Patch-based techniques play an increasing role in the medical imaging field, with various applications in image segmentation, image de-noising, image super-resolution, super-pixel/voxel-based analysis, computer-aided diagnosis, image registration, abnormality detection and image synthesis. Dictionaries of local image patches are increasingly being used for example in the context of segmentation and computer-aided diagnosis. Patch-based dictionaries are commonly used in conjunction with pattern recognition techniques to model complex anatomies in an accurate and easy way. The patch-level representation of image content is between the global image and localized voxels. This level of representation is shown to be successful in areas such as image processing (e.g., enhancement and de-noising) as well as image feature extraction and classification (e.g., convolution kernels and convolutional neural networks).
The main aim of this workshop is to help advance the scientific research within the broad field of patch-based processing 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 patch-based techniques.
Topics of interests include but are not limited to patch-based processing dedicated to:
- Image segmentation of anatomical structures or lesions (e.g., brain segmentation, cardiac segmentation, MS lesions detection, tumor segmentation)
- Image enhancement (e.g., de-noising or super-resolution dedicated to fMRI, DWI, MRI or CT)
- Computer-aided prognostic and diagnostic (e.g., for lung cancer, prostate cancer, breast cancer, colon cancer, brain diseases, liver cancer, acute disease, chronic disease, osteoporosis)
- Mono and multimodal image registration
- Multi-modality fusion (e.g., MRI/PET, PET/CT, projection X-ray/CT, X-ray/ultrasound) for diagnosis, image analysis and image guided interventions
- Mono and multi modal image synthesis (e.g., synthesis of missing a modality in a database using an external library)
- Image retrieval (e.g., context-based retrieval, lesion similarity)
- Dynamic, functional, physiologic, and anatomic imaging
- Super-pixel/voxel-based analysis in medical images
- Sparse dictionary learning and sparse coding
- Analysis of 2D, 2D+t, 3D, 3D+t and 4D and 4D+t data.
An academic objective of the workshop is to bring together researchers in medical imaging to discuss new techniques using patch-based approaches and their use in clinical decision support and large cohort studies. Another objective is to explore new paradigms of the design of biomedical image analysis systems that exploit latest results in patch-based processing and exemplar-based methods. MICCAI-PMI 2017 will feature a single-track workshop with keynote speakers, technical paper presentations, poster sessions, and demonstrations of the state-of-the-art technics and concepts that are applied to analyzing medical images.
The maximum number of pages for your paper is 8. This includes the abstract and references. Note that since Springer will enforce their formatting rules, it is extremely important that you strictly adhere to the guidelines (i.e., no vspaces, no modified margins, etc.).
Bordeaux University, LaBRI UMR CNRS, France
University of North Carolina, Chapel Hill, US
Siemens Medical Solutions, US
Imperial College London, UK
College of Charleston, US
Deutsches Zentrum fur Neurodegenerative Erkrankungen, Germany
Charles Kervrann, INRIA Rennes - Bretagne Atlantique
Daoqiang Zhang, Nanjing University of Aeronautics and Astronautics
Dinggang Shen, UNC
Francois Rousseau, IMT Atlantique
Gang Li, University of North Carolina at Chapel Hill
Guoyan Zheng, University of Bern
Hongzhi Wang, IBM Almaden Research Center
Islem Rekik, University of Dundee
Jean-Francois Mangin I2BM
Jose Manjon, ITACA institute, Universidad Politècnica de Valencia
Junzhou Huang, University of Texas at Arlington
Jussi Tohka, Universidad Carlos III de Madrid
Karim Lekadir, Universitat Pompeu Fabra
Li Shen, University of Pennsylvania
Li Wang, UNC
Martin Styner, UNC
Olivier Colliot, UPMC
Olivier Commowick, INRIA
Qian Wang, Shanghai Jiao Tong University
Rolf Heckemann, Sahlgrenska University Hospital
Sailesh Conjeti, German Center of Neurodegenerative Diseases (DZNE)
Simon Eskildsen, Center of Functionally Integrative Neuroscience, Denmark
Weidong Cai, University of Sydney
Yong Fan, University of Pennsylvania
- Keynote Speakers
Bennett Landman (Vanderbilt University)
Bennett Landman graduated with a bachelor of science (’01) and master of engineering (’02) in electrical engineering and computer science from the Massachusetts Institute of Technology, Cambridge, MA. After graduation, he worked in an image processing startup company and a private medical imaging research firm before returning for a doctorate in biomedical engineering (‘08) from Johns Hopkins University School of Medicine, Baltimore, MD. Since 2010, he has been with the Faculty of the Electrical Engineering and Computer Science Department, Vanderbilt University, Nashville, TN, where he is currently an associate professor. His research concentrates on applying image-processing technologies to leverage large-scale imaging studies to improve understanding of individual anatomy and personalize medicine.
Marc Niethammer (University of North Carolina)
His research interests lie in the areas of biomedical image analysis and visual control- and estimation-theory. He is interested in both theory development and applications to real world problems. His areas of expertise range from visual tracking for defense applications, to medical imaging algorithm development, to structural health monitoring (in a former life). He is excited by interdisciplinary work, having collaborated and worked with researchers and practitioners in mathematics, various engineering disciplines, and in the medical fields. He is particularly interested in the interplay between disciplines, where theory drives applications and applications influence theory development. His recent research focuses on biomedical image analysis, in particular, novel methods for segmentation and registration involving temporal or spatial constraints. His current application areas are (1) neuroscience and neurodevelopment, (2) osteoarthritis, (3) pediatrics, and (4) cancer.