1
|
Li T, Xie Z, Qi W, Asma E, Qi J. Unsupervised deep learning framework for data-driven gating in positron emission tomography. Med Phys 2023; 50:6047-6059. [PMID: 37538038 PMCID: PMC10592231 DOI: 10.1002/mp.16642] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Revised: 07/03/2023] [Accepted: 07/03/2023] [Indexed: 08/05/2023] Open
Abstract
BACKGROUND Physiological motion, such as respiratory motion, has become a limiting factor in the spatial resolution of positron emission tomography (PET) imaging as the resolution of PET detectors continue to improve. Motion-induced misregistration between PET and CT images can also cause attenuation correction artifacts. Respiratory gating can be used to freeze the motion and to reduce motion induced artifacts. PURPOSE In this study, we propose a robust data-driven approach using an unsupervised deep clustering network that employs an autoencoder (AE) to extract latent features for respiratory gating. METHODS We first divide list-mode PET data into short-time frames. The short-time frame images are reconstructed without attenuation, scatter, or randoms correction to avoid attenuation mismatch artifacts and to reduce image reconstruction time. The deep AE is then trained using reconstructed short-time frame images to extract latent features for respiratory gating. No additional data are required for the AE training. K-means clustering is subsequently used to perform respiratory gating based on the latent features extracted by the deep AE. The effectiveness of our proposed Deep Clustering method was evaluated using physical phantom and real patient datasets. The performance was compared against phase gating based on an external signal (External) and image based principal component analysis (PCA) with K-means clustering (Image PCA). RESULTS The proposed method produced gated images with higher contrast and sharper myocardium boundaries than those obtained using the External gating method and Image PCA. Quantitatively, the gated images generated by the proposed Deep Clustering method showed larger center of mass (COM) displacement and higher lesion contrast than those obtained using the other two methods. CONCLUSIONS The effectiveness of our proposed method was validated using physical phantom and real patient data. The results showed our proposed framework could provide superior gating than the conventional External method and Image PCA.
Collapse
Affiliation(s)
- Tiantian Li
- Department of Biomedical Engineering, University of California - Davis, Davis, CA 95616, USA
| | - Zhaoheng Xie
- Department of Biomedical Engineering, University of California - Davis, Davis, CA 95616, USA
| | - Wenyuan Qi
- Canon Medical Research USA, Inc., Vernon Hills, IL 60061, USA
| | - Evren Asma
- Canon Medical Research USA, Inc., Vernon Hills, IL 60061, USA
| | - Jinyi Qi
- Department of Biomedical Engineering, University of California - Davis, Davis, CA 95616, USA
| |
Collapse
|
2
|
Feng A, Feng Y, Zhi D, Jiang R, Fu Z, Xu M, Zhao M, Yu S, Stevens M, Sun L, Calhoun V, Sui J. Functional Imaging Derived ADHD Biotypes Based on Deep Clustering May Guide Personalized Medication Therapy. Res Sq 2023:rs.3.rs-3272441. [PMID: 37790426 PMCID: PMC10543279 DOI: 10.21203/rs.3.rs-3272441/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/05/2023]
Abstract
Attention deficit hyperactivity disorder (ADHD) is one prevalent neurodevelopmental disorder with childhood onset, however, there is no clear correspondence established between clinical ADHD subtypes and primary medications. Identifying objective and reliable neuroimaging markers for categorizing ADHD biotypes may lead to more individualized, biotype-guided treatment. Here we proposed graph convolutional network plus deep clustering for ADHD biotype detection using functional network connectivity (FNC), resulting in two biotypes based on 1069 ADHD patients selected from Adolescent Brain and Cognitive Development (ABCD) study, which were well replicated on independent ADHD adolescents undergoing longitudinal medication treatment (n=130). Interestingly, in addition to differences in cognitive performance and hyperactivity/impulsivity symptoms, biotype 1 treated with methylphenidate demonstrated significantly better recovery than biotype 2 treated with atomoxetine (p<0.05, FDR corrected). This imaging-driven, biotype-guided approach holds promise for facilitating personalized treatment of ADHD, exploring possible boundaries through innovative deep learning algorithms aimed at improving medication treatment effectiveness.
Collapse
Affiliation(s)
- Aichen Feng
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China, 100190
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, 100049
| | - Yuan Feng
- Peking University Sixth Hospital/Institute of Mental Health, National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing, China, 100191
| | - Dongmei Zhi
- State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China, 100875
| | - Rongtao Jiang
- Department of Radiology and Biomedical imaging, Yale University, New Haven, Connecticut, USA
| | - Zening Fu
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia Institute of Technology, Emory University and Georgia State University, Atlanta, Georgia, United States, 30303
| | - Ming Xu
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China, 100190
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, 100049
| | - Min Zhao
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China, 100190
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, 100049
| | - Shan Yu
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China, 100190
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, 100049
| | - Michael Stevens
- Department of Psychiatry, Olin Neuropsychiatry Research Center, Institute of Living, Hartford Healthcare Corporation, Hartford, CT, United States
- Department of Psychiatry, Yale University School of Medicine, New Haven, CT, United States
| | - Li Sun
- Peking University Sixth Hospital/Institute of Mental Health, National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing, China, 100191
| | - Vince Calhoun
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia Institute of Technology, Emory University and Georgia State University, Atlanta, Georgia, United States, 30303
| | - Jing Sui
- State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China, 100875
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia Institute of Technology, Emory University and Georgia State University, Atlanta, Georgia, United States, 30303
| |
Collapse
|
3
|
Gan Y, Chen Y, Xu G, Guo W, Zou G. Deep enhanced constraint clustering based on contrastive learning for scRNA-seq data. Brief Bioinform 2023:bbad222. [PMID: 37313714 DOI: 10.1093/bib/bbad222] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 05/03/2023] [Accepted: 05/23/2023] [Indexed: 06/15/2023] Open
Abstract
Single-cell RNA sequencing (scRNA-seq) measures transcriptome-wide gene expression at single-cell resolution. Clustering analysis of scRNA-seq data enables researchers to characterize cell types and states, shedding new light on cell-to-cell heterogeneity in complex tissues. Recently, self-supervised contrastive learning has become a prominent technique for underlying feature representation learning. However, for the noisy, high-dimensional and sparse scRNA-seq data, existing methods still encounter difficulties in capturing the intrinsic patterns and structures of cells, and seldom utilize prior knowledge, resulting in clusters that mismatch with the real situation. To this end, we propose scDECL, a novel deep enhanced constraint clustering algorithm for scRNA-seq data analysis based on contrastive learning and pairwise constraints. Specifically, based on interpolated contrastive learning, a pre-training model is trained to learn the feature embedding, and then perform clustering according to the constructed enhanced pairwise constraint. In the pre-training stage, a mixup data augmentation strategy and interpolation loss is introduced to improve the diversity of the dataset and the robustness of the model. In the clustering stage, the prior information is converted into enhanced pairwise constraints to guide the clustering. To validate the performance of scDECL, we compare it with six state-of-the-art algorithms on six real scRNA-seq datasets. The experimental results demonstrate the proposed algorithm outperforms the six competing methods. In addition, the ablation studies on each module of the algorithm indicate that these modules are complementary to each other and effective in improving the performance of the proposed algorithm. Our method scDECL is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DBLABDHU/scDECL.
Collapse
Affiliation(s)
- Yanglan Gan
- School of Computer Science and Technology, Donghua University, 201600, Shanghai, China
| | - Yuhan Chen
- School of Computer Science and Technology, Donghua University, 201600, Shanghai, China
| | - Guangwei Xu
- School of Computer Science and Technology, Donghua University, 201600, Shanghai, China
| | - Wenjing Guo
- School of Computer Science and Technology, Donghua University, 201600, Shanghai, China
| | - Guobing Zou
- School of Computer Engineering and Science, Shanghai University, 200444, Shanghai, China
| |
Collapse
|
4
|
Dadoun H, Delingette H, Rousseau AL, de Kerviler E, Ayache N. Deep clustering for abdominal organ classification in ultrasound imaging. J Med Imaging (Bellingham) 2023; 10:034502. [PMID: 37216152 PMCID: PMC10194825 DOI: 10.1117/1.jmi.10.3.034502] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Revised: 02/27/2023] [Accepted: 04/27/2023] [Indexed: 05/24/2023] Open
Abstract
Purpose The purpose of this study is to examine the utilization of unlabeled data for abdominal organ classification in multi-label (non-mutually exclusive classes) ultrasound images, as an alternative to the conventional transfer learning approach. Approach We present a new method for classifying abdominal organs in ultrasound images. Unlike previous approaches that only relied on labeled data, we consider the use of both labeled and unlabeled data. To explore this approach, we first examine the application of deep clustering for pretraining a classification model. We then compare two training methods, fine-tuning with labeled data through supervised learning and fine-tuning with both labeled and unlabeled data using semisupervised learning. All experiments were conducted on a large dataset of unlabeled images (n u = 84967 ) and a small set of labeled images (n s = 2742 ) comprising progressively 10%, 20%, 50%, and 100% of the images. Results We show that for supervised fine-tuning, deep clustering is an effective pre-training method, with performance matching that of ImageNet pre-training using five times less labeled data. For semi-supervised learning, deep clustering pre-training also yields higher performance when the amount of labeled data is limited. Best performance is obtained with deep clustering pre-training combined with semi-supervised learning and 2742 labeled example images with an F 1 -score weighted average of 84.1%. Conclusions This method can be used as a tool to preprocess large unprocessed databases, thus reducing the need for prior annotations of abdominal ultrasound studies for the training of image classification algorithms, which in turn could improve the clinical use of ultrasound images.
Collapse
Affiliation(s)
- Hind Dadoun
- Université Côte d’Azur, Inria Epione Team, Sophia Antipolis, Nice, France
| | - Hervé Delingette
- Université Côte d’Azur, Inria Epione Team, Sophia Antipolis, Nice, France
| | | | | | - Nicholas Ayache
- Université Côte d’Azur, Inria Epione Team, Sophia Antipolis, Nice, France
| |
Collapse
|
5
|
Chen S, Gao J, Chen J, Xie Y, Shen Z, Xu L, Che J, Wu J, Dong X. ClusterX: a novel representation learning-based deep clustering framework for accurate visual inspection in virtual screening. Brief Bioinform 2023; 24:7107930. [PMID: 37020333 DOI: 10.1093/bib/bbad126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2022] [Revised: 03/13/2023] [Accepted: 03/14/2023] [Indexed: 04/07/2023] Open
Abstract
Molecular clustering analysis has been developed to facilitate visual inspection in the process of structure-based virtual screening. However, traditional methods based on molecular fingerprints or molecular descriptors limit the accuracy of selecting active hit compounds, which may be attributed to the lack of representations of receptor structural and protein-ligand interaction during the clustering. Here, a novel deep clustering framework named ClusterX is proposed to learn molecular representations of protein-ligand complexes and cluster the ligands. In ClusterX, the graph was used to represent the protein-ligand complex, and the joint optimisation can be used efficiently for learning the cluster-friendly features. Experiments on the KLIFs database show that the model can distinguish well between the binding modes of different kinase inhibitors. To validate the effectiveness of the model, the clustering results on the virtual screening dataset further demonstrated that ClusterX achieved better or more competitive performance against traditional methods, such as SIFt and extended connectivity fingerprints. This framework may provide a unique tool for clustering analysis and prove to assist computational medicinal chemists in visual decision-making.
Collapse
Affiliation(s)
- Sikang Chen
- Hangzhou Institute of Innovative Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China
| | - Jian Gao
- Hangzhou Institute of Innovative Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China
| | - Jiexuan Chen
- Hangzhou Institute of Innovative Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China
| | - Yufeng Xie
- School of Software Technology, Zhejiang University, Hangzhou 310058, China
- Second Affiliated Hospital School of Medicine, and School of Public Health, Zhejiang University, Hangzhou 310058, China
| | - Zheyuan Shen
- Hangzhou Institute of Innovative Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China
| | - Lei Xu
- Cancer Center of Zhejiang University, Hangzhou 310058, China
| | - Jinxin Che
- Hangzhou Institute of Innovative Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China
| | - Jian Wu
- Second Affiliated Hospital School of Medicine, and School of Public Health, Zhejiang University, Hangzhou 310058, China
- Institute of Bioinformatics and Medical Engineering, School of Electrical and Information Engineering, Jiangsu University of Technology, Changzhou 212003, China
- College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China
| | - Xiaowu Dong
- Hangzhou Institute of Innovative Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China
- Institute of Bioinformatics and Medical Engineering, School of Electrical and Information Engineering, Jiangsu University of Technology, Changzhou 212003, China
- Innovation Institute for Artificial Intelligence in Medicine, Zhejiang University, Hangzhou 310058, China
- Department of Pharmacy, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310058, China
| |
Collapse
|
6
|
Su Y, Lin R, Wang J, Tan D, Zheng C. Denoising adaptive deep clustering with self-attention mechanism on single-cell sequencing data. Brief Bioinform 2023; 24:7008799. [PMID: 36715275 DOI: 10.1093/bib/bbad021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2022] [Revised: 12/20/2022] [Accepted: 01/05/2023] [Indexed: 01/31/2023] Open
Abstract
A large number of works have presented the single-cell RNA sequencing (scRNA-seq) to study the diversity and biological functions of cells at the single-cell level. Clustering identifies unknown cell types, which is essential for downstream analysis of scRNA-seq samples. However, the high dimensionality, high noise and pervasive dropout rate of scRNA-seq samples have a significant challenge to the cluster analysis of scRNA-seq samples. Herein, we propose a new adaptive fuzzy clustering model based on the denoising autoencoder and self-attention mechanism called the scDASFK. It implements the comparative learning to integrate cell similar information into the clustering method and uses a deep denoising network module to denoise the data. scDASFK consists of a self-attention mechanism for further denoising where an adaptive clustering optimization function for iterative clustering is implemented. In order to make the denoised latent features better reflect the cell structure, we introduce a new adaptive feedback mechanism to supervise the denoising process through the clustering results. Experiments on 16 real scRNA-seq datasets show that scDASFK performs well in terms of clustering accuracy, scalability and stability. Overall, scDASFK is an effective clustering model with great potential for scRNA-seq samples analysis. Our scDASFK model codes are freely available at https://github.com/LRX2022/scDASFK.
Collapse
Affiliation(s)
- Yansen Su
- Key Lab of Intelligent Computing and Signal Processing of Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, 230601, China
| | - Rongxin Lin
- School of Computer Science and Technology, Anhui University, Hefei, 230601, China
| | - Jing Wang
- School of Computer Science and Technology, Anhui University, Hefei, 230601, China
| | - Dayu Tan
- Institutes of Physical Science and Information Technology, Anhui University, Hefei, 230601, China
| | - Chunhou Zheng
- Key Lab of Intelligent Computing and Signal Processing of Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, 230601, China
| |
Collapse
|
7
|
Zhao J, Zhao B, Song X, Lyu C, Chen W, Xiong Y, Wei DQ. Subtype-DCC: decoupled contrastive clustering method for cancer subtype identification based on multi-omics data. Brief Bioinform 2023; 24:7005165. [PMID: 36702755 DOI: 10.1093/bib/bbad025] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2022] [Revised: 12/21/2022] [Accepted: 01/08/2023] [Indexed: 01/28/2023] Open
Abstract
Due to the high heterogeneity and complexity of cancers, patients with different cancer subtypes often have distinct groups of genomic and clinical characteristics. Therefore, the discovery and identification of cancer subtypes are crucial to cancer diagnosis, prognosis and treatment. Recent technological advances have accelerated the increasing availability of multi-omics data for cancer subtyping. To take advantage of the complementary information from multi-omics data, it is necessary to develop computational models that can represent and integrate different layers of data into a single framework. Here, we propose a decoupled contrastive clustering method (Subtype-DCC) based on multi-omics data integration for clustering to identify cancer subtypes. The idea of contrastive learning is introduced into deep clustering based on deep neural networks to learn clustering-friendly representations. Experimental results demonstrate the superior performance of the proposed Subtype-DCC model in identifying cancer subtypes over the currently available state-of-the-art clustering methods. The strength of Subtype-DCC is also supported by the survival and clinical analysis.
Collapse
Affiliation(s)
- Jing Zhao
- State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Bowen Zhao
- State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Xiaotong Song
- School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Chujun Lyu
- State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Weizhi Chen
- State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Yi Xiong
- State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China
| | - Dong-Qing Wei
- State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
- Peng Cheng Laboratory, Vanke Cloud City Phase I Building 8, Xili Street, Nanshan District, Shenzhen, Guangdong, 518055, China
- Zhongjing Research and Industrialization Institute of Chinese Medicine, Zhongguancun Scientific Park, Meixi, Nayang, Henan, 473006, China
| |
Collapse
|
8
|
Wang J, Xia J, Wang H, Su Y, Zheng CH. scDCCA: deep contrastive clustering for single-cell RNA-seq data based on auto-encoder network. Brief Bioinform 2023; 24:6984787. [PMID: 36631401 DOI: 10.1093/bib/bbac625] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Revised: 12/12/2022] [Accepted: 12/19/2022] [Indexed: 01/13/2023] Open
Abstract
The advances in single-cell ribonucleic acid sequencing (scRNA-seq) allow researchers to explore cellular heterogeneity and human diseases at cell resolution. Cell clustering is a prerequisite in scRNA-seq analysis since it can recognize cell identities. However, the high dimensionality, noises and significant sparsity of scRNA-seq data have made it a big challenge. Although many methods have emerged, they still fail to fully explore the intrinsic properties of cells and the relationship among cells, which seriously affects the downstream clustering performance. Here, we propose a new deep contrastive clustering algorithm called scDCCA. It integrates a denoising auto-encoder and a dual contrastive learning module into a deep clustering framework to extract valuable features and realize cell clustering. Specifically, to better characterize and learn data representations robustly, scDCCA utilizes a denoising Zero-Inflated Negative Binomial model-based auto-encoder to extract low-dimensional features. Meanwhile, scDCCA incorporates a dual contrastive learning module to capture the pairwise proximity of cells. By increasing the similarities between positive pairs and the differences between negative ones, the contrasts at both the instance and the cluster level help the model learn more discriminative features and achieve better cell segregation. Furthermore, scDCCA joins feature learning with clustering, which realizes representation learning and cell clustering in an end-to-end manner. Experimental results of 14 real datasets validate that scDCCA outperforms eight state-of-the-art methods in terms of accuracy, generalizability, scalability and efficiency. Cell visualization and biological analysis demonstrate that scDCCA significantly improves clustering and facilitates downstream analysis for scRNA-seq data. The code is available at https://github.com/WJ319/scDCCA.
Collapse
Affiliation(s)
- Jing Wang
- Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China
| | - Junfeng Xia
- Institutes of Physical Science and Information Technology, Anhui University, Hefei, China
| | - Haiyun Wang
- School of Mathematics and Systems Science, Xinjiang University, Urumqi, China
| | - Yansen Su
- School of Artificial Intelligence, Anhui University, Hefei, China
| | - Chun-Hou Zheng
- School of Artificial Intelligence, Anhui University, Hefei, China
| |
Collapse
|
9
|
Abstract
The similarity among samples and the discrepancy among clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling and reliable pseudo-labeling, which enable accurate and reliable self-supervision over clustering. Without using any ground-truth label, we optimize the clustering network in three stages: 1) train the feature model through contrastive learning to measure the instance similarity; 2) train the clustering head with the prototype pseudo-labeling algorithm to identify cluster semantics; and 3) jointly train the feature model and clustering head with the reliable pseudo-labeling algorithm to improve the clustering performance. Extensive experimental results demonstrate that SPICE achieves significant improvements (~10%) over existing methods and establishes the new state-of-the-art clustering results on six balanced benchmark datasets in terms of three popular metrics. Importantly, SPICE significantly reduces the gap between unsupervised and fully-supervised classification; e.g. there is only 2% (91.8% vs 93.8%) accuracy difference on CIFAR-10. Our code is made publicly available at https://github.com/niuchuangnn/SPICE.
Collapse
|
10
|
Madival SD, Mishra DC, Sharma A, Kumar S, Maji AK, Budhlakoti N, Sinha D, Rai A. A Deep Clustering-based Novel Approach for Binning of Metagenomics Data. Curr Genomics 2022; 23:353-368. [PMID: 36778191 PMCID: PMC9878855 DOI: 10.2174/1389202923666220928150100] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2022] [Revised: 08/30/2022] [Accepted: 09/02/2022] [Indexed: 11/22/2022] Open
Abstract
Background One major challenge in binning Metagenomics data is the limited availability of reference datasets, as only 1% of the total microbial population is yet cultured. This has given rise to the efficacy of unsupervised methods for binning in the absence of any reference datasets. Objective To develop a deep clustering-based binning approach for Metagenomics data and to evaluate results with suitable measures. Methods In this study, a deep learning-based approach has been taken for binning the Metagenomics data. The results are validated on different datasets by considering features such as Tetra-nucleotide frequency (TNF), Hexa-nucleotide frequency (HNF) and GC-Content. Convolutional Autoencoder is used for feature extraction and for binning; the K-means clustering method is used. Results In most cases, it has been found that evaluation parameters such as the Silhouette index and Rand index are more than 0.5 and 0.8, respectively, which indicates that the proposed approach is giving satisfactory results. The performance of the developed approach is compared with current methods and tools using benchmarked low complexity simulated and real metagenomic datasets. It is found better for unsupervised and at par with semi-supervised methods. Conclusion An unsupervised advanced learning-based approach for binning has been proposed, and the developed method shows promising results for various datasets. This is a novel approach for solving the lack of reference data problem of binning in metagenomics.
Collapse
Affiliation(s)
| | - Dwijesh Chandra Mishra
- Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India;,Address correspondence to this author at the Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India; E-mail:
| | - Anu Sharma
- Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India
| | - Sanjeev Kumar
- Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India
| | - Arpan Kumar Maji
- Division of Computer Applications, ICAR-IASRI, New Delhi- 110012, India
| | - Neeraj Budhlakoti
- Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India
| | - Dipro Sinha
- Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India
| | - Anil Rai
- Division of Agriculture Bioinformatics, ICAR-IASRI, New Delhi- 110012, India
| |
Collapse
|
11
|
Abstract
OBJECTIVE Recent advances in neural decoding have accelerated the development of brain-computer interfaces aimed at assisting users with everyday tasks such as speaking, walking, and manipulating objects. However, current approaches for training neural decoders commonly require large quantities of labeled data, which can be laborious or infeasible to obtain in real-world settings. Alternatively, self-supervised models that share self-generated pseudo-labels between two data streams have shown exceptional performance on unlabeled audio and video data, but it remains unclear how well they extend to neural decoding. APPROACH We learn neural decoders without labels by leveraging multiple simultaneously recorded data streams, including neural, kinematic, and physiological signals. Specifically, we apply cross-modal, self-supervised deep clustering to train decoders that can classify movements from brain recordings. After training, we then isolate the decoders for each input data stream and compare the accuracy of decoders trained using cross-modal deep clustering against supervised and unimodal, self-supervised models. MAIN RESULTS We find that sharing pseudo-labels between two data streams during training substantially increases decoding performance compared to unimodal, self-supervised models, with accuracies approaching those of supervised decoders trained on labeled data. Next, we extend cross-modal decoder training to three or more modalities, achieving state-of-the-art neural decoding accuracy that matches or slightly exceeds the performance of supervised models. Significance: We demonstrate that cross-modal, self-supervised decoding can be applied to train neural decoders when few or no labels are available and extend the cross-modal framework to share information among three or more data streams, further improving self-supervised training.
Collapse
Affiliation(s)
- Steven M Peterson
- Biology, University of Washington, 4000 15th Ave NE, Seattle, Washington, 98195, UNITED STATES
| | - Rajesh P N Rao
- Department of Computer Science and Engineering College of Engineering, University of Washington, Box 352350, Seattle, Washington, 98195, UNITED STATES
| | - Bingni W Brunton
- University of Washington, 4000 15th Ave NE, Seattle, Washington, 98195, UNITED STATES
| |
Collapse
|
12
|
Ryan SM, Carlson NE, Butler H, Fingerlin TE, Maier LA, Xing F. Cluster activation mapping with application to computed tomography scans of the lung. J Med Imaging (Bellingham) 2022; 9:026001. [PMID: 35274026 PMCID: PMC8902064 DOI: 10.1117/1.jmi.9.2.026001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Accepted: 02/17/2022] [Indexed: 11/14/2022] Open
Abstract
Purpose: An open question in deep clustering is how to explain what in the image is driving the cluster assignments. This is especially important for applications in medical imaging when the derived cluster assignments may inform decision-making or create new disease subtypes. We develop cluster activation mapping (CLAM), which is methodology to create localization maps highlighting the image regions important for cluster assignment. Approach: Our approach uses a linear combination of the activation channels from the last layer of the encoder within a pretrained autoencoder. The activation channels are weighted by a channelwise confidence measure, which is a modification of score-CAM. Results: Our approach performs well under medical imaging-based simulation experiments, when the image clusters differ based on size, location, and intensity of abnormalities. Under simulation, the cluster assignments were predicted with 100% accuracy when the number of clusters was set at the true value. In addition, applied to computed tomography scans from a sarcoidosis population, CLAM identified two subtypes of sarcoidosis based purely on CT scan presentation, which were significantly associated with pulmonary function tests and visual assessment scores, such as ground-glass, fibrosis, and honeycombing. Conclusions: CLAM is a transparent methodology for identifying explainable groupings of medical imaging data. As deep learning networks are often criticized and not trusted due to their lack of interpretability, our contribution of CLAM to deep clustering architectures is critical to our understanding of cluster assignments, which can ultimately lead to new subtypes of diseases.
Collapse
Affiliation(s)
- Sarah M. Ryan
- University of Colorado–Denver, Department of Biostatistics and Informatics, Anschutz Medical Campus, Aurora, Colorado, United States
| | - Nichole E. Carlson
- University of Colorado–Denver, Department of Biostatistics and Informatics, Anschutz Medical Campus, Aurora, Colorado, United States
| | - Harris Butler
- University of Colorado–Denver, Department of Biostatistics and Informatics, Anschutz Medical Campus, Aurora, Colorado, United States
| | - Tasha E. Fingerlin
- University of Colorado–Denver, Department of Biostatistics and Informatics, Anschutz Medical Campus, Aurora, Colorado, United States
- National Jewish Health, Department of Biomedical Research, Denver, Colorado, United States
- University of Colorado–Denver, Department of Epidemiology, Anschutz Medical Campus, Aurora, Colorado, United States
| | - Lisa A. Maier
- National Jewish Health, Department of Medicine, Denver, Colorado, United States
- University of Colorado–Denver, Department of Medicine, Anschutz Medical Campus, Aurora, Colorado, United States
- University of Colorado–Denver, Department of Environmental and Occupational Health, Anschutz Medical Campus, Aurora, Colorado, United States
| | - Fuyong Xing
- University of Colorado–Denver, Department of Biostatistics and Informatics, Anschutz Medical Campus, Aurora, Colorado, United States
| |
Collapse
|
13
|
Gan Y, Huang X, Zou G, Zhou S, Guan J. Deep structural clustering for single-cell RNA-seq data jointly through autoencoder and graph neural network. Brief Bioinform 2022; 23:6529282. [PMID: 35172334 DOI: 10.1093/bib/bbac018] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2021] [Revised: 12/27/2021] [Accepted: 01/13/2022] [Indexed: 12/20/2022] Open
Abstract
Single-cell RNA sequencing (scRNA-seq) permits researchers to study the complex mechanisms of cell heterogeneity and diversity. Unsupervised clustering is of central importance for the analysis of the scRNA-seq data, as it can be used to identify putative cell types. However, due to noise impacts, high dimensionality and pervasive dropout events, clustering analysis of scRNA-seq data remains a computational challenge. Here, we propose a new deep structural clustering method for scRNA-seq data, named scDSC, which integrate the structural information into deep clustering of single cells. The proposed scDSC consists of a Zero-Inflated Negative Binomial (ZINB) model-based autoencoder, a graph neural network (GNN) module and a mutual-supervised module. To learn the data representation from the sparse and zero-inflated scRNA-seq data, we add a ZINB model to the basic autoencoder. The GNN module is introduced to capture the structural information among cells. By joining the ZINB-based autoencoder with the GNN module, the model transfers the data representation learned by autoencoder to the corresponding GNN layer. Furthermore, we adopt a mutual supervised strategy to unify these two different deep neural architectures and to guide the clustering task. Extensive experimental results on six real scRNA-seq datasets demonstrate that scDSC outperforms state-of-the-art methods in terms of clustering accuracy and scalability. Our method scDSC is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/scDSC.
Collapse
Affiliation(s)
- Yanglan Gan
- School of Computer Science and Technology, Donghua University 201600, Shanghai, China
| | - Xingyu Huang
- School of Computer Science and Technology, Donghua University 201600, Shanghai, China
| | - Guobing Zou
- School of Computer Science and Technology, Shanghai University 200444, Shanghai, China
| | - Shuigeng Zhou
- Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University 200433, Shanghai, China
| | - Jihong Guan
- Computer Science and Technology, Tongji University 200092, Shanghai, China
| |
Collapse
|
14
|
Manojlović T, Štajduhar I. Deep Semi-Supervised Algorithm for Learning Cluster-Oriented Representations of Medical Images Using Partially Observable DICOM Tags and Images. Diagnostics (Basel) 2021; 11:1920. [PMID: 34679618 DOI: 10.3390/diagnostics11101920] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2021] [Revised: 10/13/2021] [Accepted: 10/15/2021] [Indexed: 11/16/2022] Open
Abstract
The task of automatically extracting large homogeneous datasets of medical images based on detailed criteria and/or semantic similarity can be challenging because the acquisition and storage of medical images in clinical practice is not fully standardised and can be prone to errors, which are often made unintentionally by medical professionals during manual input. In this paper, we propose an algorithm for learning cluster-oriented representations of medical images by fusing images with partially observable DICOM tags. Pairwise relations are modelled by thresholding the Gower distance measure which is calculated using eight DICOM tags. We trained the models using 30,000 images, and we tested them using a disjoint test set consisting of 8000 images, gathered retrospectively from the PACS repository of the Clinical Hospital Centre Rijeka in 2017. We compare our method against the standard and deep unsupervised clustering algorithms, as well as the popular semi-supervised algorithms combined with the most commonly used feature descriptors. Our model achieves an NMI score of 0.584 with respect to the anatomic region, and an NMI score of 0.793 with respect to the modality. The results suggest that DICOM data can be used to generate pairwise constraints that can help improve medical images clustering, even when using only a small number of constraints.
Collapse
|
15
|
Hu H, Li Z, Li X, Yu M, Pan X. ScCAEs: deep clustering of single-cell RNA-seq via convolutional autoencoder embedding and soft K-means. Brief Bioinform 2021; 23:6362111. [PMID: 34472585 DOI: 10.1093/bib/bbab321] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2021] [Revised: 07/23/2021] [Accepted: 07/24/2021] [Indexed: 12/12/2022] Open
Abstract
Clustering and cell type classification are a vital step of analyzing scRNA-seq data to reveal the complexity of the tissue (e.g. the number of cell types and the transcription characteristics of the respective cell type). Recently, deep learning-based single-cell clustering algorithms become popular since they integrate the dimensionality reduction with clustering. But these methods still have unstable clustering effects for the scRNA-seq datasets with high dropouts or noise. In this study, a novel single-cell RNA-seq deep embedding clustering via convolutional autoencoder embedding and soft K-means (scCAEs) is proposed by simultaneously learning the feature representation and clustering. It integrates the deep learning with convolutional autoencoder to characterize scRNA-seq data and proposes a regularized soft K-means algorithm to cluster cell populations in a learned latent space. Next, a novel constraint is introduced to the clustering objective function to iteratively optimize the clustering results, and more importantly, it is theoretically proved that this objective function optimization ensures the convergence. Moreover, it adds the reconstruction loss to the objective function combining the dimensionality reduction with clustering to find a more suitable embedding space for clustering. The proposed method is validated on a variety of datasets, in which the number of clusters in the mentioned datasets ranges from 4 to 46, and the number of cells ranges from 90 to 30 302. The experimental results show that scCAEs is superior to other state-of-the-art methods on the mentioned datasets, and it also keeps the satisfying compatibility and robustness. In addition, for single-cell datasets with the batch effects, scCAEs can ensure the cell separation while removing batch effects.
Collapse
Affiliation(s)
- Hang Hu
- Zhejiang Sci-Tech University, Hangzhou, 310018 Zhejiang, China
| | | | - Xiangjie Li
- Chinese Academy of Medical Sciences and Peking Union Medical College. But now, he is an assitant professor at School of Statistics and Data Science, Nankai University, Tianjin, China
| | - Minzhe Yu
- Zhejiang Sci-Tech University, Hangzhou, 310018 Zhejiang, China
| | - Xiutao Pan
- Zhejiang Sci-Tech University, Hangzhou, 310018 Zhejiang, China
| |
Collapse
|
16
|
Wu M, Zhang W, Guo Z, Song J, Zeng Y, Huang Y, Yang Y, Zhang P, Liu J. Separation of normal and impaired dynamic cerebral autoregulation using deep embedded clustering: a proof-of-concept study. Physiol Meas 2021; 42. [PMID: 34167102 DOI: 10.1088/1361-6579/ac0e81] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Accepted: 06/24/2021] [Indexed: 11/11/2022]
Abstract
Objective. A previous study has shown that a data-driven approach can significantly improve the discriminative power of transfer function analysis (TFA) used to differentiate between normal and impaired cerebral autoregulation (CA) in two groups of data. The data was collected from both healthy subjects (assumed to have normal CA) and symptomatic patients with severe stenosis (assumed to have impaired CA). However, the sample size of the labeled data was relatively small, owing to the difficulty in data collection. Therefore, in this proof-of-concept study, we investigate the feasibility of using an unsupervised learning model to differentiate between normal and impaired CA on TFA variables without requiring labeled data for learning.Approach. Continuous arterial blood pressure (ABP) and cerebral blood flow velocity (CBFV), which were recorded simultaneously for approximately 10 min, were included from 148 subjects (41 healthy subjects, 31 with mild stenosis, 13 with moderate stenosis, 22 asymptomatic patients with severe stenosis, and 41 symptomatic patients with severe stenosis). Tiecks' model was used to generate surrogate data with normal and impaired CA. A recently proposed unsupervised learning model was optimized and applied to separate the normal and impaired CA for both the surrogate data and real data.Main results. It achieved 98.9% and 74.1% accuracy for the surrogate and real data, respectively.Significance. To our knowledge, this is the first attempt to employ an unsupervised data-driven approach to assess CA using TFA. This method enables the development of a classifier to determine the status of CA, which is currently lacking.
Collapse
Affiliation(s)
- Menglu Wu
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.,University of Chinese Academy of Sciences, Beijing, People's Republic of China.,Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing, Shenzhen, People's Republic of China
| | - Wei Zhang
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.,University of Chinese Academy of Sciences, Beijing, People's Republic of China.,Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing, Shenzhen, People's Republic of China
| | - Zhenni Guo
- Stroke Center, Department of Neurology, the First Hospital of Jilin University, Changchun, People's Republic of China
| | - Jianing Song
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.,University of Chinese Academy of Sciences, Beijing, People's Republic of China.,Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing, Shenzhen, People's Republic of China
| | - Yuhong Zeng
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.,University of Chinese Academy of Sciences, Beijing, People's Republic of China.,Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing, Shenzhen, People's Republic of China
| | - Yuyu Huang
- Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, People's Republic of China
| | - Yi Yang
- Stroke Center, Department of Neurology, the First Hospital of Jilin University, Changchun, People's Republic of China
| | - Pandeng Zhang
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.,Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing, Shenzhen, People's Republic of China
| | - Jia Liu
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.,Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing, Shenzhen, People's Republic of China
| |
Collapse
|
17
|
Xue Z, Guo P, Desai KT, Pal A, Ajenifuja KO, Adepiti CA, Long LR, Schiffman M, Antani S. A Deep Clustering Method For Analyzing Uterine Cervix Images Across Imaging Devices. Proc IEEE Int Symp Comput Based Med Syst 2021; 2021:527-532. [PMID: 35445152 PMCID: PMC9017785 DOI: 10.1109/cbms52027.2021.00085] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Visual inspection of the cervix with acetic acid (VIA), though error prone, has long been used for screening women and to guide management for cervical cancer. The automated visual evaluation (AVE) technique, in which deep learning is used to predict precancer based on a digital image of the acetowhitened cervix, has demonstrated its promise as a low-cost method to improve on human performance. However, there are several challenges in moving AVE beyond proof-of-concept and deploying it as a practical adjunct tool in visual screening. One of them is making AVE robust across images captured using different devices. We propose a new deep learning based clustering approach to investigate whether the images taken by three different devices (a common smartphone, a custom smartphone-based handheld device for cervical imaging, and a clinical colposcope equipped with SLR digital camera-based imaging capability) can be well distinguished from each other with respect to the visual appearance/content within their cervix regions. We argue that disparity in visual appearance of a cervix across devices could be a significant confounding factor in training and generalizing AVE performance. Our method consists of four components: cervix region detection, feature extraction, feature encoding, and clustering. Multiple experiments are conducted to demonstrate the effectiveness of each component and compare alternative methods in each component. Our proposed method achieves high clustering accuracy (97%) and significantly outperforms several representative deep clustering methods on our dataset. The high clustering performance indicates the images taken from these three devices are different with respect to visual appearance. Our results and analysis establish a need for developing a method that minimizes such variance among the images acquired from different devices. It also recognizes the need for large number of training images from different sources for robust device-independent AVE performance worldwide.
Collapse
Affiliation(s)
- Zhiyun Xue
- National Library of Medicine, National Institutes of Health, Bethesda, USA
| | - Peng Guo
- National Library of Medicine, National Institutes of Health, Bethesda, USA
| | - Kanan T Desai
- National Cancer Institute, National Institutes of Health, USA
| | - Anabik Pal
- National Library of Medicine, National Institutes of Health, Bethesda, USA
| | | | | | - L Rodney Long
- National Library of Medicine, National Institutes of Health, Bethesda, USA
| | - Mark Schiffman
- National Cancer Institute, National Institutes of Health, USA
| | - Sameer Antani
- National Library of Medicine, National Institutes of Health, Bethesda, USA
| |
Collapse
|
18
|
Abstract
Despite the overwhelming success of deep learning in various speech processing tasks, the problem of separating simultaneous speakers in a mixture remains challenging. Two major difficulties in such systems are the arbitrary source permutation and unknown number of sources in the mixture. We propose a novel deep learning framework for single channel speech separation by creating attractor points in high dimensional embedding space of the acoustic signals which pull together the time-frequency bins corresponding to each source. Attractor points in this study are created by finding the centroids of the sources in the embedding space, which are subsequently used to determine the similarity of each bin in the mixture to each source. The network is then trained to minimize the reconstruction error of each source by optimizing the embeddings. The proposed model is different from prior works in that it implements an end-to-end training, and it does not depend on the number of sources in the mixture. Two strategies are explored in the test time, K-means and fixed attractor points, where the latter requires no post-processing and can be implemented in real-time. We evaluated our system on Wall Street Journal dataset and show 5.49% improvement over the previous state-of-the-art methods.
Collapse
Affiliation(s)
- Zhuo Chen
- Department of Electrical Engineering, Columbia University, New York, NY
| | - Yi Luo
- Department of Electrical Engineering, Columbia University, New York, NY
| | - Nima Mesgarani
- Department of Electrical Engineering, Columbia University, New York, NY
| |
Collapse
|