1
|
Jeon ES, Choi H, Shukla A, Wang Y, Lee H, Buman MP, Turaga P. Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024; 130:107719. [PMID: 38282698 PMCID: PMC10810240 DOI: 10.1016/j.engappai.2023.107719] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/30/2024]
Abstract
Deep learning methods have achieved a lot of success in various applications involving converting wearable sensor data to actionable health insights. A common application areas is activity recognition, where deep-learning methods still suffer from limitations such as sensitivity to signal quality, sensor characteristic variations, and variability between subjects. To mitigate these issues, robust features obtained by topological data analysis (TDA) have been suggested as a potential solution. However, there are two significant obstacles to using topological features in deep learning: (1) large computational load to extract topological features using TDA, and (2) different signal representations obtained from deep learning and TDA which makes fusion difficult. In this paper, to enable integration of the strengths of topological methods in deep-learning for time-series data, we propose to use two teacher networks - one trained on the raw time-series data, and another trained on persistence images generated by TDA methods. These two teachers are jointly used to distill a single student model, which utilizes only the raw time-series data at test-time. This approach addresses both issues. The use of KD with multiple teachers utilizes complementary information, and results in a compact model with strong supervisory features and an integrated richer representation. To assimilate desirable information from different modalities, we design new constraints, including orthogonality imposed on feature correlation maps for improving feature expressiveness and allowing the student to easily learn from the teacher. Also, we apply an annealing strategy in KD for fast saturation and better accommodation from different features, while the knowledge gap between the teachers and student is reduced. Finally, a robust student model is distilled, which can at test-time uses only the time-series data as an input, while implicitly preserving topological features. The experimental results demonstrate the effectiveness of the proposed method on wearable sensor data. The proposed method shows 71.74% in classification accuracy on GENEActiv with WRN16-1 (1D CNNs) student, which outperforms baselines and takes much less processing time (less than 17 sec) than teachers on 6k testing samples.
Collapse
Affiliation(s)
- Eun Som Jeon
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State, University, Tempe, 85281, AZ, USA
| | - Hongjun Choi
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State, University, Tempe, 85281, AZ, USA
| | - Ankita Shukla
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State, University, Tempe, 85281, AZ, USA
| | - Yuan Wang
- Department of Epidemiology and Biostatistics, University of South Carolina, Columbia, 29208, SC, USA
| | - Hyunglae Lee
- School for Engineering of Matter, Transport and Energy, Tempe, 85281, AZ, USA
| | - Matthew P Buman
- College of Health Solutions, Arizona State University, Phoenix, 85004, AZ, USA
| | - Pavan Turaga
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State, University, Tempe, 85281, AZ, USA
| |
Collapse
|
2
|
Wang Z, Liu F, Shi S, Xia S, Peng F, Wang L, Ai S, Xu Z. Automatic epileptic seizure detection based on persistent homology. Front Physiol 2023; 14:1227952. [PMID: 38192741 PMCID: PMC10773586 DOI: 10.3389/fphys.2023.1227952] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Accepted: 11/28/2023] [Indexed: 01/10/2024] Open
Abstract
Epilepsy is a prevalent brain disease, which is quite difficult-to-treat or cure. This study developed a novel automatic seizure detection method based on the persistent homology method. In this study, a Vietoris-Rips (VR) complex filtration model was constructed based on the EEG data. And the persistent homology method was applied to calculate the VR complex filtration barcodes to describe the topological changes of EEG recordings. Afterward, the barcodes as the topological characteristics of EEG signals were fed into the GoogLeNet for classification. The persistent homology is applicable for multi-channel EEG data analysis, where the global topological information is calculated and the features are extracted by considering the multi-channel EEG data as a whole, without the multiple calculations or the post-stitching. Three databases were used to evaluate the proposed approach and the results showed that the approach had high performances in the epilepsy detection. The results obtained from the CHB-MIT Database recordings revealed that the proposed approach can achieve a segment-based averaged accuracy, sensitivity and specificity values of 97.05%, 96.71% and 97.38%, and achieve an event-based averaged sensitivity value of 100% with 1.22Â s average detection latency. In addition, on the Siena Scalp Database, the proposed method yields averaged accuracy, sensitivity and specificity values of 96.42%, 95.23% and 97.6%. Multiple tasks of the Bonn Database also showed achieved accuracy of 99.55%, 98.63%, 98.28% and 97.68%, respectively. The experimental results on these three EEG databases illustrate the efficiency and robustness of our approach for automatic detection of epileptic seizure.
Collapse
Affiliation(s)
- Ziyu Wang
- School of Science, Shandong Jianzhu University, Jinan, China
| | - Feifei Liu
- School of Science, Shandong Jianzhu University, Jinan, China
| | - Shuhua Shi
- School of Science, Shandong Jianzhu University, Jinan, China
| | - Shengxiang Xia
- School of Science, Shandong Jianzhu University, Jinan, China
| | - Fulai Peng
- Medical Rehabilitation Research Center, Shandong Institute of Advanced Technology, Chinese Academy of Sciences, Jinan, China
| | - Lin Wang
- The Fifth People’s Hospital of Jinan, Jinan, China
| | - Sen Ai
- School of Science, Shandong Jianzhu University, Jinan, China
| | - Zheng Xu
- School of Science, Shandong Jianzhu University, Jinan, China
| |
Collapse
|
3
|
Jeon ES, Choi H, Shukla A, Wang Y, Buman MP, Turaga P. Constrained Adaptive Distillation Based on Topological Persistence for Wearable Sensor Data. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023; 72:2532014. [PMID: 38818128 PMCID: PMC11137740 DOI: 10.1109/tim.2023.3329818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/01/2024]
Abstract
Wearable sensor data analysis with persistence features generated by topological data analysis (TDA) has achieved great successes in various applications, however, it suffers from large computational and time resources for extracting topological features. In this paper, our approach utilizes knowledge distillation (KD) that involves the use of multiple teacher networks trained with the raw time-series and persistence images generated by TDA, respectively. However, direct transfer of knowledge from the teacher models utilizing different characteristics as inputs to the student model results in a knowledge gap and limited performance. To address this problem, we introduce a robust framework that integrates multimodal features from two different teachers and enables a student to learn desirable knowledge effectively. To account for statistical differences in multimodalities, entropy based constrained adaptive weighting mechanism is leveraged to automatically balance the effects of teachers and encourage the student model to adequately adopt the knowledge from two teachers. To assimilate dissimilar structural information generated by different style models for distillation, batch and channel similarities within a mini-batch are used. We demonstrate the effectiveness of the proposed method on wearable sensor data.
Collapse
Affiliation(s)
- Eun Som Jeon
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| | - Hongjun Choi
- Lawrence Livermore National Laboratory, Livermore, CA, USA
| | - Ankita Shukla
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| | - Yuan Wang
- Department of Epidemiology and Biostatistics, University of South Carolina, Columbia, SC 29208 USA
| | - Matthew P Buman
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004 USA
| | - Pavan Turaga
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| |
Collapse
|
4
|
Wang Y, Yin J, Desai RH. Topological inference on brain networks across subtypes of post-stroke aphasia. ARXIV 2023:arXiv:2311.01625v1. [PMID: 37961747 PMCID: PMC10635302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 11/15/2023]
Abstract
Persistent homology (PH) characterizes the shape of brain networks through the persistence features. Group comparison of persistence features from brain networks can be challenging as they are inherently heterogeneous. A recent scale-space representation of persistence diagram (PD) through heat diffusion reparameterizes using the finite number of Fourier coefficients with respect to the Laplace-Beltrami (LB) eigenfunction expansion of the domain, which provides a powerful vectorized algebraic representation for group comparisons of PDs. In this study, we advance a transposition-based permutation test for comparing multiple groups of PDs through the heat-diffusion estimates of the PDs. We evaluate the empirical performance of the spectral transposition test in capturing within- and between-group similarity and dissimilarity with respect to statistical variation of topological noise and hole location. We also illustrate how the method extends naturally into a clustering scheme by subtyping individuals with post-stroke aphasia through the PDs of their resting-state functional brain networks.
Collapse
Affiliation(s)
- Yuan Wang
- Department of Epidemiology and Biostatistics University of South Carolina U.S.A
| | - Jian Yin
- Department of Biostatistics Nanjing Medical University China
| | | |
Collapse
|
5
|
Jeon ES, Choi H, Shukla A, Wang Y, Buman MP, Turaga P. Topological Knowledge Distillation for Wearable Sensor Data. CONFERENCE RECORD. ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS 2022; 2022:837-842. [PMID: 37583442 PMCID: PMC10426276 DOI: 10.1109/ieeeconf56349.2022.10052019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/17/2023]
Abstract
Converting wearable sensor data to actionable health insights has witnessed large interest in recent years. Deep learning methods have been utilized in and have achieved a lot of successes in various applications involving wearables fields. However, wearable sensor data has unique issues related to sensitivity and variability between subjects, and dependency on sampling-rate for analysis. To mitigate these issues, a different type of analysis using topological data analysis has shown promise as well. Topological data analysis (TDA) captures robust features, such as persistence images (PI), in complex data through the persistent homology algorithm, which holds the promise of boosting machine learning performance. However, because of the computational load required by TDA methods for large-scale data, integration and implementation has lagged behind. Further, many applications involving wearables require models to be compact enough to allow deployment on edge-devices. In this context, knowledge distillation (KD) has been widely applied to generate a small model (student model), using a pre-trained high-capacity network (teacher model). In this paper, we propose a new KD strategy using two teacher models - one that uses the raw time-series and another that uses persistence images from the time-series. These two teachers then train a student using KD. In essence, the student learns from heterogeneous teachers providing different knowledge. To consider different properties in features from teachers, we apply an annealing strategy and adaptive temperature in KD. Finally, a robust student model is distilled, which utilizes the time series data only. We find that incorporation of persistence features via second teacher leads to significantly improved performance. This approach provides a unique way of fusing deep-learning with topological features to develop effective models.
Collapse
Affiliation(s)
- Eun Som Jeon
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| | - Hongjun Choi
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| | - Ankita Shukla
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| | - Yuan Wang
- Department of Epidemiology and Biostatistics, University of South Carolina, Columbia, SC 29208 USA
| | - Matthew P Buman
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004 USA
| | - Pavan Turaga
- Geometric Media Lab, School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA
| |
Collapse
|
6
|
Skaf Y, Laubenbacher R. Topological data analysis in biomedicine: A review. J Biomed Inform 2022; 130:104082. [PMID: 35508272 DOI: 10.1016/j.jbi.2022.104082] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Revised: 03/20/2022] [Accepted: 04/23/2022] [Indexed: 01/22/2023]
Abstract
Significant technological advances made in recent years have shepherded a dramatic increase in utilization of digital technologies for biomedicine- everything from the widespread use of electronic health records to improved medical imaging capabilities and the rising ubiquity of genomic sequencing contribute to a "digitization" of biomedical research and clinical care. With this shift toward computerized tools comes a dramatic increase in the amount of available data, and current tools for data analysis capable of extracting meaningful knowledge from this wealth of information have yet to catch up. This article seeks to provide an overview of emerging mathematical methods with the potential to improve the abilities of clinicians and researchers to analyze biomedical data, but may be hindered from doing so by a lack of conceptual accessibility and awareness in the life sciences research community. In particular, we focus on topological data analysis (TDA), a set of methods grounded in the mathematical field of algebraic topology that seeks to describe and harness features related to the "shape" of data. We aim to make such techniques more approachable to non-mathematicians by providing a conceptual discussion of their theoretical foundations followed by a survey of their published applications to scientific research. Finally, we discuss the limitations of these methods and suggest potential avenues for future work integrating mathematical tools into clinical care and biomedical informatics.
Collapse
Affiliation(s)
- Yara Skaf
- University of Florida, Department of Mathematics, Gainesville, FL, USA; University of Florida, Department of Medicine, Division of Pulmonary, Critical Care, & Sleep Medicine, Gainesville, FL, USA.
| | - Reinhard Laubenbacher
- University of Florida, Department of Mathematics, Gainesville, FL, USA; University of Florida, Department of Medicine, Division of Pulmonary, Critical Care, & Sleep Medicine, Gainesville, FL, USA.
| |
Collapse
|
7
|
Grbić J, Wu J, Xia K, Wei GW. ASPECTS OF TOPOLOGICAL APPROACHES FOR DATA SCIENCE. FOUNDATIONS OF DATA SCIENCE (SPRINGFIELD, MO.) 2022; 4:165-216. [PMID: 36712596 PMCID: PMC9881677 DOI: 10.3934/fods.2022002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/18/2023]
Abstract
We establish a new theory which unifies various aspects of topological approaches for data science, by being applicable both to point cloud data and to graph data, including networks beyond pairwise interactions. We generalize simplicial complexes and hypergraphs to super-hypergraphs and establish super-hypergraph homology as an extension of simplicial homology. Driven by applications, we also introduce super-persistent homology.
Collapse
Affiliation(s)
- Jelena Grbić
- School of Mathematical Sciences, University of Southampton, Southampton, UK
| | - Jie Wu
- School of Mathematical Sciences, Center of Topology and Geometry based Technology, Hebei Normal University, Yuhua District, Shijiazhuang, Hebei, 050024 China
- Yanqi Lake Beijing Institute of Mathematica Sciences, Yanqihu, Huairou District, Beijing, 101408 China
| | - Kelin Xia
- School of Physical and Mathematical Sciences, Nanyang Technological University, SPMS-MAS-05-18, 21 Nanyang Link, 1, Singapore 63737
| | - Guo-Wei Wei
- Department of Mathematics, Department of Computer Science and Engineering, Department of Biochemistry and Molecular Biology, Michigan State University, MI 48824, USA
| |
Collapse
|
8
|
Feng J, Zhang SW, Chen L. Extracting ROI-Based Contourlet Subband Energy Feature From the sMRI Image for Alzheimer's Disease Classification. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:1627-1639. [PMID: 33434134 DOI: 10.1109/tcbb.2021.3051177] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) classification and its prodromal stage-mild cognitive impairment (MCI) classification have attracted many attentions and been widely investigated in recent years. Owing to the high dimensionality, representation of the sMRI image becomes a difficult issue in AD classification. Furthermore, regions of interest (ROI) reflected in the sMRI image are not characterized properly by spatial analysis techniques, which has been a main cause of weakening the discriminating ability of the extracted spatial feature. In this study, we propose a ROI-based contourlet subband energy (ROICSE) feature to represent the sMRI image in the frequency domain for AD classification. Specifically, a preprocessed sMRI image is first segmented into 90 ROIs by a constructed brain mask. Instead of extracting features from the 90 ROIs in the spatial domain, the contourlet transform is performed on each of these ROIs to obtain their energy subbands. And then for an ROI, a subband energy (SE) feature vector is constructed to capture its energy distribution and contour information. Afterwards, SE feature vectors of the 90 ROIs are concatenated to form a ROICSE feature of the sMRI image. Finally, support vector machine (SVM) classifier is used to classify 880 subjects from ADNI and OASIS databases. Experimental results show that the ROICSE approach outperforms six other state-of-the-art methods, demonstrating that energy and contour information of the ROI are important to capture differences between the sMRI images of AD and HC subjects. Meanwhile, brain regions related to AD can also be found using the ROICSE feature, indicating that the ROICSE feature can be a promising assistant imaging marker for the AD diagnosis via the sMRI image. Code and Sample IDs of this paper can be downloaded at https://github.com/NWPU-903PR/ROICSE.git.
Collapse
|
9
|
Pun CS, Lee SX, Xia K. Persistent-homology-based machine learning: a survey and a comparative study. Artif Intell Rev 2022. [DOI: 10.1007/s10462-022-10146-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
10
|
Chen J, Zhao R, Tong Y, Wei GW. EVOLUTIONARY DE RHAM-HODGE METHOD. DISCRETE AND CONTINUOUS DYNAMICAL SYSTEMS. SERIES B 2021; 26:3785-3821. [PMID: 34675756 DOI: 10.3934/dcdsb.2020257] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
The de Rham-Hodge theory is a landmark of the 20th Century's mathematics and has had a great impact on mathematics, physics, computer science, and engineering. This work introduces an evolutionary de Rham-Hodge method to provide a unified paradigm for the multiscale geometric and topological analysis of evolving manifolds constructed from a filtration, which induces a family of evolutionary de Rham complexes. While the present method can be easily applied to close manifolds, the emphasis is given to more challenging compact manifolds with 2-manifold boundaries, which require appropriate analysis and treatment of boundary conditions on differential forms to maintain proper topological properties. Three sets of unique evolutionary Hodge Laplacians are proposed to generate three sets of topology-preserving singular spectra, for which the multiplicities of zero eigenvalues correspond to exactly the persistent Betti numbers of dimensions 0, 1 and 2. Additionally, three sets of non-zero eigenvalues further reveal both topological persistence and geometric progression during the manifold evolution. Extensive numerical experiments are carried out via the discrete exterior calculus to demonstrate the potential of the proposed paradigm for data representation and shape analysis of both point cloud data and density maps. To demonstrate the utility of the proposed method, the application is considered to the protein B-factor predictions of a few challenging cases for which existing biophysical models break down.
Collapse
Affiliation(s)
- Jiahui Chen
- Department of Mathematics, Michigan State University, MI 48824, USA
| | - Rundong Zhao
- Department of Computer Science and Engineering, Michigan State University, MI 48824, USA
| | - Yiying Tong
- Department of Computer Science and Engineering, Michigan State University, MI 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, MI 48824, USA
| |
Collapse
|
11
|
Samani EU, Yang X, Banerjee AG. Visual Object Recognition in Indoor Environments Using Topologically Persistent Features. IEEE Robot Autom Lett 2021. [DOI: 10.1109/lra.2021.3099460] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
12
|
Yen PTW, Xia K, Cheong SA. Understanding Changes in the Topology and Geometry of Financial Market Correlations during a Market Crash. ENTROPY (BASEL, SWITZERLAND) 2021; 23:1211. [PMID: 34573837 PMCID: PMC8467365 DOI: 10.3390/e23091211] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/19/2021] [Revised: 09/05/2021] [Accepted: 09/06/2021] [Indexed: 12/24/2022]
Abstract
In econophysics, the achievements of information filtering methods over the past 20 years, such as the minimal spanning tree (MST) by Mantegna and the planar maximally filtered graph (PMFG) by Tumminello et al., should be celebrated. Here, we show how one can systematically improve upon this paradigm along two separate directions. First, we used topological data analysis (TDA) to extend the notions of nodes and links in networks to faces, tetrahedrons, or k-simplices in simplicial complexes. Second, we used the Ollivier-Ricci curvature (ORC) to acquire geometric information that cannot be provided by simple information filtering. In this sense, MSTs and PMFGs are but first steps to revealing the topological backbones of financial networks. This is something that TDA can elucidate more fully, following which the ORC can help us flesh out the geometry of financial networks. We applied these two approaches to a recent stock market crash in Taiwan and found that, beyond fusions and fissions, other non-fusion/fission processes such as cavitation, annihilation, rupture, healing, and puncture might also be important. We also successfully identified neck regions that emerged during the crash, based on their negative ORCs, and performed a case study on one such neck region.
Collapse
Affiliation(s)
- Peter Tsung-Wen Yen
- Center for Crystal Researches, National Sun Yet-Sen University, No. 70, Lien-hai Rd., Kaohsiung 80424, Taiwan;
| | - Kelin Xia
- Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, Singapore 637371, Singapore;
| | - Siew Ann Cheong
- Division of Physics and Applied Physics, School of Physical and Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, Singapore 637371, Singapore
| |
Collapse
|
13
|
Caputi L, Pidnebesna A, Hlinka J. Promises and pitfalls of topological data analysis for brain connectivity analysis. Neuroimage 2021; 238:118245. [PMID: 34111515 DOI: 10.1016/j.neuroimage.2021.118245] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2021] [Revised: 05/30/2021] [Accepted: 06/05/2021] [Indexed: 11/17/2022] Open
Abstract
Developing sensitive and reliable methods to distinguish normal and abnormal brain states is a key neuroscientific challenge. Topological Data Analysis, despite its relative novelty, already generated many promising applications, including in neuroscience. We conjecture its prominent tool of persistent homology may benefit from going beyond analysing structural and functional connectivity to effective connectivity graphs capturing the direct causal interactions or information flows. Therefore, we assess the potential of persistent homology to directed brain network analysis by testing its discriminatory power in two distinctive examples of disease-related brain connectivity alterations: epilepsy and schizophrenia. We estimate connectivity from functional magnetic resonance imaging and electrophysiology data, employ Persistent Homology and quantify its ability to distinguish healthy from diseased brain states by applying a support vector machine to features quantifying persistent homology structure. We show how this novel approach compares to classification using standard undirected approaches and original connectivity matrices. In the schizophrenia classification, topological data analysis generally performs close to random, while classifications from raw connectivity perform substantially better; potentially due to topographical, rather than topological, specificity of the differences. In the easier task of seizure discrimination from scalp electroencephalography data, classification based on persistent homology features generally reached comparable performance to using raw connectivity, albeit with typically smaller accuracies obtained for the directed (effective) connectivity compared to the undirected (functional) connectivity. Specific applications for topological data analysis may open when direct comparison of connectivity matrices is unsuitable - such as for intracranial electrophysiology with individual number and location of measurements. While standard homology performed overall better than directed homology, this could be due to notorious technical problems of accurate effective connectivity estimation.
Collapse
Affiliation(s)
- Luigi Caputi
- Institute of Computer Science of the Czech Academy of Sciences, Pod Vodárenskou věžà 271/2, Prague 182 07, Czech Republic.
| | - Anna Pidnebesna
- Institute of Computer Science of the Czech Academy of Sciences, Pod Vodárenskou věžà 271/2, Prague 182 07, Czech Republic; National Institute of Mental Health, Topolová 748, Klecany 250 67, Czech Republic; Faculty of Electrical Engineering, Czech Technical University, Technická 1902/2, Prague 166 27, Czech Republic.
| | - Jaroslav Hlinka
- Institute of Computer Science of the Czech Academy of Sciences, Pod Vodárenskou věžà 271/2, Prague 182 07, Czech Republic; National Institute of Mental Health, Topolová 748, Klecany 250 67, Czech Republic.
| |
Collapse
|
14
|
Zhao X, Ang CKE, Acharya UR, Cheong KH. Application of Artificial Intelligence techniques for the detection of Alzheimer’s disease using structural MRI images. Biocybern Biomed Eng 2021. [DOI: 10.1016/j.bbe.2021.02.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
|
15
|
Ismail MS, Md Noorani MS, Ismail M, Abdul Razak F, Alias MA. Predicting next day direction of stock price movement using machine learning methods with persistent homology: Evidence from Kuala Lumpur Stock Exchange. Appl Soft Comput 2020. [DOI: 10.1016/j.asoc.2020.106422] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
16
|
Feng J, Zhang SW, Chen L. Identification of Alzheimer's disease based on wavelet transformation energy feature of the structural MRI image and NN classifier. Artif Intell Med 2020; 108:101940. [DOI: 10.1016/j.artmed.2020.101940] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2020] [Revised: 07/01/2020] [Accepted: 08/07/2020] [Indexed: 02/07/2023]
|
17
|
Weighted persistent homology for osmolyte molecular aggregation and hydrogen-bonding network analysis. Sci Rep 2020; 10:9685. [PMID: 32546801 PMCID: PMC7297731 DOI: 10.1038/s41598-020-66710-6] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2019] [Accepted: 05/20/2020] [Indexed: 12/24/2022] Open
Abstract
It has long been observed that trimethylamine N-oxide (TMAO) and urea demonstrate dramatically different properties in a protein folding process. Even with the enormous theoretical and experimental research work on these two osmolytes, various aspects of their underlying mechanisms still remain largely elusive. In this paper, we propose to use the weighted persistent homology to systematically study the osmolytes molecular aggregation and their hydrogen-bonding network from a local topological perspective. We consider two weighted models, i.e., localized persistent homology (LPH) and interactive persistent homology (IPH). Boltzmann persistent entropy (BPE) is proposed to quantitatively characterize the topological features from LPH and IPH, together with persistent Betti number (PBN). More specifically, from the localized persistent homology models, we have found that TMAO and urea have very different local topology. TMAO is found to exhibit a local network structure. With the concentration increase, the circle elements in these networks show a clear increase in their total numbers and a decrease in their relative sizes. In contrast, urea shows two types of local topological patterns, i.e., local clusters around 6 Ă… and a few global circle elements at around 12 Ă…. From the interactive persistent homology models, it has been found that our persistent radial distribution function (PRDF) from the global-scale IPH has same physical properties as the traditional radial distribution function. Moreover, PRDFs from the local-scale IPH can also be generated and used to characterize the local interaction information. Other than the clear difference of the first peak value of PRDFs at filtration size 4 Ă…, TMAO and urea also shows very different behaviors at the second peak region from filtration size 5 Ă… to 10 Ă…. These differences are also reflected in the PBNs and BPEs of the local-scale IPH. These localized topological information has never been revealed before. Since graphs can be transferred into simplicial complexes by the clique complex, our weighted persistent homology models can be used in the analysis of various networks and graphs from any molecular structures and aggregation systems.
Collapse
|
18
|
Chen X, Chen D, Weng M, Jiang Y, Wei GW, Pan F. Topology-Based Machine Learning Strategy for Cluster Structure Prediction. J Phys Chem Lett 2020; 11:4392-4401. [PMID: 32320253 PMCID: PMC7351018 DOI: 10.1021/acs.jpclett.0c00974] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
In cluster physics, the determination of the ground-state structure of medium-sized and large-sized clusters is a challenge due to the number of local minimal values on the potential energy surface growing exponentially with cluster size. Although machine learning approaches have had much success in materials sciences, their applications in clusters are often hindered by the geometric complexity clusters. Persistent homology provides a new topological strategy to simplify geometric complexity while retaining important chemical and physical information without having to "downgrade" the original data. We further propose persistent pairwise independence (PPI) to enhance the predictive power of persistent homology. We construct topology-based machine learning models to reveal hidden structure-energy relationships in lithium (Li) clusters. We integrate the topology-based machine learning models, a particle swarm optimization algorithm, and density functional theory calculations to accelerate the search of the globally stable structure of clusters.
Collapse
Affiliation(s)
- Xin Chen
- School of Advanced Materials, Shenzhen Graduate School, Peking University, Shenzhen 518055, People's Republic of China
| | - Dong Chen
- School of Advanced Materials, Shenzhen Graduate School, Peking University, Shenzhen 518055, People's Republic of China
| | - Mouyi Weng
- School of Advanced Materials, Shenzhen Graduate School, Peking University, Shenzhen 518055, People's Republic of China
| | - Yi Jiang
- School of Advanced Materials, Shenzhen Graduate School, Peking University, Shenzhen 518055, People's Republic of China
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, United States
| | - Feng Pan
- School of Advanced Materials, Shenzhen Graduate School, Peking University, Shenzhen 518055, People's Republic of China
| |
Collapse
|
19
|
Som A, Choi H, Ramamurthy KN, Buman MP, Turaga P. PI-Net: A Deep Learning Approach to Extract Topological Persistence Images. CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS. IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION. WORKSHOPS 2020; 2020:3639-3648. [PMID: 32995068 PMCID: PMC7521829 DOI: 10.1109/cvprw50498.2020.00425] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. This is greatly attributed to the robustness topological representations provide against different types of physical nuisance variables seen in real-world data, such as view-point, illumination, and more. However, key bottlenecks to their large scale adoption are computational expenditure and difficulty incorporating them in a differentiable architecture. We take an important step in this paper to mitigate these bottlenecks by proposing a novel one-step approach to generate PIs directly from the input data. We design two separate convolutional neural network architectures, one designed to take in multi-variate time series signals as input and another that accepts multi-channel images as input. We call these networks Signal PI-Net and Image PI-Net respectively. To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data. We explore the use of the proposed PI-Net architectures on two applications: human activity recognition using tri-axial accelerometer sensor data and image classification. We demonstrate the ease of fusion of PIs in supervised deep learning architectures and speed up of several orders of magnitude for extracting PIs from data. Our code is available at https://github.com/anirudhsom/PI-Net.
Collapse
Affiliation(s)
- Anirudh Som
- School of Arts, Media and Engineering, Arizona State University
- School of Electrical, Computer and Energy Engineering, Arizona State University
| | - Hongjun Choi
- School of Arts, Media and Engineering, Arizona State University
- School of Electrical, Computer and Energy Engineering, Arizona State University
| | | | | | - Pavan Turaga
- School of Arts, Media and Engineering, Arizona State University
- School of Electrical, Computer and Energy Engineering, Arizona State University
| |
Collapse
|
20
|
Wang L, Liu Y, Zeng X, Cheng H, Wang Z, Wang Q. Region-of-Interest based sparse feature learning method for Alzheimer's disease identification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 187:105290. [PMID: 31927305 DOI: 10.1016/j.cmpb.2019.105290] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/02/2019] [Revised: 12/17/2019] [Accepted: 12/19/2019] [Indexed: 06/10/2023]
Abstract
BACKGROUND AND OBJECTIVE In recent years, some clinical parameters, such as the volume of gray matter (GM) and cortical thickness, have been used as anatomical features to identify Alzheimer's disease (AD) from Healthy Controls (HC) in some feature-based machine learning methods. However, fewer image-based feature parameters have been proposed, which are equivalent to these clinical parameters, to describe the atrophy of regions-of-interest (ROIs) of the brain. In this study, we aim to extract effective image-based feature parameters to improve the diagnostic performance of AD with magnetic resonance imaging (MRI) data. METHODS A new subspace-based sparse feature learning method is proposed, which builds a union-of-subspace representation model to realize feature extraction and disease identification. Specifically, the proposed method estimates feature dimensions reasonably, at the same time, it protects local features for the specified ROIs of the brain, and realizes image-based feature extraction and classification automatically instead of computing the volume of GM or cortical thickness preliminarily. RESULTS Experimental results illustrate the effectiveness and robustness of the proposed method on feature extraction and classification, which are based on the sampled clinical dataset from Peking University Third Hospital of China and the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The extracted image-based feature parameters describe the atrophy of ROIs of the brain well as clinical parameters but show better performance in AD identification than clinical parameters. Based on them, the important ROIs for AD identification can be identified even for correlated variables. CONCLUSION The extracted features and the proposed identification parameters show high correlation with the volume of GM and the clinical mini-mental state examination (MMSE) score respectively. The proposed method will be useful in denoting the changes of cerebral pathology and cognitive function in AD patients.
Collapse
Affiliation(s)
- Ling Wang
- Center for Robotics, University of Electronic Science and Technology of China, Chengdu, 611731 China
| | - Yan Liu
- School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, 100049 China.
| | - Xiangzhu Zeng
- Department of Radiology, Peking University Third Hospital, Beijing, 100191 China.
| | - Hong Cheng
- Center for Robotics, University of Electronic Science and Technology of China, Chengdu, 611731 China
| | - Zheng Wang
- Department of Radiology, Peking University Third Hospital, Beijing, 100191 China
| | - Qiang Wang
- Beijing Union University, Beijing, 100101 China
| |
Collapse
|
21
|
Weighted persistent homology for biomolecular data analysis. Sci Rep 2020; 10:2079. [PMID: 32034168 PMCID: PMC7005716 DOI: 10.1038/s41598-019-55660-3] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2019] [Accepted: 11/29/2019] [Indexed: 11/08/2022] Open
Abstract
In this paper, we systematically review weighted persistent homology (WPH) models and their applications in biomolecular data analysis. Essentially, the weight value, which reflects physical, chemical and biological properties, can be assigned to vertices (atom centers), edges (bonds), or higher order simplexes (cluster of atoms), depending on the biomolecular structure, function, and dynamics properties. Further, we propose the first localized weighted persistent homology (LWPH). Inspired by the great success of element specific persistent homology (ESPH), we do not treat biomolecules as an inseparable system like all previous weighted models, instead we decompose them into a series of local domains, which may be overlapped with each other. The general persistent homology or weighted persistent homology analysis is then applied on each of these local domains. In this way, functional properties, that are embedded in local structures, can be revealed. Our model has been applied to systematically study DNA structures. It has been found that our LWPH based features can be used to successfully discriminate the A-, B-, and Z-types of DNA. More importantly, our LWPH based principal component analysis (PCA) model can identify two configurational states of DNA structures in ion liquid environment, which can be revealed only by the complicated helical coordinate system. The great consistence with the helical-coordinate model demonstrates that our model captures local structure variations so well that it is comparable with geometric models. Moreover, geometric measurements are usually defined in local regions. For instance, the helical-coordinate system is limited to one or two basepairs. However, our LWPH can quantitatively characterize structure information in regions or domains with arbitrary sizes and shapes, where traditional geometrical measurements fail.
Collapse
|
22
|
Xia K, Anand DV, Shikhar S, Mu Y. Persistent homology analysis of osmolyte molecular aggregation and their hydrogen-bonding networks. Phys Chem Chem Phys 2019; 21:21038-21048. [DOI: 10.1039/c9cp03009c] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
Dramatically different patterns can be observed in the topological fingerprints for hydrogen-bonding networks from two types of osmolyte systems.
Collapse
Affiliation(s)
- Kelin Xia
- Division of Mathematical Sciences
- School of Physical and Mathematical Sciences
- School of Biological Sciences
- Nanyang Technological University
- Singapore
| | - D. Vijay Anand
- Division of Mathematical Sciences
- School of Physical and Mathematical Sciences
- School of Biological Sciences
- Nanyang Technological University
- Singapore
| | - Saxena Shikhar
- School of Biological Sciences
- Nanyang Technological University
- Singapore
| | - Yuguang Mu
- School of Biological Sciences
- Nanyang Technological University
- Singapore
| |
Collapse
|
23
|
Solo V, Poline JB, Lindquist MA, Simpson SL, Bowman FD, Chung MK, Cassidy B. Connectivity in fMRI: Blind Spots and Breakthroughs. IEEE TRANSACTIONS ON MEDICAL IMAGING 2018; 37:1537-1550. [PMID: 29969406 PMCID: PMC6291757 DOI: 10.1109/tmi.2018.2831261] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
In recent years, driven by scientific and clinical concerns, there has been an increased interest in the analysis of functional brain networks. The goal of these analyses is to better understand how brain regions interact, how this depends upon experimental conditions and behavioral measures and how anomalies (disease) can be recognized. In this paper, we provide, first, a brief review of some of the main existing methods of functional brain network analysis. But rather than compare them, as a traditional review would do, instead, we draw attention to their significant limitations and blind spots. Then, second, relevant experts, sketch a number of emerging methods, which can break through these limitations. In particular we discuss five such methods. The first two, stochastic block models and exponential random graph models, provide an inferential basis for network analysis lacking in the exploratory graph analysis methods. The other three addresses: network comparison via persistent homology, time-varying connectivity that distinguishes sample fluctuations from neural fluctuations, and network system identification that draws inferential strength from temporal autocorrelation.
Collapse
|
24
|
Xia K. Persistent homology analysis of ion aggregations and hydrogen-bonding networks. Phys Chem Chem Phys 2018; 20:13448-13460. [PMID: 29722784 DOI: 10.1039/c8cp01552j] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
Despite the great advancement of experimental tools and theoretical models, a quantitative characterization of the microscopic structures of ion aggregates and their associated water hydrogen-bonding networks still remains a challenging problem. In this paper, a newly-invented mathematical method called persistent homology is introduced, for the first time, to quantitatively analyze the intrinsic topological properties of ion aggregation systems and hydrogen-bonding networks. The two most distinguishable properties of persistent homology analysis of assembly systems are as follows. First, it does not require a predefined bond length to construct the ion or hydrogen-bonding network. Persistent homology results are determined by the morphological structure of the data only. Second, it can directly measure the size of circles or holes in ion aggregates and hydrogen-bonding networks. To validate our model, we consider two well-studied systems, i.e., NaCl and KSCN solutions, generated from molecular dynamics simulations. They are believed to represent two morphological types of aggregation, i.e., local clusters and extended ion networks. It has been found that the two aggregation types have distinguishable topological features and can be characterized by our topological model very well. Further, we construct two types of networks, i.e., O-networks and H2O-networks, for analyzing the topological properties of hydrogen-bonding networks. It is found that for both models, KSCN systems demonstrate much more dramatic variations in their local circle structures with a concentration increase. A consistent increase of large-sized local circle structures is observed and the sizes of these circles become more and more diverse. In contrast, NaCl systems show no obvious increase of large-sized circles. Instead a consistent decline of the average size of the circle structures is observed and the sizes of these circles become more and more uniform with a concentration increase. As far as we know, these unique intrinsic topological features in ion aggregation systems have never been pointed out before. More importantly, our models can be directly used to quantitatively analyze the intrinsic topological invariants, including circles, loops, holes, and cavities, of any network-like structures, such as nanomaterials, colloidal systems, biomolecular assemblies, among others. These topological invariants cannot be described by traditional graph and network models.
Collapse
Affiliation(s)
- Kelin Xia
- Division of Mathematical Sciences, School of Physical and Mathematical Sciences, School of Biological Sciences, Nanyang Technological University, 637371, Singapore.
| |
Collapse
|
25
|
Cang Z, Mu L, Wei GW. Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol 2018; 14:e1005929. [PMID: 29309403 PMCID: PMC5774846 DOI: 10.1371/journal.pcbi.1005929] [Citation(s) in RCA: 144] [Impact Index Per Article: 24.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2017] [Revised: 01/19/2018] [Accepted: 12/15/2017] [Indexed: 12/05/2022] Open
Abstract
This work introduces a number of algebraic topology approaches, including multi-component persistent homology, multi-level persistent homology, and electrostatic persistence for the representation, characterization, and description of small molecules and biomolecular complexes. In contrast to the conventional persistent homology, multi-component persistent homology retains critical chemical and biological information during the topological simplification of biomolecular geometric complexity. Multi-level persistent homology enables a tailored topological description of inter- and/or intra-molecular interactions of interest. Electrostatic persistence incorporates partial charge information into topological invariants. These topological methods are paired with Wasserstein distance to characterize similarities between molecules and are further integrated with a variety of machine learning algorithms, including k-nearest neighbors, ensemble of trees, and deep convolutional neural networks, to manifest their descriptive and predictive powers for protein-ligand binding analysis and virtual screening of small molecules. Extensive numerical experiments involving 4,414 protein-ligand complexes from the PDBBind database and 128,374 ligand-target and decoy-target pairs in the DUD database are performed to test respectively the scoring power and the discriminatory power of the proposed topological learning strategies. It is demonstrated that the present topological learning outperforms other existing methods in protein-ligand binding affinity prediction and ligand-decoy discrimination.
Collapse
Affiliation(s)
- Zixuan Cang
- Department of Mathematics, Michigan State University, East Lansing, Michigan, United States of America
| | - Lin Mu
- Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, United States of America
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, East Lansing, Michigan, United States of America
- Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan, United States of America
- Department of Electrical and Computer Engineering, Michigan State University, East Lansing, Michigan, United States of America
| |
Collapse
|
26
|
Multiscale Persistent Functions for Biomolecular Structure Characterization. Bull Math Biol 2017; 80:1-31. [PMID: 29098540 DOI: 10.1007/s11538-017-0362-6] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2016] [Accepted: 10/19/2017] [Indexed: 10/18/2022]
Abstract
In this paper, we introduce multiscale persistent functions for biomolecular structure characterization. The essential idea is to combine our multiscale rigidity functions (MRFs) with persistent homology analysis, so as to construct a series of multiscale persistent functions, particularly multiscale persistent entropies, for structure characterization. To clarify the fundamental idea of our method, the multiscale persistent entropy (MPE) model is discussed in great detail. Mathematically, unlike the previous persistent entropy (Chintakunta et al. in Pattern Recognit 48(2):391-401, 2015; Merelli et al. in Entropy 17(10):6872-6892, 2015; Rucco et al. in: Proceedings of ECCS 2014, Springer, pp 117-128, 2016), a special resolution parameter is incorporated into our model. Various scales can be achieved by tuning its value. Physically, our MPE can be used in conformational entropy evaluation. More specifically, it is found that our method incorporates in it a natural classification scheme. This is achieved through a density filtration of an MRF built from angular distributions. To further validate our model, a systematical comparison with the traditional entropy evaluation model is done. It is found that our model is able to preserve the intrinsic topological features of biomolecular data much better than traditional approaches, particularly for resolutions in the intermediate range. Moreover, by comparing with traditional entropies from various grid sizes, bond angle-based methods and a persistent homology-based support vector machine method (Cang et al. in Mol Based Math Biol 3:140-162, 2015), we find that our MPE method gives the best results in terms of average true positive rate in a classic protein structure classification test. More interestingly, all-alpha and all-beta protein classes can be clearly separated from each other with zero error only in our model. Finally, a special protein structure index (PSI) is proposed, for the first time, to describe the "regularity" of protein structures. Basically, a protein structure is deemed as regular if it has a consistent and orderly configuration. Our PSI model is tested on a database of 110 proteins; we find that structures with larger portions of loops and intrinsically disorder regions are always associated with larger PSI, meaning an irregular configuration, while proteins with larger portions of secondary structures, i.e., alpha-helix or beta-sheet, have smaller PSI. Essentially, PSI can be used to describe the "regularity" information in any systems.
Collapse
|
27
|
Yoo K, Lee P, Chung MK, Sohn WS, Chung SJ, Na DL, Ju D, Jeong Y. Degree-based statistic and center persistency for brain connectivity analysis. Hum Brain Mapp 2017; 38:165-181. [PMID: 27593391 PMCID: PMC6866961 DOI: 10.1002/hbm.23352] [Citation(s) in RCA: 32] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2015] [Revised: 05/18/2016] [Accepted: 08/08/2016] [Indexed: 12/16/2022] Open
Abstract
Brain connectivity analyses have been widely performed to investigate the organization and functioning of the brain, or to observe changes in neurological or psychiatric conditions. However, connectivity analysis inevitably introduces the problem of mass-univariate hypothesis testing. Although, several cluster-wise correction methods have been suggested to address this problem and shown to provide high sensitivity, these approaches fundamentally have two drawbacks: the lack of spatial specificity (localization power) and the arbitrariness of an initial cluster-forming threshold. In this study, we propose a novel method, degree-based statistic (DBS), performing cluster-wise inference. DBS is designed to overcome the above-mentioned two shortcomings. From a network perspective, a few brain regions are of critical importance and considered to play pivotal roles in network integration. Regarding this notion, DBS defines a cluster as a set of edges of which one ending node is shared. This definition enables the efficient detection of clusters and their center nodes. Furthermore, a new measure of a cluster, center persistency (CP) was introduced. The efficiency of DBS with a known "ground truth" simulation was demonstrated. Then they applied DBS to two experimental datasets and showed that DBS successfully detects the persistent clusters. In conclusion, by adopting a graph theoretical concept of degrees and borrowing the concept of persistence from algebraic topology, DBS could sensitively identify clusters with centric nodes that would play pivotal roles in an effect of interest. DBS is potentially widely applicable to variable cognitive or clinical situations and allows us to obtain statistically reliable and easily interpretable results. Hum Brain Mapp 38:165-181, 2017. © 2016 Wiley Periodicals, Inc.
Collapse
Affiliation(s)
- Kwangsun Yoo
- Department of Bio and Brain EngineeringKorea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
- KI for Health Science and Technology, Korea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
| | - Peter Lee
- Department of Bio and Brain EngineeringKorea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
- KI for Health Science and Technology, Korea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
| | - Moo K. Chung
- Department of Biostatistics and Medical Informatics and Waisman Laboratory for Brain Imaging and BehaviorUniversity of WisconsinMadisonWisconsin 53706
| | - William S. Sohn
- Department of Bio and Brain EngineeringKorea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
- Present address:
William S. Sohn is currently at Institute of Human Behavioral Medicine, Medical Research CenterSeoul National University
| | - Sun Ju Chung
- Department of NeurologyAsan Medical Center, University of Ulsan College of MedicineSeoulRepublic of Korea
| | - Duk L. Na
- Department of NeurologySamsung Medical Center, Sungkyunkwan University, School of MedicineSeoulRepublic of Korea
- Neuroscience Center, Samsung Medical Center, Sungkyunkwan University, School of MedicineSeoulRepublic of Korea
| | - Daheen Ju
- Department of Bio and Brain EngineeringKorea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
| | - Yong Jeong
- Department of Bio and Brain EngineeringKorea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
- KI for Health Science and Technology, Korea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
| |
Collapse
|
28
|
Abstract
Persistent homology provides a new approach for the topological simplification of big data via measuring the life time of intrinsic topological features in a filtration process and has found its success in scientific and engineering applications. However, such a success is essentially limited to qualitative data classification and analysis. Indeed, persistent homology has rarely been employed for quantitative modeling and prediction. Additionally, the present persistent homology is a passive tool, rather than a proactive technique, for classification and analysis. In this work, we outline a general protocol to construct object-oriented persistent homology methods. By means of differential geometry theory of surfaces, we construct an objective functional, namely, a surface free energy defined on the data of interest. The minimization of the objective functional leads to a Laplace-Beltrami operator which generates a multiscale representation of the initial data and offers an objective oriented filtration process. The resulting differential geometry based object-oriented persistent homology is able to preserve desirable geometric features in the evolutionary filtration and enhances the corresponding topological persistence. The cubical complex based homology algorithm is employed in the present work to be compatible with the Cartesian representation of the Laplace-Beltrami flow. The proposed Laplace-Beltrami flow based persistent homology method is extensively validated. The consistence between Laplace-Beltrami flow based filtration and Euclidean distance based filtration is confirmed on the Vietoris-Rips complex for a large amount of numerical tests. The convergence and reliability of the present Laplace-Beltrami flow based cubical complex filtration approach are analyzed over various spatial and temporal mesh sizes. The Laplace-Beltrami flow based persistent homology approach is utilized to study the intrinsic topology of proteins and fullerene molecules. Based on a quantitative model which correlates the topological persistence of fullerene central cavity with the total curvature energy of the fullerene structure, the proposed method is used for the prediction of fullerene isomer stability. The efficiency and robustness of the present method are verified by more than 500 fullerene molecules. It is shown that the proposed persistent homology based quantitative model offers good predictions of total curvature energies for ten types of fullerene isomers. The present work offers the first example to design object-oriented persistent homology to enhance or preserve desirable features in the original data during the filtration process and then automatically detect or extract the corresponding topological traits from the data.
Collapse
Affiliation(s)
- Bao Wang
- Department of Mathematics Michigan State University, MI 48824, USA
| | - Guo-Wei Wei
- Mathematical Biosciences Institute, The Ohio State University, Columbus, Ohio 43210, USA
| |
Collapse
|
29
|
Xia K, Zhao Z, Wei GW. Multiresolution persistent homology for excessively large biomolecular datasets. J Chem Phys 2015; 143:134103. [PMID: 26450288 PMCID: PMC4592433 DOI: 10.1063/1.4931733] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2015] [Accepted: 09/08/2015] [Indexed: 12/21/2022] Open
Abstract
Although persistent homology has emerged as a promising tool for the topological simplification of complex data, it is computationally intractable for large datasets. We introduce multiresolution persistent homology to handle excessively large datasets. We match the resolution with the scale of interest so as to represent large scale datasets with appropriate resolution. We utilize flexibility-rigidity index to access the topological connectivity of the data set and define a rigidity density for the filtration analysis. By appropriately tuning the resolution of the rigidity density, we are able to focus the topological lens on the scale of interest. The proposed multiresolution topological analysis is validated by a hexagonal fractal image which has three distinct scales. We further demonstrate the proposed method for extracting topological fingerprints from DNA molecules. In particular, the topological persistence of a virus capsid with 273 780 atoms is successfully analyzed which would otherwise be inaccessible to the normal point cloud method and unreliable by using coarse-grained multiscale persistent homology. The proposed method has also been successfully applied to the protein domain classification, which is the first time that persistent homology is used for practical protein domain analysis, to our knowledge. The proposed multiresolution topological method has potential applications in arbitrary data sets, such as social networks, biological networks, and graphs.
Collapse
Affiliation(s)
- Kelin Xia
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, USA
| | - Zhixiong Zhao
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, USA
| |
Collapse
|
30
|
Xia K, Wei GW. Persistent topology for cryo-EM data analysis. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2015; 31:n/a-n/a. [PMID: 25851063 DOI: 10.1002/cnm.2719] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/23/2014] [Revised: 03/13/2015] [Accepted: 03/31/2015] [Indexed: 06/04/2023]
Abstract
In this work, we introduce persistent homology for the analysis of cryo-electron microscopy (cryo-EM) density maps. We identify the topological fingerprint or topological signature of noise, which is widespread in cryo-EM data. For low signal-to-noise ratio (SNR) volumetric data, intrinsic topological features of biomolecular structures are indistinguishable from noise. To remove noise, we employ geometric flows that are found to preserve the intrinsic topological fingerprints of cryo-EM structures and diminish the topological signature of noise. In particular, persistent homology enables us to visualize the gradual separation of the topological fingerprints of cryo-EM structures from those of noise during the denoising process, which gives rise to a practical procedure for prescribing a noise threshold to extract cryo-EM structure information from noise contaminated data after certain iterations of the geometric flow equation. To further demonstrate the utility of persistent homology for cryo-EM data analysis, we consider a microtubule intermediate structure Electron Microscopy Data (EMD 1129). Three helix models, an alpha-tubulin monomer model, an alpha-tubulin and beta-tubulin model, and an alpha-tubulin and beta-tubulin dimer model, are constructed to fit the cryo-EM data. The least square fitting leads to similarly high correlation coefficients, which indicates that structure determination via optimization is an ill-posed inverse problem. However, these models have dramatically different topological fingerprints. Especially, linkages or connectivities that discriminate one model from another, play little role in the traditional density fitting or optimization but are very sensitive and crucial to topological fingerprints. The intrinsic topological features of the microtubule data are identified after topological denoising. By a comparison of the topological fingerprints of the original data and those of three models, we found that the third model is topologically favored. The present work offers persistent homology based new strategies for topological denoising and for resolving ill-posed inverse problems.
Collapse
Affiliation(s)
- Kelin Xia
- Department of Mathematics, Michigan State University, MI 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, MI 48824, USA
- Department of Electrical and Computer Engineering, Michigan State University, MI 48824, USA
- Department of Biochemistry and Molecular Biology, Michigan State University, MI 48824, USA
| |
Collapse
|
31
|
Xia K, Wei GW. Multidimensional persistence in biomolecular data. J Comput Chem 2015; 36:1502-20. [PMID: 26032339 PMCID: PMC4485576 DOI: 10.1002/jcc.23953] [Citation(s) in RCA: 38] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2014] [Revised: 04/02/2015] [Accepted: 04/19/2015] [Indexed: 12/24/2022]
Abstract
Persistent homology has emerged as a popular technique for the topological simplification of big data, including biomolecular data. Multidimensional persistence bears considerable promise to bridge the gap between geometry and topology. However, its practical and robust construction has been a challenge. We introduce two families of multidimensional persistence, namely pseudomultidimensional persistence and multiscale multidimensional persistence. The former is generated via the repeated applications of persistent homology filtration to high-dimensional data, such as results from molecular dynamics or partial differential equations. The latter is constructed via isotropic and anisotropic scales that create new simiplicial complexes and associated topological spaces. The utility, robustness, and efficiency of the proposed topological methods are demonstrated via protein folding, protein flexibility analysis, the topological denoising of cryoelectron microscopy data, and the scale dependence of nanoparticles. Topological transition between partial folded and unfolded proteins has been observed in multidimensional persistence. The separation between noise topological signatures and molecular topological fingerprints is achieved by the Laplace-Beltrami flow. The multiscale multidimensional persistent homology reveals relative local features in Betti-0 invariants and the relatively global characteristics of Betti-1 and Betti-2 invariants.
Collapse
Affiliation(s)
- Kelin Xia
- Department of Mathematics, Michigan State University, MI 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, MI 48824, USA
- Department of Electrical and Computer Engineering, Michigan State University, MI 48824, USA
- Department of Biochemistry and Molecular Biology, Michigan State University, MI 48824, USA
| |
Collapse
|
32
|
Lorenzi M, Ayache N, Pennec X. Regional flux analysis for discovering and quantifying anatomical changes: An application to the brain morphometry in Alzheimer's disease. Neuroimage 2015; 115:224-34. [PMID: 25963734 PMCID: PMC6343474 DOI: 10.1016/j.neuroimage.2015.04.051] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2014] [Revised: 04/01/2015] [Accepted: 04/25/2015] [Indexed: 11/26/2022] Open
Abstract
In this study we introduce the regional flux analysis, a novel approach to deformation based morphometry based on the Helmholtz decomposition of deformations parameterized by stationary velocity fields. We use the scalar pressure map associated to the irrotational component of the deformation to discover the critical regions of volume change. These regions are used to consistently quantify the associated measure of volume change by the probabilistic integration of the flux of the longitudinal deformations across the boundaries. The presented framework unifies voxel-based and regional approaches, and robustly describes the volume changes at both group-wise and subject-specific level as a spatial process governed by consistently defined regions. Our experiments on the large cohorts of the ADNI dataset show that the regional flux analysis is a powerful and flexible instrument for the study of Alzheimer's disease in a wide range of scenarios: cross-sectional deformation based morphometry, longitudinal discovery and quantification of group-wise volume changes, and statistically powered and robust quantification of hippocampal and ventricular atrophy.
Collapse
Affiliation(s)
- M Lorenzi
- Asclepios Research Project, INRIA Sophia Antipolis, 2004 route des Lucioles BP 93, 06 902 Sophia Antipolis, France.
| | - N Ayache
- Asclepios Research Project, INRIA Sophia Antipolis, 2004 route des Lucioles BP 93, 06 902 Sophia Antipolis, France.
| | - X Pennec
- Asclepios Research Project, INRIA Sophia Antipolis, 2004 route des Lucioles BP 93, 06 902 Sophia Antipolis, France.
| |
Collapse
|
33
|
Weiner MW, Veitch DP, Aisen PS, Beckett LA, Cairns NJ, Cedarbaum J, Green RC, Harvey D, Jack CR, Jagust W, Luthman J, Morris JC, Petersen RC, Saykin AJ, Shaw L, Shen L, Schwarz A, Toga AW, Trojanowski JQ. 2014 Update of the Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inception. Alzheimers Dement 2015; 11:e1-120. [PMID: 26073027 PMCID: PMC5469297 DOI: 10.1016/j.jalz.2014.11.001] [Citation(s) in RCA: 210] [Impact Index Per Article: 23.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Revised: 04/18/2013] [Indexed: 01/18/2023]
Abstract
The Alzheimer's Disease Neuroimaging Initiative (ADNI) is an ongoing, longitudinal, multicenter study designed to develop clinical, imaging, genetic, and biochemical biomarkers for the early detection and tracking of Alzheimer's disease (AD). The initial study, ADNI-1, enrolled 400 subjects with early mild cognitive impairment (MCI), 200 with early AD, and 200 cognitively normal elderly controls. ADNI-1 was extended by a 2-year Grand Opportunities grant in 2009 and by a competitive renewal, ADNI-2, which enrolled an additional 550 participants and will run until 2015. This article reviews all papers published since the inception of the initiative and summarizes the results to the end of 2013. The major accomplishments of ADNI have been as follows: (1) the development of standardized methods for clinical tests, magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF) biomarkers in a multicenter setting; (2) elucidation of the patterns and rates of change of imaging and CSF biomarker measurements in control subjects, MCI patients, and AD patients. CSF biomarkers are largely consistent with disease trajectories predicted by β-amyloid cascade (Hardy, J Alzheimer's Dis 2006;9(Suppl 3):151-3) and tau-mediated neurodegeneration hypotheses for AD, whereas brain atrophy and hypometabolism levels show predicted patterns but exhibit differing rates of change depending on region and disease severity; (3) the assessment of alternative methods of diagnostic categorization. Currently, the best classifiers select and combine optimum features from multiple modalities, including MRI, [(18)F]-fluorodeoxyglucose-PET, amyloid PET, CSF biomarkers, and clinical tests; (4) the development of blood biomarkers for AD as potentially noninvasive and low-cost alternatives to CSF biomarkers for AD diagnosis and the assessment of α-syn as an additional biomarker; (5) the development of methods for the early detection of AD. CSF biomarkers, β-amyloid 42 and tau, as well as amyloid PET may reflect the earliest steps in AD pathology in mildly symptomatic or even nonsymptomatic subjects and are leading candidates for the detection of AD in its preclinical stages; (6) the improvement of clinical trial efficiency through the identification of subjects most likely to undergo imminent future clinical decline and the use of more sensitive outcome measures to reduce sample sizes. Multimodal methods incorporating APOE status and longitudinal MRI proved most highly predictive of future decline. Refinements of clinical tests used as outcome measures such as clinical dementia rating-sum of boxes further reduced sample sizes; (7) the pioneering of genome-wide association studies that leverage quantitative imaging and biomarker phenotypes, including longitudinal data, to confirm recently identified loci, CR1, CLU, and PICALM and to identify novel AD risk loci; (8) worldwide impact through the establishment of ADNI-like programs in Japan, Australia, Argentina, Taiwan, China, Korea, Europe, and Italy; (9) understanding the biology and pathobiology of normal aging, MCI, and AD through integration of ADNI biomarker and clinical data to stimulate research that will resolve controversies about competing hypotheses on the etiopathogenesis of AD, thereby advancing efforts to find disease-modifying drugs for AD; and (10) the establishment of infrastructure to allow sharing of all raw and processed data without embargo to interested scientific investigators throughout the world.
Collapse
Affiliation(s)
- Michael W Weiner
- Department of Veterans Affairs Medical Center, Center for Imaging of Neurodegenerative Diseases, San Francisco, CA, USA; Department of Radiology, University of California, San Francisco, CA, USA; Department of Medicine, University of California, San Francisco, CA, USA; Department of Psychiatry, University of California, San Francisco, CA, USA; Department of Neurology, University of California, San Francisco, CA, USA.
| | - Dallas P Veitch
- Department of Veterans Affairs Medical Center, Center for Imaging of Neurodegenerative Diseases, San Francisco, CA, USA
| | - Paul S Aisen
- Department of Neurosciences, University of California, San Diego, La Jolla, CA, USA
| | - Laurel A Beckett
- Division of Biostatistics, Department of Public Health Sciences, University of California, Davis, CA, USA
| | - Nigel J Cairns
- Knight Alzheimer's Disease Research Center, Washington University School of Medicine, Saint Louis, MO, USA; Department of Neurology, Washington University School of Medicine, Saint Louis, MO, USA
| | - Jesse Cedarbaum
- Neurology Early Clinical Development, Biogen Idec, Cambridge, MA, USA
| | - Robert C Green
- Division of Genetics, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA
| | - Danielle Harvey
- Division of Biostatistics, Department of Public Health Sciences, University of California, Davis, CA, USA
| | | | - William Jagust
- Helen Wills Neuroscience Institute, University of California Berkeley, Berkeley, CA, USA
| | - Johan Luthman
- Neuroscience Clinical Development, Neuroscience & General Medicine Product Creation Unit, Eisai Inc., Philadelphia, PA, USA
| | - John C Morris
- Department of Neurosciences, University of California, San Diego, La Jolla, CA, USA
| | | | - Andrew J Saykin
- Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN, USA; Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Leslie Shaw
- Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Li Shen
- Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Adam Schwarz
- Tailored Therapeutics, Eli Lilly and Company, Indianapolis, IN, USA
| | - Arthur W Toga
- Laboratory of Neuroimaging, Institute of Neuroimaging and Informatics, Keck School of Medicine of University of Southern California, Los Angeles, CA, USA
| | - John Q Trojanowski
- Institute on Aging, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA; Alzheimer's Disease Core Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA; Udall Parkinson's Research Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA; Department of Pathology and Laboratory Medicine, Center for Neurodegenerative Research, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| |
Collapse
|
34
|
Xia K, Feng X, Tong Y, Wei GW. Persistent homology for the quantitative prediction of fullerene stability. J Comput Chem 2014; 36:408-22. [PMID: 25523342 DOI: 10.1002/jcc.23816] [Citation(s) in RCA: 54] [Impact Index Per Article: 5.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2014] [Revised: 10/25/2014] [Accepted: 11/23/2014] [Indexed: 11/08/2022]
Abstract
Persistent homology is a relatively new tool often used for qualitative analysis of intrinsic topological features in images and data originated from scientific and engineering applications. In this article, we report novel quantitative predictions of the energy and stability of fullerene molecules, the very first attempt in using persistent homology in this context. The ground-state structures of a series of small fullerene molecules are first investigated with the standard Vietoris-Rips complex. We decipher all the barcodes, including both short-lived local bars and long-lived global bars arising from topological invariants, and associate them with fullerene structural details. Using accumulated bar lengths, we build quantitative models to correlate local and global Betti-2 bars, respectively with the heat of formation and total curvature energies of fullerenes. It is found that the heat of formation energy is related to the local hexagonal cavities of small fullerenes, while the total curvature energies of fullerene isomers are associated with their sphericities, which are measured by the lengths of their long-lived Betti-2 bars. Excellent correlation coefficients (>0.94) between persistent homology predictions and those of quantum or curvature analysis have been observed. A correlation matrix based filtration is introduced to further verify our findings.
Collapse
Affiliation(s)
- Kelin Xia
- Department of Mathematics, Michigan State University, Michigan, 48824
| | | | | | | |
Collapse
|
35
|
Xia K, Wei GW. Persistent homology analysis of protein structure, flexibility, and folding. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2014; 30:814-44. [PMID: 24902720 PMCID: PMC4131872 DOI: 10.1002/cnm.2655] [Citation(s) in RCA: 114] [Impact Index Per Article: 11.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/04/2014] [Revised: 05/19/2014] [Accepted: 05/21/2014] [Indexed: 05/04/2023]
Abstract
Proteins are the most important biomolecules for living organisms. The understanding of protein structure, function, dynamics, and transport is one of the most challenging tasks in biological science. In the present work, persistent homology is, for the first time, introduced for extracting molecular topological fingerprints (MTFs) based on the persistence of molecular topological invariants. MTFs are utilized for protein characterization, identification, and classification. The method of slicing is proposed to track the geometric origin of protein topological invariants. Both all-atom and coarse-grained representations of MTFs are constructed. A new cutoff-like filtration is proposed to shed light on the optimal cutoff distance in elastic network models. On the basis of the correlation between protein compactness, rigidity, and connectivity, we propose an accumulated bar length generated from persistent topological invariants for the quantitative modeling of protein flexibility. To this end, a correlation matrix-based filtration is developed. This approach gives rise to an accurate prediction of the optimal characteristic distance used in protein B-factor analysis. Finally, MTFs are employed to characterize protein topological evolution during protein folding and quantitatively predict the protein folding stability. An excellent consistence between our persistent homology prediction and molecular dynamics simulation is found. This work reveals the topology-function relationship of proteins.
Collapse
Affiliation(s)
- Kelin Xia
- Department of Mathematics, Michigan State University, MI 48824, USA
- Center for Mathematical Molecular Biosciences, Michigan State University, MI 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, MI 48824, USA
- Center for Mathematical Molecular Biosciences, Michigan State University, MI 48824, USA
- Department of Electrical and Computer Engineering, Michigan State University, MI 48824, USA
- Department of Biochemistry and Molecular Biology, Michigan State University, MI 48824, USA
| |
Collapse
|
36
|
Kim WH, Singh V, Chung MK, Hinrichs C, Pachauri D, Okonkwo OC, Johnson SC. Multi-resolutional shape features via non-Euclidean wavelets: applications to statistical analysis of cortical thickness. Neuroimage 2014; 93 Pt 1:107-23. [PMID: 24614060 DOI: 10.1016/j.neuroimage.2014.02.028] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2013] [Revised: 01/16/2014] [Accepted: 02/24/2014] [Indexed: 01/18/2023] Open
Abstract
Statistical analysis on arbitrary surface meshes such as the cortical surface is an important approach to understanding brain diseases such as Alzheimer's disease (AD). Surface analysis may be able to identify specific cortical patterns that relate to certain disease characteristics or exhibit differences between groups. Our goal in this paper is to make group analysis of signals on surfaces more sensitive. To do this, we derive multi-scale shape descriptors that characterize the signal around each mesh vertex, i.e., its local context, at varying levels of resolution. In order to define such a shape descriptor, we make use of recent results from harmonic analysis that extend traditional continuous wavelet theory from the Euclidean to a non-Euclidean setting (i.e., a graph, mesh or network). Using this descriptor, we conduct experiments on two different datasets, the Alzheimer's Disease NeuroImaging Initiative (ADNI) data and images acquired at the Wisconsin Alzheimer's Disease Research Center (W-ADRC), focusing on individuals labeled as having Alzheimer's disease (AD), mild cognitive impairment (MCI) and healthy controls. In particular, we contrast traditional univariate methods with our multi-resolution approach which show increased sensitivity and improved statistical power to detect a group-level effects. We also provide an open source implementation.
Collapse
Affiliation(s)
- Won Hwa Kim
- Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI 53706, USA; Geriatric Research Education and Clinical Center, William S. Middleton Memorial Veteran's Hospital, Madison, WI 53705, USA.
| | - Vikas Singh
- Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI 53706, USA; Department of Biostatistics & Med. Informatics, University of Wisconsin-Madison, Madison, WI 53705, USA; Geriatric Research Education and Clinical Center, William S. Middleton Memorial Veteran's Hospital, Madison, WI 53705, USA.
| | - Moo K Chung
- Department of Biostatistics & Med. Informatics, University of Wisconsin-Madison, Madison, WI 53705, USA
| | - Chris Hinrichs
- Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI 53706, USA
| | - Deepti Pachauri
- Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI 53706, USA
| | - Ozioma C Okonkwo
- Geriatric Research Education and Clinical Center, William S. Middleton Memorial Veteran's Hospital, Madison, WI 53705, USA; Wisconsin Alzheimer's Disease Research Center, University of Wisconsin School of Medicine and Public Health, Madison, WI 53792, USA
| | - Sterling C Johnson
- Geriatric Research Education and Clinical Center, William S. Middleton Memorial Veteran's Hospital, Madison, WI 53705, USA; Wisconsin Alzheimer's Disease Research Center, University of Wisconsin School of Medicine and Public Health, Madison, WI 53792, USA
| | | |
Collapse
|
37
|
Jie B, Zhang D, Gao W, Wang Q, Wee CY, Shen D. Integration of network topological and connectivity properties for neuroimaging classification. IEEE Trans Biomed Eng 2014; 61:576-89. [PMID: 24108708 PMCID: PMC4106141 DOI: 10.1109/tbme.2013.2284195] [Citation(s) in RCA: 84] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
Abstract
Rapid advances in neuroimaging techniques have provided an efficient and noninvasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer's disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HCs). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multikernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multikernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9%, which is 10.8% better than those by single network-property-based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1 year, and 2 years, also demonstrating very promising results.
Collapse
Affiliation(s)
- Biao Jie
- Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China, and also with the School of Mathematics and Computer Science, Anhui Normal University, Wuhui, 241000, China
| | - Daoqiang Zhang
- Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
| | - Wei Gao
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA
| | - Qian Wang
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA
| | - Chong-Yaw Wee
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA
| | - Dinggang Shen
- Department of Radiology and BRIC, the University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA, and also with the Department of Brain and Cognitive Engineering, Korea University, Seoul 136-701, Korea
| |
Collapse
|
38
|
Sparks R, Madabhushi A. Explicit shape descriptors: novel morphologic features for histopathology classification. Med Image Anal 2013; 17:997-1009. [PMID: 23850744 PMCID: PMC3811112 DOI: 10.1016/j.media.2013.06.002] [Citation(s) in RCA: 35] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2011] [Revised: 05/31/2013] [Accepted: 06/03/2013] [Indexed: 11/25/2022]
Abstract
Object morphology, defined as shape and size characteristics, observed on medical imagery is often an important marker for disease presence and/or aggressiveness. In the context of prostate cancer histopathology, gland morphology is an integral component of the Gleason grading system which enables discrimination between low and high grade disease. However, clinicians are often unable to distinguish between subtle differences in object morphology, as evidenced by high inter-observer variability in Gleason grading. Boundary-based morphologic descriptors, such as the variance in the distance from points on the boundary of an object to its center, may not have the requisite discriminability to separate objects with subtle shape differences. In this paper, we present a set of novel explicit shape descriptors (ESDs) which are capable of distinguishing subtle shape differences between prostate glands of intermediate Gleason grades (grades 3 and 4) on prostate cancer histopathology. Calculation of ESDs involves: (1) representing object morphology using an explicit shape model (e.g. medial axis); (2) aligning the shape models via a non-rigid registration scheme with a diffeomorphic constraint and quantifying shape model dissimilarity; and (3) applying a non-linear dimensionality reduction scheme (e.g. Graph Embedding) to learn a low dimensional projection encoding the shape differences between objects. ESDs are hence the principal eigenvectors in the reduced embedding space. In this work we demonstrate that ESDs in conjunction with a Support Vector Machine classifier are able to correctly distinguish between 888 prostate glands corresponding to different Gleason grades (benign, grade 3, or grade 4) of prostate cancer from 58 needle biopsy specimens with a maximum accuracy of 0.89 and corresponding area under the receiver operating characteristic curve of 0.78.
Collapse
Affiliation(s)
- Rachel Sparks
- Rutgers University, Department of Biomedical Engineering, 599 Taylor Road, Piscataway, NJ, USA
| | - Anant Madabhushi
- Case Western Reserve University, Department of Biomedical Engineering, 10900 Euclid Ave, Cleveland, OH, USA
| |
Collapse
|
39
|
Weiner MW, Veitch DP, Aisen PS, Beckett LA, Cairns NJ, Green RC, Harvey D, Jack CR, Jagust W, Liu E, Morris JC, Petersen RC, Saykin AJ, Schmidt ME, Shaw L, Shen L, Siuciak JA, Soares H, Toga AW, Trojanowski JQ. The Alzheimer's Disease Neuroimaging Initiative: a review of papers published since its inception. Alzheimers Dement 2013; 9:e111-94. [PMID: 23932184 DOI: 10.1016/j.jalz.2013.05.1769] [Citation(s) in RCA: 317] [Impact Index Per Article: 28.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Revised: 04/18/2013] [Indexed: 01/19/2023]
Abstract
The Alzheimer's Disease Neuroimaging Initiative (ADNI) is an ongoing, longitudinal, multicenter study designed to develop clinical, imaging, genetic, and biochemical biomarkers for the early detection and tracking of Alzheimer's disease (AD). The study aimed to enroll 400 subjects with early mild cognitive impairment (MCI), 200 subjects with early AD, and 200 normal control subjects; $67 million funding was provided by both the public and private sectors, including the National Institute on Aging, 13 pharmaceutical companies, and 2 foundations that provided support through the Foundation for the National Institutes of Health. This article reviews all papers published since the inception of the initiative and summarizes the results as of February 2011. The major accomplishments of ADNI have been as follows: (1) the development of standardized methods for clinical tests, magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF) biomarkers in a multicenter setting; (2) elucidation of the patterns and rates of change of imaging and CSF biomarker measurements in control subjects, MCI patients, and AD patients. CSF biomarkers are consistent with disease trajectories predicted by β-amyloid cascade (Hardy, J Alzheimers Dis 2006;9(Suppl 3):151-3) and tau-mediated neurodegeneration hypotheses for AD, whereas brain atrophy and hypometabolism levels show predicted patterns but exhibit differing rates of change depending on region and disease severity; (3) the assessment of alternative methods of diagnostic categorization. Currently, the best classifiers combine optimum features from multiple modalities, including MRI, [(18)F]-fluorodeoxyglucose-PET, CSF biomarkers, and clinical tests; (4) the development of methods for the early detection of AD. CSF biomarkers, β-amyloid 42 and tau, as well as amyloid PET may reflect the earliest steps in AD pathology in mildly symptomatic or even nonsymptomatic subjects, and are leading candidates for the detection of AD in its preclinical stages; (5) the improvement of clinical trial efficiency through the identification of subjects most likely to undergo imminent future clinical decline and the use of more sensitive outcome measures to reduce sample sizes. Baseline cognitive and/or MRI measures generally predicted future decline better than other modalities, whereas MRI measures of change were shown to be the most efficient outcome measures; (6) the confirmation of the AD risk loci CLU, CR1, and PICALM and the identification of novel candidate risk loci; (7) worldwide impact through the establishment of ADNI-like programs in Europe, Asia, and Australia; (8) understanding the biology and pathobiology of normal aging, MCI, and AD through integration of ADNI biomarker data with clinical data from ADNI to stimulate research that will resolve controversies about competing hypotheses on the etiopathogenesis of AD, thereby advancing efforts to find disease-modifying drugs for AD; and (9) the establishment of infrastructure to allow sharing of all raw and processed data without embargo to interested scientific investigators throughout the world. The ADNI study was extended by a 2-year Grand Opportunities grant in 2009 and a renewal of ADNI (ADNI-2) in October 2010 through to 2016, with enrollment of an additional 550 participants.
Collapse
Affiliation(s)
- Michael W Weiner
- Department of Veterans Affairs Medical Center, Center for Imaging of Neurodegenerative Diseases, San Francisco, CA, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
40
|
Adluru N, Hanlon BM, Lutz A, Lainhart JE, Alexander AL, Davidson RJ. Penalized likelihood phenotyping: unifying voxelwise analyses and multi-voxel pattern analyses in neuroimaging: penalized likelihood phenotyping. Neuroinformatics 2013; 11:227-47. [PMID: 23397550 PMCID: PMC3624987 DOI: 10.1007/s12021-012-9175-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
Abstract
Neuroimage phenotyping for psychiatric and neurological disorders is performed using voxelwise analyses also known as voxel based analyses or morphometry (VBM). A typical voxelwise analysis treats measurements at each voxel (e.g., fractional anisotropy, gray matter probability) as outcome measures to study the effects of possible explanatory variables (e.g., age, group) in a linear regression setting. Furthermore, each voxel is treated independently until the stage of correction for multiple comparisons. Recently, multi-voxel pattern analyses (MVPA), such as classification, have arisen as an alternative to VBM. The main advantage of MVPA over VBM is that the former employ multivariate methods which can account for interactions among voxels in identifying significant patterns. They also provide ways for computer-aided diagnosis and prognosis at individual subject level. However, compared to VBM, the results of MVPA are often more difficult to interpret and prone to arbitrary conclusions. In this paper, first we use penalized likelihood modeling to provide a unified framework for understanding both VBM and MVPA. We then utilize statistical learning theory to provide practical methods for interpreting the results of MVPA beyond commonly used performance metrics, such as leave-one-out-cross validation accuracy and area under the receiver operating characteristic (ROC) curve. Additionally, we demonstrate that there are challenges in MVPA when trying to obtain image phenotyping information in the form of statistical parametric maps (SPMs), which are commonly obtained from VBM, and provide a bootstrap strategy as a potential solution for generating SPMs using MVPA. This technique also allows us to maximize the use of available training data. We illustrate the empirical performance of the proposed framework using two different neuroimaging studies that pose different levels of challenge for classification using MVPA.
Collapse
|
41
|
Kim WH, Adluru N, Chung MK, Charchut S, GadElkarim JJ, Altshuler L, Moody T, Kumar A, Singh V, Leow AD. Multi-resolutional brain network filtering and analysis via wavelets on non-Euclidean space. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2013; 16:643-51. [PMID: 24505816 DOI: 10.1007/978-3-642-40760-4_80] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Advances in resting state fMRI and diffusion weighted imaging (DWI) have led to much interest in studies that evaluate hypotheses focused on how brain connectivity networks show variations across clinically disparate groups. However, various sources of error (e.g., tractography errors, magnetic field distortion, and motion artifacts) leak into the data, and make downstream statistical analysis problematic. In small sample size studies, such noise have an unfortunate effect that the differential signal may not be identifiable and so the null hypothesis cannot be rejected. Traditionally, smoothing is often used to filter out noise. But the construction of convolving with a Gaussian kernel is not well understood on arbitrarily connected graphs. Furthermore, there are no direct analogues of scale-space theory for graphs--ones which allow to view the signal at multiple resolutions. We provide rigorous frameworks for performing 'multi-resolutional' analysis on brain connectivity graphs. These are based on the recent theory of non-Euclidean wavelets. We provide strong evidence, on brain connectivity data from a network analysis study (structural connectivity differences in adult euthymic bipolar subjects), that the proposed algorithm allows identifying statistically significant network variations, which are clinically meaningful, where classical statistical tests, if applied directly, fail.
Collapse
|
42
|
Lee H, Kang H, Chung MK, Kim BN, Lee DS. Persistent brain network homology from the perspective of dendrogram. IEEE TRANSACTIONS ON MEDICAL IMAGING 2012; 31:2267-2277. [PMID: 23008247 DOI: 10.1109/tmi.2012.2219590] [Citation(s) in RCA: 105] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/01/2023]
Abstract
The brain network is usually constructed by estimating the connectivity matrix and thresholding it at an arbitrary level. The problem with this standard method is that we do not have any generally accepted criteria for determining a proper threshold. Thus, we propose a novel multiscale framework that models all brain networks generated over every possible threshold. Our approach is based on persistent homology and its various representations such as the Rips filtration, barcodes, and dendrograms. This new persistent homological framework enables us to quantify various persistent topological features at different scales in a coherent manner. The barcode is used to quantify and visualize the evolutionary changes of topological features such as the Betti numbers over different scales. By incorporating additional geometric information to the barcode, we obtain a single linkage dendrogram that shows the overall evolution of the network. The difference between the two networks is then measured by the Gromov-Hausdorff distance over the dendrograms. As an illustration, we modeled and differentiated the FDG-PET based functional brain networks of 24 attention-deficit hyperactivity disorder children, 26 autism spectrum disorder children, and 11 pediatric control subjects.
Collapse
Affiliation(s)
- Hyekyoung Lee
- Department of Nuclear Medicine and Department of Brain and Cognitive Sciences, Seoul National University, Seoul 110-744, Korea.
| | | | | | | | | |
Collapse
|
43
|
Pachauri D, Collins M, Kondor R, Singh V. Incorporating Domain Knowledge in Matching Problems via Harmonic Analysis. PROCEEDINGS OF THE ... INTERNATIONAL CONFERENCE ON MACHINE LEARNING. INTERNATIONAL CONFERENCE ON MACHINE LEARNING 2012; 2012:1271-1278. [PMID: 25309968 PMCID: PMC4191746] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
Matching one set of objects to another is a ubiquitous task in machine learning and computer vision that often reduces to some form of the quadratic assignment problem (QAP). The QAP is known to be notoriously hard, both in theory and in practice. Here, we investigate if this difficulty can be mitigated when some additional piece of information is available: (a) that all QAP instances of interest come from the same application, and (b) the correct solution for a set of such QAP instances is given. We propose a new approach to accelerate the solution of QAPs based on learning parameters for a modified objective function from prior QAP instances. A key feature of our approach is that it takes advantage of the algebraic structure of permutations, in conjunction with special methods for optimizing functions over the symmetric group đť•Š n in Fourier space. Experiments show that in practical domains the new method can outperform existing approaches.
Collapse
Affiliation(s)
| | | | - Risi Kondor
- Dept. of Computer Science and Dept. of Statistics, University of Chicago
| | - Vikas Singh
- Dept. of Computer Sciences, University of Wisconsin Madison
- Dept. of Biostatistics & Med. Informatics, University of Wisconsin Madison
| |
Collapse
|
44
|
Kim WH, Pachauri D, Hatt C, Chung MK, Johnson SC, Singh V. Wavelet based multi-scale shape features on arbitrary surfaces for cortical thickness discrimination. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 2012; 2012:1241-1249. [PMID: 25284968 PMCID: PMC4182864] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
Hypothesis testing on signals defined on surfaces (such as the cortical surface) is a fundamental component of a variety of studies in Neuroscience. The goal here is to identify regions that exhibit changes as a function of the clinical condition under study. As the clinical questions of interest move towards identifying very early signs of diseases, the corresponding statistical differences at the group level invariably become weaker and increasingly hard to identify. Indeed, after a multiple comparisons correction is adopted (to account for correlated statistical tests over all surface points), very few regions may survive. In contrast to hypothesis tests on point-wise measurements, in this paper, we make the case for performing statistical analysis on multi-scale shape descriptors that characterize the local topological context of the signal around each surface vertex. Our descriptors are based on recent results from harmonic analysis, that show how wavelet theory extends to non-Euclidean settings (i.e., irregular weighted graphs). We provide strong evidence that these descriptors successfully pick up group-wise differences, where traditional methods either fail or yield unsatisfactory results. Other than this primary application, we show how the framework allows performing cortical surface smoothing in the native space without mappint to a unit sphere.
Collapse
Affiliation(s)
- Won Hwa Kim
- Dept. of Computer Sciences, University of Wisconsin, Madison, WI
- Wisconsin Alzheimer’s Disease Research Center, University of Wisconsin, Madison, WI
- GRECC, William S. Middleton VA Hospital, Madison, WI
| | - Deepti Pachauri
- Dept. of Computer Sciences, University of Wisconsin, Madison, WI
| | - Charles Hatt
- Dept. of Biomedical Engineering, University of Wisconsin, Madison, WI
| | - Moo K. Chung
- Dept. of Biostatistics & Med. Informatics, University of Wisconsin, Madison, WI
| | - Sterling C. Johnson
- Wisconsin Alzheimer’s Disease Research Center, University of Wisconsin, Madison, WI
- GRECC, William S. Middleton VA Hospital, Madison, WI
| | - Vikas Singh
- Dept. of Computer Sciences, University of Wisconsin, Madison, WI
- Dept. of Biostatistics & Med. Informatics, University of Wisconsin, Madison, WI
- Wisconsin Alzheimer’s Disease Research Center, University of Wisconsin, Madison, WI
- GRECC, William S. Middleton VA Hospital, Madison, WI
| |
Collapse
|