Hai Shu
Hai Shu
Scroll
Assistant Professor of Biostatistics
-
Professional overview
-
Dr. Hai Shu is an Assistant Professor in the Department of Biostatistics at New York University. He earned a Ph.D. in Biostatistics from University of Michigan and a B.S. in Information and Computational Science from Harbin Institute of Technology in China.
His research interests include high-dimensional data analysis (esp. data integration), machine/deep learning, medical image analysis (e.g., PET, MRI, Mammography), and their applications in Alzheimer’s disease, brain tumors, breast cancer, etc. He has published relevant papers in top-tier journals and conference, such as The Annals of Statistics, Journal of the American Statistical Association, Biometrics, and AAAI Conference on Artificial Intelligence. He has also served as a reviewer on related topics for Journal of the American Statistical Association, Statistica Sinica, International Joint Conference on Artificial Intelligence, etc.
Prior to joining NYU, Dr. Hai Shu was a Postdoctoral Fellow in the Department of Biostatistics at The University of Texas MD Anderson Cancer Center.
View Dr. Hai Shu's website at https://wp.nyu.edu/haishu
-
Education
-
Postdoctoral Fellow, Department of Biostatistics, The University of Texas MD Anderson Cancer Center, USAPh.D. in Biostatistics, Department of Biostatistics, University of Michigan, Ann Arbor, USAM.S. in Biostatistics, Department of Biostatistics, University of Michigan, Ann Arbor, USAB.S. in Information and Computational Science, Department of Mathematics, Harbin Institute of Technology (哈尔滨工业大学), China
-
Areas of research and study
-
Alzheimer’s diseaseBrain tumorsBreast cancerDeep learningHigh-dimensional data analysis/integrationMachine learningMedical image analysisSpatial/temporal data analysis
-
Publications
Publications
Conditional Diffusion Models Based Conditional Independence Testing
AbstractYang, Y., Li, S., Zhang, Y., Sun, Z., Shu, H., Chen, Z., & Zhang, R. (n.d.).Publication year
2025Journal title
Proceedings of the AAAI Conference on Artificial IntelligenceVolume
39Issue
21Page(s)
22020-22028AbstractConditional independence (CI) testing is a fundamental task in modern statistics and machine learning. The conditional randomization test (CRT) was recently introduced to test whether two random variables, X and Y , are conditionally independent given a potentially high-dimensional set of random variables, Z. The CRT operates exceptionally well under the assumption that the conditional distribution X|Z is known. However, since this distribution is typically unknown in practice, accurately approximating it becomes crucial. In this paper, we propose using conditional diffusion models (CDMs) to learn the distribution of X|Z. Theoretically and empirically, it is shown that CDMs closely approximate the true conditional distribution. Furthermore, CDMs offer a more accurate approximation of X|Z compared to GANs, potentially leading to a CRT that performs better than those based on GANs. To accommodate complex dependency structures, we utilize a computationally efficient classifier-based conditional mutual information (CMI) estimator as our test statistic. The proposed testing procedure performs effectively without requiring assumptions about specific distribution forms or feature dependencies, and is capable of handling mixed-type conditioning sets that include both continuous and discrete variables. Theoretical analysis shows that our proposed test achieves a valid control of the type I error. A series of experiments on synthetic data demonstrates that our new test effectively controls both type-I and type-II errors, even in high dimensional scenarios.NCCT-to-CECT synthesis with contrast-enhanced knowledge and anatomical perception for multi-organ segmentation in non-contrast CT images
AbstractZhong, L., Xiao, R., Shu, H., Zheng, K., Li, X., Wu, Y., Ma, J., Feng, Q., & Yang, W. (n.d.).Publication year
2025Journal title
Medical Image AnalysisVolume
100AbstractContrast-enhanced computed tomography (CECT) is constantly used for delineating organs-at-risk (OARs) in radiation therapy planning. The delineated OARs are needed to transfer from CECT to non-contrast CT (NCCT) for dose calculation. Yet, the use of iodinated contrast agents (CA) in CECT and the dose calculation errors caused by the spatial misalignment between NCCT and CECT images pose risks of adverse side effects. A promising solution is synthesizing CECT images from NCCT scans, which can improve the visibility of organs and abnormalities for more effective multi-organ segmentation in NCCT images. However, existing methods neglect the difference between tissues induced by CA and lack the ability to synthesize the details of organ edges and blood vessels. To address these issues, we propose a contrast-enhanced knowledge and anatomical perception network (CKAP-Net) for NCCT-to-CECT synthesis. CKAP-Net leverages a contrast-enhanced knowledge learning network to capture both similarities and dissimilarities in domain characteristics attributable to CA. Specifically, a CA-based perceptual loss function is introduced to enhance the synthesis of CA details. Furthermore, we design a multi-scale anatomical perception transformer that utilizes multi-scale anatomical information from NCCT images, enabling the precise synthesis of tissue details. Our CKAP-Net is evaluated on a multi-center abdominal NCCT-CECT dataset, a head an neck NCCT-CECT dataset, and an NCMRI-CEMRI dataset. It achieves a MAE of 25.96 ± 2.64, a SSIM of 0.855 ± 0.017, and a PSNR of 32.60 ± 0.02 for CECT synthesis, and a DSC of 81.21 ± 4.44 for segmentation on the internal dataset. Extensive experiments demonstrate that CKAP-Net outperforms state-of-the-art CA synthesis methods and has better generalizability across different datasets.Comments on : Data integration via analysis of subspaces (DIVAS)
AbstractShu, H., & Zhu, H. (n.d.).Publication year
2024Journal title
TestVolume
33Issue
3Page(s)
686-688Abstract~DeepFDR : A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
AbstractKim, T., Shu, H., Jia, Q., & de Leon, M. J. (n.d.).Publication year
2024Journal title
Proceedings of Machine Learning ResearchVolume
238Page(s)
946-954AbstractVoxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer’s disease FDG-PET image analysis, demonstrate DeepFDR’s superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.Multi-Scale Tokens-Aware Transformer Network for Multi-Region and Multi-Sequence MR-to-CT Synthesis in a Single Model
AbstractZhong, L., Chen, Z., Shu, H., Zheng, K., Li, Y., Chen, W., Wu, Y., Ma, J., Feng, Q., & Yang, W. (n.d.).Publication year
2024Journal title
IEEE Transactions on Medical ImagingVolume
43Issue
2Page(s)
794-806AbstractThe superiority of magnetic resonance (MR)-only radiotherapy treatment planning (RTP) has been well demonstrated, benefiting from the synthesis of computed tomography (CT) images which supplements electron density and eliminates the errors of multi-modal images registration. An increasing number of methods has been proposed for MR-to-CT synthesis. However, synthesizing CT images of different anatomical regions from MR images with different sequences using a single model is challenging due to the large differences between these regions and the limitations of convolutional neural networks in capturing global context information. In this paper, we propose a multi-scale tokens-aware Transformer network (MTT-Net) for multi-region and multi-sequence MR-to-CT synthesis in a single model. Specifically, we develop a multi-scale image tokens Transformer to capture multi-scale global spatial information between different anatomical structures in different regions. Besides, to address the limited attention areas of tokens in Transformer, we introduce a multi-shape window self-attention into Transformer to enlarge the receptive fields for learning the multi-directional spatial representations. Moreover, we adopt a domain classifier in generator to introduce the domain knowledge for distinguishing the MR images of different regions and sequences. The proposed MTT-Net is evaluated on a multi-center dataset and an unseen region, and remarkable performance was achieved with MAE of 69.33 ± 10.39 HU, SSIM of 0.778 ± 0.028, and PSNR of 29.04 ± 1.32 dB in head & neck region, and MAE of 62.80 ± 7.65 HU, SSIM of 0.617 ± 0.058 and PSNR of 25.94 ± 1.02 dB in abdomen region. The proposed MTT-Net outperforms state-of-the-art methods in both accuracy and visual quality.A generic fundus image enhancement network boosted by frequency self-supervised representation learning
AbstractLi, H., Liu, H., Fu, H., Xu, Y., Shu, H., Niu, K., Hu, Y., & Liu, J. (n.d.).Publication year
2023Journal title
Medical Image AnalysisVolume
90AbstractFundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on degraded images, high data demands and limited applicability hinder their clinical deployment. To circumvent this bottleneck, a generic fundus image enhancement network (GFE-Net) is developed in this study to robustly correct unknown fundus images without supervised or extra data. Levering image frequency information, self-supervised representation learning is conducted to learn robust structure-aware representations from degraded images. Then with a seamless architecture that couples representation learning and image enhancement, GFE-Net can accurately correct fundus images and meanwhile preserve retinal structures. Comprehensive experiments are implemented to demonstrate the effectiveness and advantages of GFE-Net. Compared with state-of-the-art algorithms, GFE-Net achieves superior performance in data dependency, enhancement performance, deployment efficiency, and scale generalizability. Follow-up fundus image analysis is also facilitated by GFE-Net, whose modules are respectively verified to be effective for image enhancement.Cross-Task Feedback Fusion GAN for Joint MR-CT Synthesis and Segmentation of Target and Organs-At-Risk
AbstractZhang, Y., Zhong, L., Shu, H., Dai, Z., Zheng, K., Chen, Z., Feng, Q., Wang, X., & Yang, W. (n.d.).Publication year
2023Journal title
IEEE Transactions on Artificial IntelligenceVolume
4Issue
5Page(s)
1246 - 1257AbstractThe synthesis of computed tomography (CT) images from magnetic resonance imaging (MR) images and segmentation of target and organs-at-risk (OARs) are two important tasks in MR-only radiotherapy treatment planning (RTP). Some methods have been proposed to utilize the paired MR and CT images for MR-CT synthesis or target and OARs segmentation. However, these methods usually handle synthesis and segmentation as two separate tasks, and ignore the inevitable registration errors in paired images after standard registration. In this paper, we propose a cross-task feedback fusion generative adversarial network (CTFF-GAN) for joint MR-CT synthesis and segmentation of target and OARs to enhance each task’s performance. Specifically, we propose a cross-task feedback fusion (CTFF) module to feedback the semantic information from the segmentation task to the synthesis task for the anatomical structure correction in synthetic CT images. Besides, we use CT images synthesized from MR images for multi-modal segmentation to eliminate the registration errors. Moreover, we develop a multi-task discriminator to urge the generator to devote more attention to the organ boundaries. Experiments on our nasopharyngeal carcinoma dataset show that CTFF-GAN achieves impressive performance with MAE of 70.69 $\pm$ 10.50 HU, SSIM of 0.755 $\pm$ 0.03, and PSNR of 27.44 $\pm$ 1.20 dB in synthetic CT, and the mean Dice of 0.783 $\pm$ 0.075 in target and OARs segmentation. Our CTFF-GAN outperforms state-of-the-art methods in both the synthesis and segmentation tasks. Impact Statement—Radiation therapy is a crucial part of cancer treatment, with nearly half of all cancer patients receiving it at some point during their illness. It usually takes a radiation oncologist several hours to delineate the targets and organs-at-risk (OARs) for a radiotherapy treatment planning (RTP). Worse, the inevitable registration errors between computed tomography (CT) images and magnetic resonance imaging (MR) images increase the uncertainty of delineation. Although some deep-learning based segmentation and synthesis methods have been proposed to solve the above-mentioned difficulties respectively, they ignore the potential relationship between the two tasks. The technology proposed in this paper takes the synergy of synthesis and segmentation into account and achieves superior performance in both tasks. Our method can automatically realize MR-CT synthesis and segmentation of targets and OARs only based on MR images in half a minute, which will simplify the workflow of RTP and improve the efficiency of radiation oncologist.DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
AbstractKim, T., Shu, H., Jia, Q., & de Leon, M. (n.d.).Publication year
2023AbstractVoxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer's disease FDG-PET image analysis, demonstrate DeepFDR's superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data. [Journal_ref: The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024)]Domain Adaptative Retinal Image Quality Assessment with Knowledge Distillation Using Competitive Teacher-Student Network
AbstractLin, Y., Li, H., Liu, H., Shu, H., Li, Z., Hu, Y., & Liu, J. (n.d.).Publication year
2023AbstractRetinal image quality assessment (RIQA) is essential for retinal examinations, as it impacts the certainty of both manual and intelligent diagnosis. Unfortunately, domain shifts, such as the variance of colors and illumination, are prone to confuse RIQA. Though efficient domain adaptation solutions have been proposed, properly transferring RIQA models to new domains remains a troublesome task. This paper presents a domain adaptative RIQA algorithm with knowledge distillation using a competitive teacher-student network (CTSN) to address the above issue. The main structure consists of a teacher network, a student network, and a competition module. The teacher network provides pseudo-labels by adapting source and target domain features, and the student network learns features from target-specific pseudo-labels. The competition module boosts the fine-grained adaptation of RIQA. Comparison experiments and ablation studies demonstrate that our method performs outstandingly in RIQA with domain shifts.Efficient Estimation in Linear Regression with DivergingCovariates
AbstractChen, Z., Wen, W., Shu, H., Tang, M.-L., & Zhu, H. (n.d.).Publication year
2023Journal title
Statistica SinicaAbstract~Invited talk: D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data
AbstractShu, H., Qu, Z., & Zhu, H. (n.d.).Publication year
2023AbstractInvited talk at ICSA 2023 Applied Statistics Symposium, Ann Arbor, MI, USAInvited talk: D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data
AbstractShu, H., Qu, Z., & Zhu, H. (n.d.).Publication year
2023AbstractInvited talk at The 12th ICSA International Conference, Hong Kong, ChinaInvited talk: D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data
AbstractShu, H., Qu, Z., & Zhu, H. (n.d.).Publication year
2023AbstractInvited talk at ICSA 2023 China Conference, Chengdu, ChinaK-Nearest-Neighbor Local Sampling Based Conditional Independence Testing
AbstractLi, S., Zhang, Y., Zhu, H., Wang, C., Shu, H., Chen, Z., Sun, Z., & Yang, Y. (n.d.).Publication year
2023Abstract~K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing
AbstractLi, S., Zhang, Y., Zhu, H., Wang, C. D., Shu, H., Chen, Z., Sun, Z., & Yang, Y. (n.d.).Publication year
2023Journal title
Advances in Neural Information Processing SystemsVolume
36AbstractConditional independence (CI) testing is a fundamental task in statistics and machine learning, but its effectiveness is hindered by the challenges posed by high-dimensional conditioning variables and limited data samples. This article introduces a novel testing approach to address these challenges and enhance control of the type I error while achieving high power under alternative hypotheses. The proposed approach incorporates a computationally efficient classifier-based conditional mutual information (CMI) estimator, capable of capturing intricate dependence structures among variables. To approximate a distribution encoding the null hypothesis, a k-nearest-neighbor local sampling strategy is employed. An important advantage of this approach is its ability to operate without assumptions about distribution forms or feature dependencies. Furthermore, it eliminates the need to derive asymptotic null distributions for the estimated CMI and avoids dataset splitting, making it particularly suitable for small datasets. The method presented in this article demonstrates asymptotic control of the type I error and consistency against all alternative hypotheses. Extensive analyses using both synthetic and real data highlight the computational efficiency of the proposed test. Moreover, it outperforms existing state-of-the-art methods in terms of type I and II errors, even in scenarios with high-dimensional conditioning sets. Additionally, the proposed approach exhibits robustness in the presence of heavy-tailed data.Multi-Scale Tokens-Aware Transformer Network for Multi-Region and Multi-Sequence MR-to-CT Synthesis in a Single Model
AbstractZhong, L., Chen, Z., Shu, H., Zheng, K., Li, Y., Chen, W., Wu, Y., Ma, J., Feng, Q., & Yang, W. (n.d.).Publication year
2023Journal title
IEEE Transactions on Medical ImagingAbstract~QACL : Quartet attention aware closed-loop learning for abdominal MR-to-CT synthesis via simultaneous registration
AbstractZhong, L., Chen, Z., Shu, H., Zheng, Y., Zhang, Y., Wu, Y., Feng, Q., Li, Y., & Yang, W. (n.d.).Publication year
2023Journal title
Medical Image AnalysisVolume
83AbstractSynthesis of computed tomography (CT) images from magnetic resonance (MR) images is an important task to overcome the lack of electron density information in MR-only radiotherapy treatment planning (RTP). Some innovative methods have been proposed for abdominal MR-to-CT synthesis. However, it is still challenging due to the large misalignment between preprocessed abdominal MR and CT images and the insufficient feature information learned by models. Although several studies have used the MR-to-CT synthesis to alleviate the difficulty of multi-modal registration, this misalignment remains unsolved when training the MR-to-CT synthesis model. In this paper, we propose an end-to-end quartet attention aware closed-loop learning (QACL) framework for MR-to-CT synthesis via simultaneous registration. Specifically, the proposed quartet attention generator and mono-modal registration network form a closed-loop to improve the performance of MR-to-CT synthesis via simultaneous registration. In particular, a quartet-attention mechanism is developed to enlarge the receptive fields in networks to extract the long-range and cross-dimension spatial dependencies. Experimental results on two independent abdominal datasets demonstrate that our QACL achieves impressive results with MAE of 55.30±10.59 HU, PSNR of 22.85±1.43 dB, and SSIM of 0.83±0.04 for synthesis, and with Dice of 0.799±0.129 for registration. The proposed QACL outperforms the state-of-the-art MR-to-CT synthesis and multi-modal registration methods.Self-Supervision Boosted Retinal Vessel Segmentation for Cross-Domain Data
AbstractLi, H., Li, H., Shu, H., Chen, J., Hu, Y., & Liu, J. (n.d.).Publication year
2023AbstractThe morphology of the retinal vascular structure in fundus images is of great importance for ocular disease diagnosis. However, due to the poor fundus image quality and domain shifts between datasets, retinal vessel segmentation has long been regarded as a problematic machine-learning task. This work proposes a novel algorithm High-frequency Guided Cascaded Network (HGC-Net) to address the above issues. In our algorithm, a self-supervision mechanism is designed to improve the generalizability and robustness of the model. We apply Fourier Augmented Co-Teacher (FACT) augmentation to convert the style of fundus images, and extract high-frequency component (HFC) to highlight the vascular structure. The main structure of the algorithm is two cascaded U-nets, in which the first U-net generates a domain-invariant high-frequency map of fundus images, thus improving the segmentation stability of the second U-net. Comparison with the state-of-the-art methods and ablation study are conducted to demonstrate the excellent performance of our proposed HGC-Net.United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration
AbstractZhong, L., Huang, P., Shu, H., Li, Y., Zhang, Y., Feng, Q., Wu, Y., & Yang, W. (n.d.).Publication year
2023Journal title
Computer Methods and Programs in BiomedicineVolume
231AbstractSynthesizing abdominal contrast-enhanced computed tomography (CECT) images from non-enhanced CT (NECT) images is of great importance, in the delineation of radiotherapy target volumes, to reduce the risk of iodinated contrast agent and the registration error between NECT and CECT for transferring the delineations. NECT images contain structural information that can reflect the contrast difference between lesions and surrounding tissues. However, existing methods treat synthesis and registration as two separate tasks, which neglects the task collaborative and fails to address misalignment between images after the standard image pre-processing in training a CECT synthesis model. Thus, we propose an united multi-task learning (UMTL) for joint synthesis and deformable registration of abdominal CECT. Specifically, our UMTL is an end-to-end multi-task framework, which integrates a deformation field learning network for reducing the misalignment errors and a 3D generator for synthesizing CECT images. Furthermore, the learning of enhanced component images and the multi-loss function are adopted for enhancing the performance of synthetic CECT images. The proposed method is evaluated on two different resolution datasets and a separate test dataset from another center. The synthetic venous phase CECT images of the separate test dataset yield mean absolute error (MAE) of 32.78±7.27 HU, mean MAE of 24.15±5.12 HU on liver region, mean peak signal-to-noise rate (PSNR) of 27.59±2.45 dB, and mean structural similarity (SSIM) of 0.96±0.01. The Dice similarity coefficients of liver region between the true and synthetic venous phase CECT images are 0.96±0.05 (high-resolution) and 0.95±0.07 (low-resolution), respectively. The proposed method has great potential in aiding the delineation of radiotherapy target volumes.A Comparative Study of non-deep Learning, Deep Learning, and Ensemble Learning Methods for Sunspot Number Prediction
AbstractDang, Y., Chen, Z., Li, H., & Shu, H. (n.d.).Publication year
2022Journal title
Applied Artificial IntelligenceVolume
36Issue
1AbstractSolar activity has significant impacts on human activities and health. One most commonly used measure of solar activity is the sunspot number. This paper compares three important non-deep learning models, four popular deep learning models, and their five ensemble models in forecasting sunspot numbers. In particular, we propose an ensemble model called XGBoost-DL, which uses XGBoost as a two-level nonlinear ensemble method to combine the deep learning models. Our XGBoost-DL achieves the best forecasting performance (RMSE (Formula presented.) and MAE (Formula presented.)) in the comparison, outperforming the best non-deep learning model SARIMA (RMSE (Formula presented.) and MAE (Formula presented.)), the best deep learning model Informer (RMSE (Formula presented.) and MAE (Formula presented.)) and the NASA’s forecast (RMSE (Formula presented.) and MAE (Formula presented.)). Our XGBoost-DL forecasts a peak sunspot number of 133.47 in May 2025 for Solar Cycle 25 and 164.62 in November 2035 for Solar Cycle 26, similar to but later than the NASA’s at 137.7 in October 2024 and 161.2 in December 2034. An open-source Python package of our XGBoost-DL for the sunspot number prediction is available at https://github.com/yd1008/ts_ensemble_sunspot.Big Data and Machine Learning in Oncology
AbstractWei, P., & Shu, H. (n.d.).Publication year
2022Abstract~BiTr-Unet : A CNN-Transformer Combined Network for MRI Brain Tumor Segmentation
AbstractJia, Q., & Shu, H. (n.d.). (A. Crimi & S. Bakas, Eds.).Publication year
2022Page(s)
3-14AbstractConvolutional neural networks (CNNs) have achieved remarkable success in automatically segmenting organs or lesions on 3D medical images. Recently, vision transformer networks have exhibited exceptional performance in 2D image classification tasks. Compared with CNNs, transformer networks have an appealing advantage of extracting long-range features due to their self-attention algorithm. Therefore, we propose a CNN-Transformer combined model, called BiTr-Unet, with specific modifications for brain tumor segmentation on multi-modal MRI scans. Our BiTr-Unet achieves good performance on the BraTS2021 validation dataset with median Dice score 0.9335, 0.9304 and 0.8899, and median Hausdorff distance 2.8284, 2.2361 and 1.4142 for the whole tumor, tumor core, and enhancing tumor, respectively. On the BraTS2021 testing dataset, the corresponding results are 0.9257, 0.9350 and 0.8874 for Dice score, and 3, 2.2361 and 1.4142 for Hausdorff distance. The code is publicly available at https://github.com/JustaTinyDot/BiTr-Unet.CDPA : Common and distinctive pattern analysis between high-dimensional datasets
AbstractShu, H., & Qu, Z. (n.d.).Publication year
2022Journal title
Electronic Journal of StatisticsVolume
16Issue
1Page(s)
2475-2517AbstractA representative model in integrative analysis of two high-dimensional correlated datasets is to decompose each data matrix into a low-rank common matrix generated by latent factors shared across datasets, a low-rank distinctive matrix corresponding to each dataset, and an additive noise matrix. Existing decomposition methods claim that their common matrices capture the common pattern of the two datasets. However, their so-called common pattern only denotes the common latent factors but ig-nores the common pattern between the two coefficient matrices of these common latent factors. We propose a new unsupervised learning method, called the common and distinctive pattern analysis (CDPA), which appro-priately defines the two types of data patterns by further incorporating the common and distinctive patterns of the coefficient matrices. A consistent estimation approach is developed for high-dimensional settings, and shows reasonably good finite-sample performance in simulations. Our simulation studies and real data analysis corroborate that the proposed CDPA can provide better characterization of common and distinctive patterns and thereby benefit data mining.D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data.
AbstractShu, H., Shu, H., Qu, Z., & Zhu, H. (n.d.).Publication year
2022Journal title
Journal of Machine Learning ResearchVolume
23AbstractModern biomedical studies often collect multi-view data, that is, multiple types of data measured on the same set of objects. A popular model in high-dimensional multi-view data analysis is to decompose each view's data matrix into a low-rank common-source matrix generated by latent factors common across all data views, a low-rank distinctive-source matrix corresponding to each view, and an additive noise matrix. We propose a novel decomposition method for this model, called decomposition-based generalized canonical correlation analysis (D-GCCA). The D-GCCA rigorously defines the decomposition on the L2 space of random variables in contrast to the Euclidean dot product space used by most existing methods, thereby being able to provide the estimation consistency for the low-rank matrix recovery. Moreover, to well calibrate common latent factors, we impose a desirable orthogonality constraint on distinctive latent factors. Existing methods, however, inadequately consider such orthogonality and may thus suffer from substantial loss of undetected common-source variation. Our D-GCCA takes one step further than generalized canonical correlation analysis by separating common and distinctive components among canonical variables, while enjoying an appealing interpretation from the perspective of principal component analysis. Furthermore, we propose to use the variable-level proportion of signal variance explained by common or distinctive latent factors for selecting the variables most influenced. Consistent estimators of our D-GCCA method are established with good finite-sample numerical performance, and have closed-form expressions leading to efficient computation especially for large-scale data. The superiority of D-GCCA over state-of-the-art methods is also corroborated in simulations and real-world data examples.mFI-PSO : A Flexible and Effective Method in Adversarial Image Generation for Deep Neural Networks
AbstractShu, H., Shi, R., Jia, Q., Zhu, H., & Chen, Z. (n.d.).Publication year
2022AbstractDeep neural networks (DNNs) have achieved great success in image classification, but can be very vulnerable to adversarial attacks with small perturbations to images. To improve adversarial image generation for DNNs, we develop a novel method, called mFI-PSO, which utilizes a Manifold-based First-order Influence measure for vulnerable image and pixel selection and the Particle Swarm Optimization for various objective functions. Our mFI-PSO can thus effectively design adversarial images with flexible, customized options on the number of perturbed pixels, the misclassification probability, and the targeted incorrect class. Experiments demonstrate the flexibility and effectiveness of our mFI-PSO in adversarial attacks and its appealing advantages over some popular methods.