our system consistently provides more reliable prediction on the qualities of segmentation results.

cs.CV↗
arXiv2019

V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation

Deep learning algorithms, in particular 2D and 3D fully convolutional neural networks (FCNs), have rapidly become the mainstream methodology for volumetric medical image segmentation. However, 2D convolutions cannot fully leverage the rich spatial information along the third axis, while 3D convolutions suffer from the demanding computation and high GPU memory consumption. In this paper, we propose to automatically search the network architecture tailoring to volumetric medical image segmentation problem. Concretely, we formulate the structure learning as differentiable neural architecture search, and let the network itself choose between 2D, 3D or Pseudo-3D (P3D) convolutions at each layer. We evaluate our method on 3 public datasets, i.e., the NIH Pancreas dataset, the Lung and Pancreas dataset from the Medical Segmentation Decathlon (MSD) Challenge. Our method, named V-NAS, consistently outperforms other state-of-the-arts on the segmentation task of both normal organ (NIH Pancreas) and abnormal organs (MSD Lung tumors and MSD Pancreas tumors), which shows the power of chosen architecture. Moreover, the searched architecture on one dataset can be well generalized to other datasets, which demonstrates the robustness and practical use of our proposed method.

eess.IV↗
arXiv2019

Correlation via synthesis: end-to-end nodule image generation and radiogenomic map learning based on generative adversarial network

Radiogenomic map linking image features and gene expression profiles is useful for noninvasively identifying molecular properties of a particular type of disease. Conventionally, such map is produced in three separate steps: 1) gene-clustering to "metagenes", 2) image feature extraction, and 3) statistical correlation between metagenes and image features. Each step is independently performed and relies on arbitrary measurements. In this work, we investigate the potential of an end-to-end method fusing gene data with image features to generate synthetic image and learn radiogenomic map simultaneously. To achieve this goal, we develop a generative adversarial network (GAN) conditioned on both background images and gene expression profiles, synthesizing the corresponding image. Image and gene features are fused at different scales to ensure the realism and quality of the synthesized image. We tested our method on non-small cell lung cancer (NSCLC) dataset. Results demonstrate that the proposed method produces realistic synthetic images, and provides a promising way to find gene-image relationship in a holistic end-to-end manner.

cs.CV↗
arXiv2019

When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including different imaging protocols, device vendors and patient populations. Here we consider the problem of domain generalization, when a model is trained once, and its performance generalizes to unseen domains. Intuitively, within a specific medical imaging modality the domain differences are smaller relative to natural images domain variability. We rethink data augmentation for medical 3D images and propose a deep stacked transformations (DST) approach for domain generalization. Specifically, a series of n stacked transformations are applied to each image in each mini-batch during network training to account for the contribution of domain-specific shifts in medical images. We comprehensively evaluate our method on three tasks: segmentation of whole prostate from 3D MRI, left atrial from 3D MRI, and left ventricle from 3D ultrasound. We demonstrate that when trained on a small source dataset, (i) on average, DST models on unseen datasets degrade only by 11% (Dice score change), compared to the conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%); (ii) when evaluation on the same domain, DST is also better albeit only marginally. (iii) When training on large-sized data, DST on unseen domains reaches performance of state-of-the-art fully supervised models. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of robust deep segmentation models for clinical deployment.

cs.CV↗
arXiv2019

MRI Reconstruction via Cascaded Channel-wise Attention Network

We consider an MRI reconstruction problem with input of k-space data at a very low undersampled rate. This can practically benefit patient due to reduced time of MRI scan, but it is also challenging since quality of reconstruction may be compromised. Currently, deep learning based methods dominate MRI reconstruction over traditional approaches such as Compressed Sensing, but they rarely show satisfactory performance in the case of low undersampled k-space data. One explanation is that these methods treat channel-wise features equally, which results in degraded representation ability of the neural network. To solve this problem, we propose a new model called MRI Cascaded Channel-wise Attention Network (MICCAN), highlighted by three components: (i) a variant of U-net with Channel-wise Attention (UCA) module, (ii) a long skip connection and (iii) a combined loss. Our model is able to attend to salient information by filtering irrelevant features and also concentrate on high-frequency information by enforcing low-frequency information bypassed to the final output. We conduct both quantitative evaluation and qualitative analysis of our method on a cardiac dataset. The experiment shows that our method achieves very promising results in terms of three common metrics on the MRI reconstruction with low undersampled k-space data.

cs.CV↗
arXiv2019

Analysing Motifs in Multilayer Networks

Network motifs can capture basic interaction patterns and inform the functional properties of networks. However, real-world complex systems often have multiple types of relationships, which cannot be represented by a monolayer network. The multilayer nature of complex systems demands research on extending the notion of motifs to multilayer networks, thereby exploring the interaction patterns with a higher resolution. In this paper, we propose a formal definition of multilayer motifs, and analyse the occurrence of three-node multilayer motifs in a set of real-world multilayer networks. We find that multilayer motifs in social networks are more homogeneous across layers, indicating that different types of social relationships are reinforcing each other, while those in the transportation network are more complementary across layers. We find that biological networks are often associated with heterogeneous functions. This research sheds light on how multilayer network framework enables the capture of the hidden multi-aspect relationships among the nodes.

physics.soc-ph↗
arXiv2018

The interplay between 2-and-3-Calabi--Yau triangulated categories

This short note surveys the constructions of 3-Calabi--Yau triangulated categories with simple-minded collections due to Ginzburg and Kontsevich--Soibelman and the constructions of 2-Calabi--Yau triangulated categories with cluster-tilting objects due to Buan--Marsh--Reineke--Reiten--Todorov and Amiot, and includes a discussion on the normal form of 2-Calabi--Yau triangulated categories with cluster-tilting objects.

math.RT↗
arXiv2018

The equivalence of two discretenesses of triangulated categories

Given an ST-triple $(\mathcal{C},\mathcal{D},M)$ one can associate a co-$t$-structure on $\mathcal{C}$ and a $t$-structure on $\mathcal{D}$. It is shown that the discreteness of $\mathcal{C}$ with respect to the co-$t$-structure is equivalent to the discreteness of $\mathcal{D}$ with respect to the $t$-structure. As a special case, the discreteness of $\mathcal{D}^b(\mathrm{mod} A)$ in the sense of Vossieck is equivalent to the discreteness of $K^b(\mathrm{proj} A)$ in a dual sense, where $A$ is a finite-dimensional algebra.

math.RT↗
arXiv2018

Every entangled state provides an advantage in classical communication

We investigate the use of noisy entanglement as a resource in classical communication via a quantum channel. In particular, we are interested in the question whether for any entangled state, including bound entangled states, there exists a quantum channel the classical capacity of which can be increased by providing the state as an additional resource. We partially answer this question by showing, for any entangled state, the existence of a quantum memory channel the feedback-assisted classical capacity with product encodings of which can be increased by using the state as a resource. Using a different (memoryless) channel construction, we also provide a sufficient entropic condition for an advantage in classical communication (without feedback and for general encodings) and thus provide an example of a state that is not distillable by means of one-way local operations and classical communication (LOCC), but can provide an advantage in the classical capacity of a number of quantum channels. As separable states cannot provide an advantage in classical communication, our condition also provides an entropic entanglement witness.

quant-ph↗
arXiv2018

Important Attribute Identification in Knowledge Graph

The knowledge graph(KG) composed of entities with their descriptions and attributes, and relationship between entities, is finding more and more application scenarios in various natural language processing tasks. In a typical knowledge graph like Wikidata, entities usually have a large number of attributes, but it is difficult to know which ones are important. The importance of attributes can be a valuable piece of information in various applications spanning from information retrieval to natural language generation. In this paper, we propose a general method of using external user generated text data to evaluate the relative importance of an entity's attributes. To be more specific, we use the word/sub-word embedding techniques to match the external textual data back to entities' attribute name and values and rank the attributes by their matching cohesiveness. To our best knowledge, this is the first work of applying vector based semantic matching to important attribute identification, and our method outperforms the previous traditional methods. We also apply the outcome of the detected important attributes to a language generation task; compared with previous generated text, the new method generates much more customized and informative messages.

cs.CL↗
arXiv2018

First Investigation on the Radiation Field of the Gas-Filled Three-Axis Cylindrical Hohlraum

A novel ignition hohlraum named three-axis cylindrical hohlraum (TACH) is designed for indirect-drive inertial confinement fusion. TACH is a kind of 6 laser entrance holes (LEHs) hohlraum, which is orthogonally jointed of three cylindrical hohlraums. The first experiment on the radiation field of TACH was performed on Shenguang III laser facility. 24 laser beams were elected and injected into 6 LEHs quasi-symmetrically. Total laser energy was about 59 kJ, and the peak radiation temperature reached about 192 eV. Radiation temperature and pinhole images in gas-filled hohlraum are largely identical but with minor differences with those in vacuum hohlraum. All laser energy can be totally delivered into hohlraum in 3 ns duration even without filled gas in the hohlraum of 1.4 mm diameter. Plasma filling cannot be obviously suppressed even with 0.5 atm pressure gas in the small hohlraum. Backscattering fractions of vacuum hohlraum and gas-filled hohlraum are both lower than 2%. Experimental study of this new kind of hohlraum can provide guidance for future target design and implosion experiment.

physics.plasm-ph↗
arXiv2018

First Integrated Implosion Experiment of Three-Axis Cylindrical Hohlraum at the SGIII Laser Facility

The first integrated implosion experiment of three-axis cylindrical hohlraum (TACH) was accomplished at the SGIII laser facility. 24 laser beams of the SGIII laser facility were carefully chosen and quasi-symmetrically injected into the TACH, in which a highly symmetric radiation filed was generated with a peak radiation temperature of ~190eV. Driven by the radiation field, the neutron yield of a deuterium gas filled capsule reached ~1e9, and the corresponding yield over clean (YOC) was ~40% for a convergence ratio (Cr) of ~17. The X-ray self-emission image of imploded capsule cores was nearly round, and the backscatter fraction of laser beams was less than 1.25%. This experiment preliminarily demonstrated the major performance of TACH, such as the robustness of symmetry, and a laser plasma instability (LPI) behavior similar to that of the outer ring of traditional cylindrical hohlraum.

physics.plasm-ph↗
arXiv2018

Discreteness of silting objects and t-structures in triangulated categories

We introduce the notion of ST-pairs of triangulated subcategories, a prototypical example of which is the pair of the bound homotopy category and the bound derived category of a finite-dimensional algebra. For an ST-pair $(\C,\D)$, we construct an order-preserving map from silting objects in $\C$ to bounded $t$-structures on $\D$ and show that the map is bijective if and only if $\C$ is silting-discrete if and only if $\D$ is $t$-discrete. Based on a work of Qiu and Woolf, the above result is applied to show that if $\C$ is silting-discrete then the stability space of $\D$ is contractible. This is used to obtain the contractibility of the stability spaces of some Calabi--Yau triangulated categories associated to Dynkin quivers.

math.RT↗
arXiv2018

Saliency deep embedding for aurora image search

Deep neural networks have achieved remarkable success in the field of image search. However, the state-of-the-art algorithms are trained and tested for natural images captured with ordinary cameras. In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images. To reduce the interference from uninformative regions and focus on the most interested regions, we propose a saliency proposal network (SPN) to replace the region proposal network (RPN) in the recent Mask R-CNN. In our SPN, the centers of the anchors are not distributed in a rectangular meshing manner, but exhibit spherical distortion. Additionally, the directions of the anchors are along the deformation lines perpendicular to the magnetic meridian, which perfectly accords with the imaging principle of circular fisheye lens. Extensive experiments are performed on the big aurora data, demonstrating the superiority of our method in both search accuracy and efficiency.

cs.CV↗
arXiv2018

Silting reduction and Calabi--Yau reduction of triangulated categories

It is shown that the silting reduction $\ct/\thick\cp$ of a triangulated category $\ct$ with respect to a presilting subcategory $\cp$ can be realized as a certain subfactor category of $\ct$, and that there is a one-to-one correspondence between the set of (pre)silting subcategories of $\ct$ containing $\cp$ and the set of (pre)silting subcategories of $\ct/\thick\cp$. This is analogous to a result for Calabi-Yau reduction. This result is applied to show that Amiot-Guo-Keller's construction of $d$-Calabi-Yau triangulated categories with $d$-cluster-tilting objects takes silting reduction to Calabi-Yau reduction.

math.RT↗