arXiv subjects

Zhijian Yang

Publications and source records attributed to Zhijian Yang.

35 records · Page 2Linked to original sources

arXiv2022

Subtyping brain diseases from imaging data

The imaging community has increasingly adopted machine learning (ML) methods to provide individualized imaging signatures related to disease diagnosis, prognosis, and response to treatment. Clinical neuroscience and cancer imaging have been two areas in which ML has offered particular promise. However, many neurologic and neuropsychiatric diseases, as well as cancer, are often heterogeneous in terms of their clinical manifestations, neuroanatomical patterns or genetic underpinnings. Therefore, in such cases, seeking a single disease signature might be ineffectual in delivering individualized precision diagnostics. The current chapter focuses on ML methods, especially semi-supervised clustering, that seek disease subtypes using imaging data. Work from Alzheimer Disease and its prodromal stages, psychosis, depression, autism, and brain cancer are discussed. Our goal is to provide the readers with a broad overview in terms of methodology and clinical applications.

cs.LG↗

arXiv2022

Continuity of the attractors in time-dependent spaces and applications

In this paper, we investigate the continuity of the attractors in time-dependent phase spaces. (i) We establish two abstract criteria on the upper semicontinuity and the residual continuity of the pullback $\mathscr D$-attractor with respect to the perturbations, and an equivalence criterion between their continuity and the pullback equi-attraction, which generalize the continuity theory of attractors developed recently in [27,28] to that in time-dependent spaces. (ii) We propose the notion of pullback $\mathscr D$-exponential attractor, which includes the notion of time-dependent exponential attractor [33] as its spacial case, and establish its existence and Hölder continuity criterion via quasi-stability method introduced originally by Chueshov and Lasiecka [12,13]. (iii) We apply above-mentioned criteria to the semilinear damped wave equations with perturbed time-dependent speed of propagation: $\eρ(t) u_{tt}+αu_t -Δu+f(u)=g$, with perturbation parameter $\e\in(0, 1]$, to realize above mentioned continuity of pullback $\mathscr D$ and $\mathscr D$-exponential attractors in time-dependent phase spaces, and the method developed here allows to overcome the difficulty of the hyperbolicity of the model. These results deepen and extend recent theory of attractors in time-dependent spaces in literatures [15,20,19].

math.AP↗

arXiv2021

PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound

Reconstructing the 3D pose of a person in metric scale from a single view image is a geometrically ill-posed problem. For example, we can not measure the exact distance of a person to the camera from a single view image without additional scene assumptions (e.g., known height). Existing learning based approaches circumvent this issue by reconstructing the 3D pose up to scale. However, there are many applications such as virtual telepresence, robotics, and augmented reality that require metric scale reconstruction. In this paper, we show that audio signals recorded along with an image, provide complementary information to reconstruct the metric 3D pose of the person. The key insight is that as the audio signals traverse across the 3D space, their interactions with the body provide metric information about the body's pose. Based on this insight, we introduce a time-invariant transfer function called pose kernel -- the impulse response of audio signals induced by the body pose. The main properties of the pose kernel are that (1) its envelope highly correlates with 3D pose, (2) the time response corresponds to arrival time, indicating the metric distance to the microphone, and (3) it is invariant to changes in the scene geometry configurations. Therefore, it is readily generalizable to unseen scenes. We design a multi-stage 3D CNN that fuses audio and visual signals and learns to reconstruct 3D pose in a metric scale. We show that our multi-modal method produces accurate metric reconstruction in real world scenes, which is not possible with state-of-the-art lifting approaches including parametric mesh regression and depth regression.

cs.CV↗

arXiv2021

Multidimensional representations in late-life depression: convergence in neuroimaging, cognition, clinical symptomatology and genetics

Late-life depression (LLD) is characterized by considerable heterogeneity in clinical manifestation. Unraveling such heterogeneity would aid in elucidating etiological mechanisms and pave the road to precision and individualized medicine. We sought to delineate, cross-sectionally and longitudinally, disease-related heterogeneity in LLD linked to neuroanatomy, cognitive functioning, clinical symptomatology, and genetic profiles. Multimodal data from a multicentre sample (N=996) were analyzed. A semi-supervised clustering method (HYDRA) was applied to regional grey matter (GM) brain volumes to derive dimensional representations. Two dimensions were identified, which accounted for the LLD-related heterogeneity in voxel-wise GM maps, white matter (WM) fractional anisotropy (FA), neurocognitive functioning, clinical phenotype, and genetics. Dimension one (Dim1) demonstrated relatively preserved brain anatomy without WM disruptions relative to healthy controls. In contrast, dimension two (Dim2) showed widespread brain atrophy and WM integrity disruptions, along with cognitive impairment and higher depression severity. Moreover, one de novo independent genetic variant (rs13120336) was significantly associated with Dim 1 but not with Dim 2. Notably, the two dimensions demonstrated significant SNP-based heritability of 18-27% within the general population (N=12,518 in UKBB). Lastly, in a subset of individuals having longitudinal measurements, Dim2 demonstrated a more rapid longitudinal decrease in GM and brain age, and was more likely to progress to Alzheimers disease, compared to Dim1 (N=1,413 participants and 7,225 scans from ADNI, BLSA, and BIOCARD datasets).

q-bio.NC↗

arXiv2021

Exponential attractor for the viscoelastic wave model with time-dependent memory kernels

The paper is concerned with the exponential attractors for the viscoelastic wave model in $Ω\subset \mathbb R^3$: $$u_{tt}-h_t(0)Δu-\int_0^\infty\partial_sh_t(s)Δu(t-s)\mathrm ds+f(u)=h,$$ with time-dependent memory kernel $h_t(\cdot)$ which is used to model aging phenomena of the material. Conti et al [Amer. J. Math., 2018] recently provided the correct mathematical setting for the model and a well-posedness result within the novel theory of dynamical systems acting on. time-dependent spaces, recently established by Conti, Pata and Temam [J. Differential Equations, 2013], and proved the existence and the regularity of the time-dependent global attractor. In this work, we further study the existence of the time-dependent exponential attractors as well as their regularity. We establish an abstract existence criterion via quasi-stability method introduced originally by Chueshov and Lasiecka [J. Dynam. Diff.Eqs.,2004], and on the basis of the theory and technique developed in [Amer. J. Math., 2018] we further provide a new method to overcome the difficulty of the lack of further regularity to show the existence of the time-dependent exponential attractor. And these techniques can be used to tackle other hyperbolic models.

math.AP↗

arXiv2021

Convergence Rate Analysis for Deep Ritz Method

Using deep neural networks to solve PDEs has attracted a lot of attentions recently. However, why the deep learning method works is falling far behind its empirical success. In this paper, we provide a rigorous numerical analysis on deep Ritz method (DRM) \cite{wan11} for second order elliptic equations with Neumann boundary conditions. We establish the first nonasymptotic convergence rate in $H^1$ norm for DRM using deep networks with $\mathrm{ReLU}^2$ activation functions. In addition to providing a theoretical justification of DRM, our study also shed light on how to set the hyper-parameter of depth and width to achieve the desired convergence rate in terms of number of training samples. Technically, we derive bounds on the approximation error of deep $\mathrm{ReLU}^2$ network in $H^1$ norm and on the Rademacher complexity of the non-Lipschitz composition of gradient norm and $\mathrm{ReLU}^2$ network, both of which are of independent interest.

math.NA↗

arXiv2021

Disentangling brain heterogeneity via semi-supervised deep-learning and MRI: dimensional representations of Alzheimer's Disease

Heterogeneity of brain diseases is a challenge for precision diagnosis/prognosis. We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a novel semi-supervised deep-clustering method, which dissects neuroanatomical heterogeneity, enabling identification of disease subtypes via their imaging signatures relative to controls. When applied to MRIs (2 studies; 2,832 participants; 8,146 scans) including cognitively normal individuals and those with cognitive impairment and dementia, Smile-GAN identified 4 neurodegenerative patterns/axes: P1, normal anatomy and highest cognitive performance; P2, mild/diffuse atrophy and more prominent executive dysfunction; P3, focal medial temporal atrophy and relatively greater memory impairment; P4, advanced neurodegeneration. Further application to longitudinal data revealed two distinct progression pathways: P1$\rightarrow$P2$\rightarrow$P4 and P1$\rightarrow$P3$\rightarrow$P4. Baseline expression of these patterns predicted the pathway and rate of future neurodegeneration. Pattern expression offered better yet complementary performance in predicting clinical progression, compared to amyloid/tau. These deep-learning derived biomarkers offer promise for precision diagnostics and targeted clinical trial recruitment.

cs.LG↗

arXiv2020

Generative Learning With Euler Particle Transport

We propose an Euler particle transport (EPT) approach for generative learning. The proposed approach is motivated by the problem of finding an optimal transport map from a reference distribution to a target distribution characterized by the Monge-Ampere equation. Interpreting the infinitesimal linearization of the Monge-Ampere equation from the perspective of gradient flows in measure spaces leads to a stochastic McKean-Vlasov equation. We use the forward Euler method to solve this equation. The resulting forward Euler map pushes forward a reference distribution to the target. This map is the composition of a sequence of simple residual maps, which are computationally stable and easy to train. The key task in training is the estimation of the density ratios or differences that determine the residual maps. We estimate the density ratios (differences) based on the Bregman divergence with a gradient penalty using deep density-ratio (difference) fitting. We show that the proposed density-ratio (difference) estimators do not suffer from the "curse of dimensionality" if data is supported on a lower-dimensional manifold. Numerical experiments with multi-mode synthetic datasets and comparisons with the existing methods on real benchmark datasets support our theoretical results and demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2020

Smile-GANs: Semi-supervised clustering via GANs for dissecting brain disease heterogeneity from medical images

Machine learning methods applied to complex biomedical data has enabled the construction of disease signatures of diagnostic/prognostic value. However, less attention has been given to understanding disease heterogeneity. Semi-supervised clustering methods can address this problem by estimating multiple transformations from a (e.g. healthy) control (CN) group to a patient (PT) group, seeking to capture the heterogeneity of underlying pathlogic processes. Herein, we propose a novel method, Smile-GANs (SeMi-supervIsed cLustEring via GANs), for semi-supervised clustering, and apply it to brain MRI scans. Smile-GANs first learns multiple distinct mappings by generating PT from CN, with each mapping characterizing one relatively distinct pathological pattern. Moreover, a clustering model is trained interactively with mapping functions to assign PT into corresponding subtype memberships. Using relaxed assumptions on PT/CN data distribution and imposing mapping non-linearity, Smile-GANs captures heterogeneous differences in distribution between the CN and PT domains. We first validate Smile-GANs using simulated data, subsequently on real data, by demonstrating its potential in characterizing heterogeneity in Alzheimer's Disease (AD) and its prodromal phases. The model was first trained using baseline MRIs from the ADNI2 database and then applied to longitudinal data from ADNI1 and BLSA. Four robust subtypes with distinct neuroanatomical patterns were discovered: 1) normal brain, 2) diffuse atrophy atypical of AD, 3) focal medial temporal lobe atrophy, 4) typical-AD. Further longitudinal analyses discover two distinct progressive pathways from prodromal to full AD: i) subtypes 1 - 2 - 4, and ii) subtypes 1 - 3 - 4. Although demonstrated on an important biomedical problem, Smile-GANs is general and can find application in many biomedical and other domains.

q-bio.QM↗

arXiv2020

Robust Decoding from Binary Measurements with Cardinality Constraint Least Squares

The main goal of 1-bit compressive sampling is to decode $n$ dimensional signals with sparsity level $s$ from $m$ binary measurements. This is a challenging task due to the presence of nonlinearity, noises and sign flips. In this paper, the cardinality constraint least square is proposed as a desired decoder. We prove that, up to a constant $c$, with high probability, the proposed decoder achieves a minimax estimation error as long as $m \geq \mathcal{O}( s\log n)$. Computationally, we utilize a generalized Newton algorithm (GNA) to solve the cardinality constraint minimization problem with the cost of solving a least squares problem with small size at each iteration. We prove that, with high probability, the $\ell_{\infty}$ norm of the estimation error between the output of GNA and the underlying target decays to $\mathcal{O}(\sqrt{\frac{\log n }{m}}) $ after at most $\mathcal{O}(\log s)$ iterations. Moreover, the underlying support can be recovered with high probability in $\mathcal{O}(\log s)$ steps provided that the target signal is detectable. Extensive numerical simulations and comparisons with state-of-the-art methods are presented to illustrate the robustness of our proposed decoder and the efficiency of the GNA algorithm.

cs.IT↗

arXiv2020

A machine learning approach to using Quality-of-Life patient scores in guiding prostate radiation therapy dosing

Thanks to advancements in diagnosis and treatment, prostate cancer patients have high long-term survival rates. Currently, an important goal is to preserve quality-of-life during and after treatment. The relationship between the radiation a patient receives and the subsequent side effects he experiences is complex and difficult to model or predict. Here, we use machine learning algorithms and statistical models to explore the connection between radiation treatment and post-treatment gastro-urinary function. Since only a limited number of patient datasets are currently available, we used image flipping and curvature-based interpolation methods to generate more data in order to leverage transfer learning. Using interpolated and augmented data, we trained a convolutional autoencoder network to obtain near-optimal starting points for the weights. A convolutional neural network then analyzed the relationship between patient-reported quality-of-life and radiation. We also used analysis of variance and logistic regression to explore organ sensitivity to radiation and develop dosage thresholds for each organ region. Our findings show no connection between the bladder and quality-of-life scores. However, we found a connection between radiation applied to posterior and anterior rectal regions to changes in quality-of-life. Finally, we estimated radiation therapy dosage thresholds for each organ. Our analysis connects machine learning methods with organ sensitivity, thus providing a framework for informing cancer patient care using patient reported quality-of-life metrics.

q-bio.QM↗

arXiv2019

Uniform attractors of non-autonomous Kirchhoff wave models

The paper investigates the existence and upper semicontinuity of uniform attractors of the perturbed non-autonomous Kirchhoff wave equations with strong damping and supercritical nonlinearity: $u_{tt}-Δu_{t}-(1+ε\|\nabla u\|^{2})Δu+f(u)=g(x,t)$, where $ε\in [0,1]$ is a perturbed parameter. It shows that when the nonlinearity $f(u)$ is of supercritical growth $p: \frac{N+2}{N-2}=p^*<p<p^{**}=\frac{N+4}{(N-4)^+}$: (i) the related evolution process has a compact uniform attractor $\mathcal{A}_\ls^\e $ for each $ε\in [0,1]$; (ii) the family of uniform attractor $\mathcal{A}_\ls^\e $ is upper semicontinuous on the perturbed parameter $ε$ in the sense of partially strong topology.

math.AP↗

arXiv2019

Global attractors and their upper semicontinuity for a structural damped wave equation with supercritical nonlinearity on $\mathbb{R}^{N}$

The paper investigates the existence of global attractors and their upper semicontinuity for a structural damped wave equation on $\mathbb{R}^{N}: u_{tt}-Δu+(-Δ)^αu_{t}+u_{t}+u+g(u)=f(x)$, where $α\in (1/2, 1)$ is called a dissipative index. We propose a new method based on the harmonic analysis technique and the commutator estimate to exploit the dissipative effect of the structural damping $(-Δ)^αu_{t}$ and to overcome the essential difficulty: "both the unbounded domain $\mathbb{R}^N$ and the supercritical nonlinearity cause that the Sobolev embedding loses its compactness"; Meanwhile we show that there exists a supercritical index $p_α\equiv\frac{N+4α}{N-4α}$ depending on $α$ such that when the growth exponent $p$ of the nonlinearity $g(u)$ is up to the supercritical range: $1\leqslant p 0$; (ii) the related solution semigroup possesses a global attractor $\mathcal{A}_α$ in natural energy space for each $α\in (1/2, 1)$; (iii) the family of global attractors $\{\mathcal{A}_α\}_{α\in (1/2, 1) }$ is upper semicontinuous at each point $α_0\in (1/2, 1)$.

math.AP↗

arXiv2019

A finite element method by patch reconstruction for the Stokes problem using mixed formulations

In this paper, we develop a patch reconstruction finite element method for the Stokes problem. The weak formulation of the interior penalty discontinuous Galerkin is employed. The proposed method has a great flexibility in velocity-pressure space pairs whose stability properties are confirmed by the inf-sup tests. Numerical examples show the applicability and efficiency of the proposed method.

math.NA↗

arXiv2018

A Discontinuous Galerkin Method for the Stokes Equation by Divergence-free Patch Reconstruction

A discontinuous Galerkin method by patch reconstruction is proposed for Stokes flows. A locally divergence-free reconstruction space is employed as the approximation space, and the interior penalty method is adopted which imposes the normal component penalty terms to cancel out the pressure term. Consequently, the Stokes equation can be solved as an elliptic system instead of a saddle-point problem due to such weak form. The number of degree of freedoms of our method is the same as the number of elements in the mesh for different order of accuracy. The error estimations of the proposed method are given in a classical style, which are then verified by some numerical examples.

math.NA↗

arXiv2018

A Discontinuous Galerkin Method by Patch Reconstruction for Biharmonic Problem

We propose a new discontinuous Galerkin method based on the least-squares patch reconstruction for the biharmonic problem. We prove the optimal error estimate of the proposed method. The two-dimensional and three-dimensional numerical examples are presented to confirm the accuracy and efficiency of the method with several boundary conditions and several types of polygon meshes and polyhedral meshes.

math.NA↗

arXiv2018

An Arbitrary-Order Discontinuous Galerkin Method with One Unknown Per Element

We propose an arbitrary-order discontinuous Galerkin method for second-order elliptic problem on general polygonal mesh with only one degree of freedom per element. This is achieved by locally solving a discrete least-squares over a neighboring element patch. Under a geometrical condition on the element patch, we prove an optimal a priori error estimates for the energy norm and for the L$^2$ norm. The accuracy and the efficiency of the method up to order six on several polygonal meshes are illustrated by a set of benchmark problems.

math.NA↗