Second International Workshop on

Machine Learning in Medical Imaging (MLMI)

In conjunction with MICCAI 2011

Westin Harbour Castle, Toronto, Canada

September 18, 2011

Introduction

Machine learning plays an essential role in the medical imaging field, including computer-aided diagnosis, image segmentation, image registration, image fusion, image-guided therapy, image annotation and image database retrieval. Machine Learning in Medical Imaging (MLMI) 2011 is the second workshop on this topic in conjunction with MICCAI. This workshop focuses on major trends and challenges in this area, and it presents work aimed to identify new cutting-edge techniques and their use in medical imaging. Our goal is to help advance the scientific research within the broad field of machine learning in medical imaging. The technical program will consist of previously unpublished, contributed, and invited papers, with a substantial time allocated to discussion. We are looking for original, high-quality submissions on innovative research and development in the analysis of medical image data using machine learning techniques.

News:
Key Dates:
  • Paper Submission: June 1, 2011 Extended to the midnight of June 13, 2011 PST (3am, June 14 EST, Toronto Time)
  • Notification of Acceptance: July 11, 2011 July 16, 2011
  • Camera-ready Version: July 18, 2011 July 22, 2011
  • Workshop: September 18, 2011
Organizers:

Call For Papers

Machine learning plays an essential role in the medical imaging field, including computer-aided diagnosis, image segmentation, image registration, image fusion, image-guided therapy, image annotation and image database retrieval. With advances in medical imaging, new imaging modalities and methodologies such as cone-beam/multi-slice CT, 3D ultrasound imaging, tomosynthesis, diffusion-weighted MRI, positron-emission tomography (PET)/CT, electrical impedance tomography and diffuse optical tomography, new machine-learning algorithms/applications are demanded in the medical imaging field. Single-sample evidence provided by the patient?fs imaging data is often not sufficient to provide satisfactory performance. Because of large variations and complexity, it is generally difficult to derive analytic solutions or simple equations to represent objects such as lesions and anatomy in medical images. Therefore, tasks in medical imaging require learning from examples for accurate representation of data and prior knowledge.

Researchers are now beginning to use techniques such as modern implementations of supervised, unsupervised, semi-supervised and reinforcement learning, for instance, using probabilistic modeling, manifold learning and kernel methods. The main aim of this workshop is to help advance the scientific research within the broad field of machine learning in medical imaging. This workshop will focus on major trends and challenges in this area, and it presents work aimed to identify new cutting-edge techniques and their use in medical imaging. We hope the workshop to become a new platform for translating research from bench to bedside. We are looking for original, high-quality submissions on innovative research and development in the analysis of medical image data using machine learning techniques.

Topics of interests include but are not limited to:

  • Machine learning (e.g., with support vector machines, statistical methods, manifold-space-based methods, artificial neural networks) applications to medical images with 2D, 3D and 4D data
  • Medical image analysis (e.g., pattern recognition, classification, segmentation, registration) of anatomical structures and lesions
  • Computer-aided detection/diagnosis (e.g., for lung cancer, prostate cancer, breast cancer, colon cancer, liver cancer, acute disease, chronic disease, osteoporosis)
  • Multi-modality fusion (e.g., MRI/PET, PET/CT, projection X-ray/CT, X-ray/ultrasound) for diagnosis, image analysis and image guided interventions
  • Image reconstruction (e.g., expectation maximization (EM) algorithm, statistical methods) for medical imaging (e.g., CT, PET, MRI, X-ray)
  • Image retrieval (e.g., context-based retrieval, lesion similarity)
  • Cellular image analysis (e.g., genotype, phenotype, classification, identification, cell tracking)
  • Molecular/pathologic image analysis
  • Dynamic, functional, physiologic, and anatomic imaging

Download the workshop flyer in PDF format

Submission Guidelines

Proceedings: The MLMI 2011 proceedings will be published as a volume in the Springer Lecture Notes in Computer Science (LNCS) series.

Paper Formatting: Papers are limited to eight pages. Papers should be formatted in Lecture Notes in Computer Science style. Style files can be found on the Springer website. The file format for submissions is Adobe Portable Document Format (PDF). Other formats will not be accepted.

Blind review: MLMI reviewing is double blind: authors do not know the names of the reviewers of their papers, and reviewers do not know the names of the authors. Please see the Anonymity guidelines of MICCAI 2011 for detailed explanations of how to ensure this.

Submission: MLMI is using an online submission system.

Supplemental material: Supplemental material submission is optional. This material may include: videos of results that cannot be included in the main paper, anonymized related submissions to other conferences and journals, and appendices or technical reports containing extended proofs and mathematical derivations that are not essential for understanding of the paper. Contents of the supplemental material should be referred to appropriately in the paper and that reviewers are not obliged to look at it.

Simultaneous submissions: Our policy is that in submitting a paper, authors implicitly acknowledge that NO paper of substantially similar content has been or will be submitted to another conference or workshop until MLMI decisions are made.

Camera-ready Submission MLMI is using the same site for the final submission. Please follow the instructions from the Springer website to prepare your final submission. Authors of each accepted paper needs to upload a single zip file including the following materials: 1. a completed copyright form, 2. a PDF of the camera ready, and 3. source files of the camera ready, namely, a Word file or a .tex file plus all figures, style files, special fonts, .eps, .bib etc.

Registration

Please register for the MLMI workshop through the MICCAI registration system.  Make sure to select the MLMI workshop.

Workshop Program

Plenary Speaker:

  • Prof. Daniel Rueckert from Department of Computing at Imperial College London gives a keynote talk entitled "Learning and Discovery of Clinically Useful Information from Medical Images"

   Abstract:  Three-dimensional (3D) and four-dimensional (4D) imaging plays an increasingly important role in computer-assisted diagnosis, intervention and therapy. However, in many cases the interpretation of these images is heavily dependent on the subjective assessment of the imaging data by clinicians. Over the last decades image registration has transformed the clinical workflow in many areas of medical imaging. At the same time, advances in machine learning have transformed many of the classical problems in computer vision into machine learning problems. This talk will focus on the convergence of image registration and machine learning techniques for the discovery and quantification of clinically useful information from medical images. To illustrate this I will show several examples such as the segmentation of neuro-anatomical structures, the discovery of biomarkers for neurodegenerative diseases such as Alzheimer’s and the quantification of temporal changes such as growth in the developing brain.

Final Agenda:

  • 8:30 - 8:45 Opening Remarks & Announcements
  • 8:45 - 9:45 Keynote Address: Prof. Daniel Rueckert (Imperial College London)

    Learning and Discovery of Clinically Useful Information from Medical Images

  • 9:45 - 10:30 Oral Session 1: Disease Classification
        Session Chair: Xiaogang Wang
  1. Random Forest-Based Manifold Learning for Classification of Imaging Data in Dementia
    Katherine Gray, Paul Aljabar, Rolf Heckemann, Alexander Hammers, and Daniel Rueckert
  2. Anatomical Regularization on Statistical Manifolds for the Classification of Patients with Alzheimer's Disease
    Remi Cuingnet, Joan Alexis Glaunès, Marie Chupin, Habib Benali, and Olivier Colliot
  3. Tree Structured Model of Skin Lesion Growth Pattern via Color Based Cluster Analysis
    Sina KhakAbi, Tim Lee, and M. Stella Atkins
  • 10:30 - 10:45 Coffee Break
  • 10:45 - 12:00 Oral Session 2: Anatomical Segmentation
        Session Chair: Alison Noble
  1. Segmenting Hippocampus from 7.0 Tesla MR Images by Combining Multiple Atlases and Auto-Context Models
    Minjeong Kim, Guorong Wu, Wei Li, Li Wang, Young-Don Son, Zang-Hee Cho, and Dinggang Shen
  2. Subject-Specific Cardiac Segmentation Based on Reinforcement Learning with Shape Instantiation
    Lichao Wang, Su-Lin Lee, Robert Merrifield, and Guang-Zhong Yang
  3. Maximum Likelihood and James-Stein Edge Estimators for Left Ventricle Tracking in 3D Echocardiography
    Engin Dikici, and Fredrik Orderud
  4. Automatic Segmentation of Vertebrae from Radiographs: A Sample-driven Active Shape Model Approach
    Peter Mysling, Kersten Petersen, Mads Nielsen, and Martin Lillholm
  5. An Effective Supervised Framework for Retinal Blood Vessel Segmentation using Local Standardisation and Bagging
    Uyen Nguyen, Ramamohanarao Kotagi, Laurence Park, and Alauddin Bhuiyan
  • 12:00 - 13:00 Lunch (on your own)
  • 13:00 - 14:30 Poster Session
  • 14:30 - 15:15 Oral Session 3: Localization/Detection
        Session Chair: Yiqiang Zhan
  1. Automated Cephalometric Landmark Localization using Sparse Shape and Appearance Models
    Johannes Keustermans, Dirk Smeets, Dirk Vandermeulen, and Paul Suetens
  2. Automated Detection of Major Thoracic Structures with a Novel Online Learning Method
    Nima Tajbakhsh, Hong Wu, Wenzhe Xue, and Jianming Liang
  3. Segmentation of Skull Base Tumors from MRI Using A Hybrid Support Vector Machine-based Method
    Jiayin Zhou, Qi Tian, Vincent Chong, Wei Xiong, Weimin Huang, and Zhimin Wang
  • 15:15 - 15:45 Coffee Break
  • 15:45 - 17:00 Oral Session 4: Prediction/Modeling
        Session Chair: Jiang Li
  1. A Large-Scale Manifold Learning Approach for Brain Tumor Progression Prediction
    Loc Tran, Debrup Banerjee, Jihong Wang, Ashok Kumar, Fredrick McKenzie, Yaohang Li, and Jiang Li
  2. Multi-Kernel Classification for Integration of Clinical and Imaging Data: Application to Prediction of Cognitive Decline in Older Adults
    Roman Filipovych, Susan Resnick, and Christos Davatzikos
  3. Accurate Regression-based 4D Mitral Valve Surface Reconstruction from 2D+t MRI Slices
    Dime Vitanovski, Alexey Tsymbal, Razvan Ionasec, Andreas Greiser, Michaela Schmidt, Edgar Mueller, Xiaoguang Lu, Gareth Funka-Lea, Joachim Hornegger, and Dorin Comaniciu
  4. Hot Spots Conjecture and Its Application to Modeling Tubular Structures
    Moo Chung, Seongho Seo, Nagesh Adluru, and Houri Vorperian
  • 17:00 - 17:15 Award Announcement and Closing Remarks

Download the final program in PDF format

For oral presenters:  Each paper has 12 minutes for presentation and 3 minutes for questions & answers.  Presenters should contact their session chair before each session starts.  Please bring your slides in a USB drive and load them into a laptop computer in the workshop room before your session starts.

Posters:

  1. Learning Statistical Correlation of Prostate Deformations for Fast Registration
    Yonghong Shi, Shu Liao, and Dinggang Shen
  2. Computer-Assisted Intramedullary Nailing using Real-Time Bone Detection in 2D Ultrasound Images
    Agnès Masson-Sibut, Amir Nakib, Eric Petit, and François Leitner
  3. Automated Selection of Standardized Planes From Ultrasound Volume
    Bahbibi Rahmatullah, Aris Papageorghiou, and J. Alison Noble
  4. A Locally Deformable Statistical Shape Model
    Carsten Last, Simon Winkelbach, Friedrich Wahl, Klaus Eichhorn, and Friedrich Bootz
  5. Monte Carlo Expectation Maximization with Hidden Markov Models to Detect Functional Networks in Resting-State fMRI
    Wei Liu, Suyash Awate, Jeffrey Anderson, Deborah Yurgelun-Todd, and Thomas Fletcher
  6. DCE-MRI Analysis using Sparse Adaptive Representations
    Gabriele Chiusano, Alessandra Stagliano, Curzio Basso, and Alessandro Verri
  7. Learning Optical Flow Propagation Strategies using Random Forests for Fast Segmentation in Dynamic 2D & 3D Echocardiography
    Michael Verhoek, John McManigle, and J. Alison Noble
  8. A Non-rigid Registration Framework That Accommodates Pathology Detection
    Chao Lu, and James Duncan
  9. Segmentation based Features for Lymph Node Detection from 3-D Chest CT
    Johannes Feulner, Kevin Zhou, Matthias Hammon, Joachim Hornegger, and Dorin Comaniciu
  10. Texture analysis by a PLS based method for combined feature extraction and selection
    Joselene Marques, and Erik Dam
  11. Automated Identification of Thoracolumbar Vertebrae Using Orthogonal Matching Pursuit
    Tao Wu, Bing Jian, and Sean Zhou
  12. Spatial nonparametric mixed-effects model with spatial-varying coefficients for analysis of populations
    Juan Ospina, Oscar Acosta, Gael Dréan, Guillaume Cazoulat, Antoine Simon, Pascal Haigron, Renaud de Crevoisier, and Juan Correa
  13. A Machine Learning Approach to Tongue Motion Analysis in 2D Ultrasound Image Sequences
    Lisa Tang, Ghassan Hamarneh, and Tim Bressmann
  14. Probabilistic Graphical Model of SPECT/MRI
    Stefano Pedemonte, Alexandre Bousse, Brian Hutton, Simon Arridge, and Sebastien Ourselin
  15. Directed Graph Based Image Registration
    Hongjun Jia, Guorong Wu, Qian Wang, Yaping Wang, Minjeong Kim, and Dinggang Shen
  16. Improving the Classification Accuracy of the Classic RF Method by Intelligent Feature Selection and Weighted Voting of Trees with Application to Medical Image Segmentation
    Kassim Javaid, Cyrus Cooper, and J. Alison Noble
  17. Network-based Classification using Cortical Thickness of AD Patients
    Dai Dai, Huiguang He, Joshua Vogelstein, and Zengguang Hou
  18. Rapidly Adaptive Cell Detection using Transfer Learning with a Global Parameter
    Nhat Nguyen, Eric Norris, Mark Clemens, and Min Shin
  19. Automatic Morphological Classification of Lung Cancer Subtypes with Boosting Algorithms for Optimizing Therapy
    Ching-Wei Wang, and Cheng-Ping Yu
  20. Fuzzy Statistical Unsupervised Learning based Total Lesion Metabolic Activity Estimation in Positron Emission Tomography Images
    Jose George, Kathleen Vunckx, Sabine Tejpar, Christophe Deroose, Johan Nuyts, Dirk Loeckx, and Paul Suetens
  21. Predicting Clinical Scores Using Semi-supervised Multimodal Relevance Vector Regression
    Bo Cheng, Daoqiang Zhang, Songcan Chen, and Dinggang Shen
  22. A Comparison Study of Inferences on Graphical Model for Registering Surface Model to 3D Image
    Yoshihide Sawada, and Hidekata Hontani
  23. Faster Segmentation Algorithm for Optical Coherence Tomography Images with Guaranteed Smoothness
    Lei Xu, Branislav Stojkovic, Hu Ding, Qi Song, Xiaodong Wu, Milan Sonka, and Jinhui Xu
  24. Automated Nuclear Segmentation of Coherent Anti-Stokes Raman Scattering Microscopy Images by Coupling Superpixel Context Information with Artificial Neural Networks
    Ahmad Hammoudi, Fuhai Li, Liang Gao, Zhyiong Wang, Michael Thrall, Yehia Massou, and Stephen Wong
  25. 3D Segmentation in CT Imagery with Conditional Random Fields and Histograms of Oriented Gradients
    Chetan Bhole, Nicholas Morsillo, and Christopher Pal
  26. Automatic Human Knee Cartilage Segmentation from Multi-contrast MR Images Using Extreme Learning Machines and Discriminative Random Fields
    Kunlei Zhang, and Wenmiao Lu
  27. MultiCost: Multi-stage Cost-sensitive Classification of Alzheimer's Disease
    Daoqiang Zhang, and Dinggang Shen
  28. Classifying Small Lesions on Breast MRI Through Dynamic Enhancement Pattern Characterization
    Mahesh Nagarajan, Thomas Schlossbauer, Markus Huber, Gerda Leinsinger, Andrzej Krol, and Axel Wismueller
  29. Computer-Aided Detection of Polyps in CT Colonography with Pixel-based Machine Learning Techniques
    Jianwu Xu, and Kenji Suzuki

For poster presenters:  The poster size should be a maximum of 120cm x 120cm.  Please prepare your poster accordingly.  The poster session will be held in Harbour Ballroom B in the 3rd floor.  The poster session will be held in Harbour Ballroom B in the 3rd floor.  The workshop will supply materials for mounting the poster.  Please mount your poster between 7:00-8:30 am.  Please take your poster down by 3:45 pm.

People

Organizers:

Program Committee

  • David Beymer, IBM Research, USA
  • Guangzhi Cao, GE Healthcare, USA
  • Heang-Ping Chan, University of Michigan Medical Center, USA
  • Sheng Chen, University of Chicago, USA
  • Zohara Cohen, NIBIB, NIH, USA
  • Marleen de Bruijne, University of Copenhagen, Denmark
  • Yong Fan, Chinese Academy of Sciences, China
  • Roman Filipovych, University of Pennsylvania, USA
  • Alejandro Frangi, Pompeu Fabra University, Spain
  • Hayit Greenspan, Tel Aviv University, Israel
  • Ghassan Hamarneh, Simon Fraser University, Canada
  • Joachim Hornegger, Friedrich-Alexander University, Germany
  • Steve Jiang, University of California, San Diego, USA
  • Xiaoyi Jiang, University of M?nster, Germany
  • Nico Karssemeijer, Radboud University Nijmegen Medical Centre, Netherlands
  • Minjeong Kim, University of North Carolina, Chapel Hill, USA
  • Ritwik Kumar, IBM Almaden Research Center, USA
  • Shuo Li, GE Healthcare, Canada
  • Yang Li, Allen Institute for Brain Science
  • Marius Linguraru, National Institutes of Health, USA
  • Yoshitaka Masutani, University of Tokyo, Japan
  • Marc Niethammer, University of North Carolina, Chapel Hill, USA
  • Ipek Oguz, University of North Carolina, Chapel Hill, USA
  • Kazunori Okada, San Francisco State University, USA
  • Sebastien Ourselin, University College London, UK
  • Kilian M. Pohl, University of Pennsylvania, USA
  • Yu Qiao, Shanghai Jiao Tong University, China
  • Xu Qiao, University of Chicago, USA
  • Daniel Rueckert, Imperial College London, UK
  • Clarisa Sanchez, University Medical Center Utrecht, Netherlands
  • Li Shen, Indiana University School of Medicine, USA
  • Akinobu Shimizu, Tokyo University of Agriculture and Technology, Japan
  • Min C. Shin, University of North Carolina, Charlotte, USA
  • Hotaka Takizawa, University of Tsukuba, Japan
  • Xiaodong Tao, GE Global Research, USA
  • Bram van Ginneken, Radboud University Nijmegen Medical Centre, Netherlands
  • Axel W. E. Wismueller, University of Rochester, USA
  • Guorong Wu, University of North Carolina, Chapel Hill, USA
  • Jianwu Xu, University of Chicago, USA
  • Yiqiang Zhan, Siemens Medical Solutions, USA
  • Daoqiang Zhang, Nanjing University of Aeronautics and Astronautics, China
  • Yong Zhang, IBM Almaden Research Center, USA
  • Bin Zheng, University of Pittsburgh, USA
  • Guoyan Zheng, University of Bern, Switzerland
  • Kevin Zhou, Siemens Corporate Research, USA
  • Sean Zhou, Siemens Medical Solutions, USA
  • Xiangrong Zhou, Gifu University, Japan
  • Luping Zhou, CSIRO, Australia
  • Yun Zhu, University of California, San Diego, USA
  • Hongtu Zhu, University of North Carolina, Chapel Hill, USA

Workshop Summary

Proceedings: The MLMI 2011 proceedings has been published as a volume (vol. 7009), Machine Learning in Medical Imaging, in the Springer Lecture Notes in Computer Science (LNCS) series.

Statistics: A total of 74 papers were submitted to the workshop in response to the call for papers.  Each of the 74 papers underwent a rigorous double-blinded peer-review process, with each paper being reviewed by at least two (mostly three) external reviewers in the program committee composed of 50 known experts in the field.  Based on the reviewing scores and critics, a total of the 44 best papers (59%) were accepted and included in the Springer LNCS volume as well as the MICCAI Workshop Proceedings.  Among them, 15 papers (20%) were selected for oral presentations.  We would like to thank the 50 program committee members for their outstanding reviews.

The Best Paper Award: The MLMI 2011 presented the Best Paper Award to Katherine Gray, Paul Aljabar, Rolf Heckemann, Alexander Hammers, and Daniel Rueckert in recognition of excellence of their paper entitled "Random Forest-Based Manifold Learning for Classification of Imaging Data in Dementia."  The rigorous selection process is summarized as follows:  Papers with an average score greater than or equal to 4.0 (out of 5.0) given by three reviewers on the program committee in the double-blinded review process were selected as award candidates.  Organizers reviewed and rated final submitted papers of the candidates before the workshop as well as their presentations including questions and answers during the workshop.  The final decision was made by taking both paper and presentation qualities into account.  Since all papers were outstanding, it was not an easy decision.

Attendance: There were 136 chairs in the workshop room.  Almost all the seats were occupied by interested audience throughout the workshop.  Prof. Rueckert gave an invited talk that covered key topics, methods and examples of "learning and discovery of clinically useful information from medical images" in the field of machine learning in medical imaging.  We would like to thank Prof. Rueckert for his insightful talk.  Speakers were energetic in their presentations.  Attendees actively participated in question and answer sessions.  Poster session was crowded with interested audience, and there were enthusiastic discussions.  We would like to thank all the presenters for their excellent research and presentations and all the attendees for their active participation.  We are also grateful to session chairs for their outstanding presiding.

Photos: Please enjoy some photos taken during the workshop.