Filter by type:

Sort by year:

Adaptive Graph Convolutional Neural Networks

Ruoyu Li, Sheng Wang, Feiyun Zhu, Junzhou Huang
Conference Papers The 32rd AAAI Conference on Artificial Intelligence (AAAI'18), February 2018.

Abstract

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training. To efficiently learn the graph, a distance metric learning is proposed. Extensive experiments on nine graph-structured datasets have demonstrated the superior performance improvement on both convergence speed and predictive accuracy.

Learning Graph While Training: An Evolving Graph Convolutional Neural Network

Ruoyu Li, Junzhou Huang
Conference Papers arXiv preprint arXiv:1708.04675 (2017).

Abstract

Convolution Neural Networks on Graphs are important generalization and extension of classical CNNs. While previous works generally assumed that the graph structures of samples are regular with unified dimensions, in many applications, they are highly diverse or even not well defined. Under some circumstances, e.g. chemical molecular data, clustering or coarsening for simplifying the graphs is hard to be justified chemically. In this paper, we propose a more general and flexible graph convolution network (EGCN) fed by batch of arbitrarily shaped data together with their evolving graph Laplacians trained in supervised fashion. Extensive experiments have been conducted to demonstrate the superior performance in terms of both the acceleration of parameter fitting and the significantly improved prediction accuracy on multiple graph-structured datasets.

Fast Preconditioning for Accelerated Multi-contrast MRI Reconstruction

Ruoyu Li, Yeqing Li, Ruogu Fang, Shaoting Zhang, Hao Pan, Junzhou Huang
Conference PapersThe 18th Annual International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'15), October 2015.

Abstract

Real-time reconstruction in multi-contrast magnetic resonance imaging (MC-MRI) is very challenging due to the slow scanning and reconstruction process. In this study, we propose a novel algorithm to accelerate the MC-MRI reconstruction in the framework of compressed sensing. The problem is formulated as the minimization of the least square data fitting with joint total variation (JTV) regularization term. We first utilized the iterative reweighted least square (IRLS) framework to reformulate the problem. A joint preconditioner is dexterously designed to efficiently compute the inverse of large transform matrix at each iteration. We compared our algorithm with eight cutting-edge compressive sensing MRI algorithms on real MC-MRI dataset. Extensive experiments demonstrate that the proposed algorithm can achieve far better reconstruction performance than all other eight cutting-edge methods.

Multi-frequency Diffuse Optical Tomography for Cancer Detection

Chen Chen, Venkaiah C Kavuri, Xinlong Wang, Ruoyu Li, Hanli Liu, Junzhou Huang
Conference Papers The 12th IEEE International Symposium on Biomedical Imaging, (ISBI'15), April 2015.

Abstract

Previous work has validated that the accuracy of absorption coefficient can be improved using frequency-domain (FD) DOT measurements with multiple modulation frequencies. In this paper, we investigate the use of multi-frequency FD-DOT to improve the recovery accuracy of scattering coefficient, which is of great interest to cancer study. A new method called the clustered sparsity reconstruction (CSR) is proposed to reconstruct the absorption and scattering coefficients jointly. We conduct numerical simulations for FD-DOT image reconstruction with multi-modulation frequencies. The numerical results show that the recovery accuracy of scattering coefficient can be significantly improved using multi-frequency data and the proposed CSR method. It is interesting to demonstrate that the combination of two modulation frequencies results in the best reconstruction accuracy in terms of contrast-to-noise ratio (CNR) and root-mean-square error (RMSE), while more number of modulation frequencies does not improve the image quality much.

Fast Regions-of-interest Detection in Whole Slide Histopathology Images

Ruoyu Li, Junzhou Huang
Conference Papers The 1st International Workshop on Patch-based Techniques in Medical Imaging, PMI'15, October 2015.

Abstract

In this paper, we present a novel superpixel based Region of Interest (ROI) search and segmentation algorithm. The proposed superpixel generation method differs from pioneer works due to its combination of boundary update and coarse-to-fine refinement for superpixel clustering. The former maintains the accuracy of segmentation, meanwhile, avoids much of unnecessary revisit to the 'non-boundary' pixels. The latter reduces the complexity by faster localizing those boundary blocks. The paper introduces the novel superpixel algorithm [10] to the problem of ROI detection and segmentation along with a coarse-to-fine refinement scheme over a set of image of different magnification. Extensive experiments indicates that the proposed method gives better accuracy and efficiency than other superpixel-based methods for lung cancer cell images. Moreover, the block-wise coarse-to-fine scheme enables a quick search and segmentation of ROIs in whole slide images, while, other methods still cannot.

Hybrid Maximum Likelihood Modulation Classification Using Multiple Radios

Onur Ozdemir, Ruoyu Li, Pramod K Varshney
Journal PapersIEEE Communications Letters, Volume: 17, Issue: 10, October 2013

Abstract

In this paper, we focus on amplitude-phase modulations and propose a modulation classification framework based on centralized data fusion using multiple radios and the hybrid maximum likelihood (ML) approach. In order to alleviate the computational complexity associated with ML estimation, we adopt the Expectation Maximization (EM) algorithm. Due to SNR diversity, the proposed multi-radio framework provides robustness to channel SNR. Numerical results show the superiority of the proposed approach with respect to single radio approaches as well as to modulation classifiers using moments based estimators.