Current Research Projects*

Intelligent 3D Single Neuron Reconstruction

The single neuron reconstruction is one of the major domains in computational neuroscience, a frontier research area intersected with signal processing, computer vision, artificial intelligence and learning theory, applied mathematics, fundamental neuroscience and quantum physics. The 3D morphology of a neuron determines its connectivity, integration of synaptic inputs and cellular firing properties, and also changes dynamically with its activity and the state of the organism. Analyzing the three-dimensional shape of neurons in an unbiased way is critical to understanding how neurons function and developing applications to model neural circuitry. Such analysis can be enabled by reconstructing tree models from microscopic image stacks by manual tracing. However, such manual process is tedious and hard to scale. This project aims to develop novel computational approaches for automatic 3D reconstruction of neuron models from noisy microscopic image stacks. Such methods would enable faster and more accurate neuron models to further accumulate the knowledge of single neuron functionality and neural network connectome.

Structural Feature Representation for Image Pattern Classification and Object Recognition

Image pattern classification has a wide variety of applications, such as differentiation of disease patterns and detection of interest objects. The classification performance is largely dependent on the descriptiveness and discriminativeness of feature representation. Consequently, how to best model the complex visual features especially the complex structural interactions is crucial. Currently many different ways of image feature extraction have been proposed in the literature, yet their performance is still unsatisfactory and feature extraction remains a hot topic in computer vision. This project aims to study the various techniques of structural feature representation, and to develop new methodologies for various applications in the medical imaging domain.

Multi-modal Neuroimaging Computing for Early Detection of Dementia

Dementia is one of the leading causes of disability in Australia, and the socioeconomic burden of dementia will be aggravated over the forthcoming decades as people live longer. So far, there is no cure for dementia, and current medical interventions may only halt or slow down the progression of the disease. Therefore, early detection of the dementia symptoms is the most important step in the management of the disease. Multi-modal neuroimaging has been increasingly used in the evaluation of patents with early dementia in the research setting, and shows great potential in mental health and clinical applications. The objective of this project is to design and develop novel neuroimaging computing models and methods to investigate pattern of dementia pathology with a focus on early detection of the disease.

Context Modeling for Medical Image Retrieval

Content-based medical image retrieval is a valuable mechanism to assist patient diagnosis. Different from text-based search engines, similarity of images is evaluated based on comparison between visual features. Consequently, how to best encode the complex visual features in a comparable mathematic form is crucial. Different from the image retrieval techniques proposed for general imaging, in the medical domain, disease-specific contexts need to be modeled as the retrieval target. This project aims to study the various techniques of visual feature extraction and context modeling in medical imaging, and to develop new methodologies for content-based image retrieval of various medical applications.

Learning-based Feature-Centric Visual Content Analysis

Great advances in biological tissue labeling and automated microscopic imaging have revolutionized how biologists visualize molecular, sub-cellular, cellular, and super-cellular structures and study their respective functions. How to interpret such image datasets in a quantitative and automatic way has become a major challenge in current computational biology. The essential methods of bioimage informatics involve generation, visualization, analysis and management. This project aims to develop novel algorithms for content analysis in microscopic images, such as segmentation of cell nuclei, detection of certain cell structures, and tracing of cell changes over time. Such algorithms would be valuable to turn image data into useful biological knowledge. The studies will focus on computer vision methodologies in feature extraction and learning-based modeling.

* For the latest research project offerings, please contact Associate Professor Weidong (Tom) Cai

 

Selected Recent Research Outcomes

Research Publications*

     Edited Books / Proceedings and Book Chapters
  • Henning Muller, Michael Kelm, Tal Arbel, Weidong Cai, Jorge Cardoso, Georg Langs, Bjoern Menze, Dimitris Metaxas, Albert Montillo, William Wells III, Shaoting Zhang, Albert Chung, Mark Jenkinson, Annemie Ribbens (Eds.), “Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging”, ISBN: 978-3-319-61188-4, Springer, 2017. (9,870 downloads as of 2018-03-25)
  • Bjoern Menze, Georg Langs, Albert Montillo, Michael Kelm, Henning Muller, Shaoting Zhang, Weidong Cai, Dimitrios Metaxas (Eds.), “Medical Computer Vision: Algorithms for Big Data – MCV 2015”, ISBN: 978-3-319-42016-5, Springer Switzerland, 2016. (6,883 downloads as of 2018-03-25)
  • Bjoern Menze, Georg Langs, Albert Montillo, Michael Kelm, Henning Muller, Shaoting Zhang, Weidong Cai, Dimitrios Metaxas (Eds.), “Medical Computer Vision: Algorithms for Big Data”, ISBN: 978-3-319-13971-5, Springer Switzerland, 2014. (18,375 downloads as of 2018-03-25)
  • Yang Song, Weidong Cai, “Handling of Feature Space Complexity for Texture Analysis in Medical Images”, in Biomedical Texture Analysis: Fundamentals, Tools and Challenges, Edited by A. Depeursinge, O.S. Al-Kadi, J.R. Mitchell, Elsevier, pp163-191, 2017. (Invited book chapter).
  • Fan Zhang, Yang Song, Weidong Cai, Adrien Depeursinge, Henning Muller, “Text- and Content-based Medical Image Retrievals in the VISCERAL Retrieval Benchmark”, in Cloud-Based Benchmarking of Medical Image Analysis, Edited by A. Hanbury, H. Muller, G. Langs, Springer, pp237-249, 2017. (Invited book chapter).
     Refereed Journal Articles
  • Afaf Tareef, Yang Song, Heng Huang, Dagan Feng, Mei Chen, Yue Wang, Weidong Cai, “Multi-pass Fast Watershed for Accurate Segmentation of Overlapping Cervical Cells”, IEEE Transactions on Medical Imaging, 2018. (Accepted to appear)
  • Fan Zhang, Weining Wu, Lipeng Ning, Gloria McAnulty, Deborah Waber, Borjan Gagoski, Kiera Sarill, Hesham M. Hamoda, Yang Song, Weidong Cai, Yogesh Rathi, Lauren J. O’Donnell, “Suprathreshold Fiber Cluster Statistics: Leveraging White Matter Geometry to Enhance Tractography Statistical Analysis”, NeuroImage, 2018. (Accepted to appear)
  • Yuchen Yuan, Yi Shi, Xianbin Su, Xin Zou, Qing Luo, Dagan Feng, Weidong Cai, Zeguang Han, “Cancer Type Prediction based on Copy Number Aberration and Chromatin 3D Structure with Convolutional Neural Networks”, BMC Genomics, 2018. (Accepted to appear)
  • Mosin Russell, Ju Jia Zou, Gu Fang, Weidong Cai, “Feature-based Image Patch Classification for Moving Shadow Detection”, IEEE Transactions on Circuits and Systems for Video Technology, 2018. (Accepted to appear)
  • Yuchen Yuan, Changyang Li, Jinman Kim, Weidong Cai, Dagan Feng, “Reversion Correction and Regularized Random Walks Ranking for Saliency Detection”, IEEE Transactions on Image Processing, Vol.27, Issue.3, pp.1311-1322, 2018.
  • Donghao Zhang, Siqi Liu, Yang Song, Dagan Feng, Hanchuan Peng, Weidong Cai, “Automated 3D Soma Segmentation with Morphological Surface Evolution for Neuron Reconstruction”, Neuroinformatics, DOI: 10.1007/s12021-017-9353-x, Springer, 2018.
  • Yang Song, Qing Li, Heng Huang, Dagan Feng, Mei Chen, Weidong Cai, “Low Dimensional Representation of Fisher Vectors for Microscopy Image Classification”, IEEE Transactions on Medical Imaging, pp1636-1649, Vol.36, No.8, 2017.
  • Yang Song, Qing Li, Fan Zhang, Heng Huang, Dagan Feng, Yue Wang, Mei Chen, Weidong Cai, “Dual Discriminative Local Coding for Tissue Aging Analysis”, Medical Image Analysis, Vol.38, pp65-76, 2017.
  • Fan Zhang, Peter Savadjiev, Weidong Cai, Yang Song, Yogesh Rathi, Birkan Tunc, Drew Parker, Tina Kapur, Robert T. Schultz, Nikos Makris, Ragini Verma, Lauren J. O’Donnell, “Whole Brain White Matter Connectivity Analysis using Machine Learning: An Application to Autism”, NeuroImage, 2017. (Accepted to appear)
  • Yang Song, Weidong Cai, Heng Huang, Dagan Feng, Yue Wang, Mei Chen, “Bioimage Classification with Subcategory Discriminant Transform of High Dimensional Visual Descriptors”, BMC Bioinformatics, 17:465, DOI 10.1186/s12859-016-1318-9, 2016.
  • Siqi Liu, Donghao Zhang, Sidong Liu, Dagan Feng, Hanchuan Peng, Weidong Cai, “Rivulet: 3D Neuron Morphology Tracing with Iterative Back-Tracking”, Neuroinformatics, Vol.14, Issue 4, pp387-401, DOI: 10.1007/s12021-016-9302-0, 2016.
  • Fan Zhang, Yang Song, Weidong Cai, Sidong Liu, Siqi Liu, Sonia Pujol, Ron Kikinis, Yong Xia, Michael Fulham, Dagan Feng, ADNI, “Pairwise Latent Semantic Association for Similarity Computation in Medical Imaging”, IEEE Transactions on Biomedical Engineering, Vol.63, No.5, pp1058-1069, 2016.
  • Sidong Liu, Weidong Cai, Sonia Pujol, Ron Kikinis, Dagan Feng, ADNI, “Cross-View Neuroimage Pattern Analysis in Alzheimer’s Disease Staging”, Frontiers in Aging Neuroscience, Feb 23;8:23. DOI: 10.3389/fnagi.2016.00023, 2016.
  • Sidong Liu, Weidong Cai, Siqi Liu, Fan Zhanng, Michael Fulham, Dagan Feng, Sonia Pujol, Ron Kikinis,”Multimodal Neuroimaging Computing: A Review of the Applications in Neuropsychiatric Disorders”, Brain Informatics, Vol.2, No.3, Springer, 2015. (Invited paper)
  • Yang Song, Weidong Cai, Heng Huang, Yun Zhou, Yue Wang, Dagan Feng, “Locality-constrained Subcluster Representation Ensemble for Lung Image Classification”, Medical Image Analysis, Vol.22, Issue 1, pp102-113, 2015.
  • Siqi Liu, Sidong Liu, Weidong Cai, Hangyu Che, Sonia Pujol, Ron Kikinis, Dagan Feng, Michael Fulham, ADNI,”Multi-Modal Neuroimaging Feature Learning for Multi-Class Diagnosis of Alzheimers’s Disease”, IEEE Transactions on Biomedical Engineering, Vol.62, Issue 4, pp1132-1140, 2015.
  • Yang Song, Weidong Cai, Heng Huang, Yun Zhou, Dagan Feng, Yue Wang, Michael Fulham, Mei Chen,”Large Margin Local Estimate with Applications to Medical Image Classification”, IEEE Transactions on Medical Imaging, Vol.34, No.6, pp1362-1377, 2015.
      Refereed Conference Papers
  • Yang Song, Hang Chang, Heng Huang, Weidong Cai, “Supervised Intra-Embedding of Fisher Vectors for Histopathology Image Classification”, The 20th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2017), Lecture Notes in Computer Science, Vol.10435, pp99-106, 2017.
  • Fan Zhang, Weining Wu, Lipeng Ning, Gloria McAnulty, Deborah Waber, Borjan Gagoski, Kiera Sarill, Hesham Hamoda, Yang Song, Weidong Cai, Yogesh Rathi, Lauren J. O’Donnell, “Supra-threshold Fiber Cluster Statistics for Data-driven Whole Brain Tractography Analysis”, MICCAI 2017, Lecture Notes in Computer Science, Vol.10433, pp556-565, 2017.
  • Yutong Xie, Yong Xia, Jianpeng Zhang, Dagan Feng, Michael Fulham, Weidong Cai, “Transferable Multi-Model Ensemble for Benign-Malignant Lung Nodule Classification on Chest CT”, MICCAI 2017, Lecture Notes in Computer Science, Vol.10435, pp656-664, 2017.
  • Siqi Liu, Donghao Zhang, Yang Song, Hanchuan Peng, Weidong Cai, “Triple-Crossing 2.5D Convolutional Neural Network for Detecting Neuronal Arbours in 3D Microscopic Images”, MICCAI 2017 Workshop on Machine Learning in Medical Imaging, Lecture Notes in Computer Science, Vol.10541, pp185-193, 2017.
  • Yang Song, Fan Zhang, Qing Li, Heng Huang, Lauren O’Donnell, Weidong Cai, “Locally-Transferred Fisher Vectors for Texture Classification”, The IEEE International Conference on Computer Vision (ICCV 2017), pp4912-4920, 2017.
  • Kamran Ghasedi Dizaji, Amirhossein Herandi, Cheng Deng, Weidong Cai, Heng Huang, “Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization”, ICCV 2017, pp5736-5745, 2017.
  • Zihao Tang, Donghao Zhang, Siqi Liu, Yang Song, Hanchuan Peng, Weidong Cai, “Automatic 3D Single Neuron Reconstruction with Exhaustive Tracing”, ICCV 2017 Workshop on Bioimage Computing, pp126-133, 2017.
  • Xiaoqian Wang, Hong Chen, Weidong Cai, Dinggang Shen, Heng Huang, “Regularized Modal Regression with Applications in Cognitive Impairment Prediction”, The 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), pp1447-1457, 2017.
  • Zhouyuan Huo, Shangqian Gao, Weidong Cai, Heng Huang, “Video Recovery via Learning Variation and Consistency of Images”, The 31st AAAI Conference on Artificial Intelligence (AAAI 2017), pp4082-4088, 2017.
  • Ju Han, Yunfu Wang, Weidong Cai, Alexander Borowsky, Bahram Parvin, Hang Chang, “Integrative Analysis of Cellular Morphometric Context Reveals Clinically Relevant Signatures in Lower Grade Glioma”, MICCAI 2016, Lecture Notes in Computer Science, Vol.9900, pp72-80, 2016.
  • Yutong Xie, Jianpeng Zhang, Sidong Liu, Weidong Cai, Yong Xia, “Lung Nodule Classification by Jointly using Visual Descriptors and Deep Features”, MICCAI 2016 Workshop on Medical Computer Vision, Lecture Notes in Computer Science, Vol.10081, pp116-125, 2016.
  • Hong Chen, Haifeng Xia, Heng Huang, Weidong Cai, “Error Analysis of Generalized Nystrom Kernel Regression”, NIPS2016, pp2541-2549, 2016.
  • Yang Song, Qing Li, Heng Huang, Dagan Feng, Mei Chen, Weidong Cai,”Histopathology Image Categorization with Discriminative Dimension Reduction of Fisher Vectors”, The 14th European Conference on Computer Vision (ECCV 2016) Workshop on Bioimage Computing, Lecture Notes in Computer Science, Vol.9913, pp306-317, 2016. 
  • Fan Zhang, Yang Song, Siqi Liu, Paul Young, Daniela Traini, Lucy Morgan, Hui-Xin Ong, Lachlan Buddle, Sidong Liu, Dagan Feng, Weidong Cai,”Motion Representation of Ciliated Cell Images with Contour-Alignment for Automated CBF Estimation”, MICCAI 2015, Lecture Notes in Computer Science 9351, pp300-307, 2015.
  • Yang Song, Weidong Cai, Fan Zhang, Heng Huang, Yun Zhou, Dagan Feng, Michael Fulham, “Latent Discriminative Modeling for Lesion Detection in PET-CT Images”,  MICCAI 2015 Workshop on Computational Methods for Molecular Imaging, pp52-62, 2015.
  • Yang Song, Weidong Cai, Qing Li, Fan Zhang, Dagan Feng, Heng Huang,”Fusing Subcategory Probabilities for Texture Classification”, The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), pp4409-4417, 2015.
  • Changyang Li, Yuchen Yuan, Weidong Cai, Yong Xia, Dagan Feng,”Robust Saliency Detection via Regularized Random Walks Ranking”, CVPR 2015, pp2710-2717, 2015.
  • Peng Li, Weidong Cai, Heng Huang, “Weakly Supervised Natural Language Processing Framework for Abstractive Multi-Document Summarization”,The 24th ACM International Conference on Information and Knowledge Management (CIKM 2015), pp1401-1410, 2015.
  • Hongchang Gao, Feiping Nie, Weidong Cai, Heng Huang,”Robust Capped Norm Nonnegative Matrix Factorization”, CIKM 2015, pp871-880, 2015.
  • Hongchang Gao, Lin Yan, Weidong Cai, Heng Huang, “Anatomical Annotations for Drosophila Gene Expression Patterns via Multi-Dimensional Visual Descriptors Integration”, The 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2015), pp339-348, 2015.

* For more research publications, please see Associate Professor Weidong (Tom) Cai’s Google Scholar

International Computational Challenges

  • Siqi Liu, Sidong Liu, Weidong Cai, “DTI Tractography Challenge with Constrained Spherical Deconvolution”, The 18th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2015) DTI Challenge on Tractography for Brain Tumor Surgery, Munich, Germany, October 5, 2015.
  • Yang Song, Fan Zhang, Weidong Cai, “Tumor Classification from Digital Pathology Images with Patch-based Local Approximation”, MICCAI 2015 – Computational Brain Tumor Cluster of Events (CBTC): Challenges in Imaging & Digital Pathology, Munich, Germany, October 9, 2015.
  • Fan Zhang, Yang Song, Weidong Cai, Adrien Depeursinge, Henning Muller, “USYD/HES-SO in the VISCERAL Retrieval Benchmark”, The 37th European Conference on Information Retrieval (ECIR 2015) Workshop on Multimodal Retrieval in the Medical Domain – VISCERAL Retrieval Benchmark, Vienna, Austria, March 29, pp139-143, LNCS 9059, March 29, 2015.
  • Siqi Liu, Sidong Liu, Weidong Cai, “3D Neuron-Reconstruction with Light Microscopic Image-Stacks of Fruit-Flies”, BigNeuron Hackathon 2015, Beijing, China, March 16-20, 2015.
  • Sidong Liu, Weidong Cai, Sonia Pujol, Ron Kikinis, Dagan Feng, “Synergy Quantization for Multi-Modal Neuroimage Classification by Cross-View Pattern Analysis”, IEEE EMBS BRAIN Grand Challenges Conference (BRAIN Challenges 2014), Washington DC, USA, November 13-14, 2014.
  • Siqi Liu, Sidong Liu, Weidong Cai, MICCAI 2014 – Machine Learning Challenge (MLC) on Predicting Binary and Continuous Phenotypes from Structural Brain MRI Data, MIT, Boston, USA, September 18, 2014.

Computational Tool Development and Software Packages

  • Yang Song, Zihao Tang, Weidong Cai, et al., Cell Tracking Toolkit, 2017, 2018. (with Faculty of Pharmacy / Charles Perkins Centre, USyd)
  • Siqi Liu, Donghao Zhang, Weidong Cai, et al., Rivulet / Rivulet 2: 3D Neuron Morphology Tracing Software, 2016, 2017, 2018. (with Allen Institute for Brain Science, Seattle, USA)
  • Yang Song, Fan Zhang, Weidong Cai, et al., n3D Bioimage Analysis Software, 2016, 2017, 2018. (with Faculty of Pharmacy / Sydney Nano Institute, USyd)
  • Sidong Liu, Siqi Liu, Fan Zhang, Yang Song, Weidong Cai, et al., “CAD Toolbox for Neurological Disorders”, The National Alliance for Medical Image Computing (NA-MIC) 2014 Summer Project Week, MIT, Boston, USA, June 23-27, 2014. (with Surgical Planning Laboratory, Harvard Medical School)
  • Sidong Liu, Weidong Cai, et al., “Individualized Neuroimaging Content Analysis using 3D Slicer in Alzheimer’s Disease”, The 17th National Alliance for Medical Image Computing (NA-MIC) 2013 Summer Project Week, MIT, Boston, USA, June 17-21, 2013. (with Surgical Planning Laboratory, Harvard Medical School)