Special Issue on Advances in Scalable Computing Techniques for Signal Reconstruction and Medical Image Analysis
Large-scale methods have attracted considerable amount of interests in many communities such as machine learning, computer vision and medical image computing. There is an explosive growth of papers using relevant techniques to solve medical imaging problems. These methods have been used successfully to speed up the development of traditional techniques in medical imaging, such as reconstruction, organ segmentation from CT and MRI and classification methods for diseases. They have attracted increasing research interests in major medical imaging conferences and journals, proving that scalable methods and related clinical applications are very important topics in this community.
This special issue will emphasize on novel scalable solutions for large dataset generated by medical devices, and aim to explore the use of “big data” algorithms in medical image domains. It focuses on scalable image reconstruction and analysis algorithms, methods and solutions for addressing the ever-increasing amounts of image data that are dynamic, complex, multidimensional and multi-modal, in addition to their applications in medical imaging and major trends and challenges in this area. This special issue covers all aspects of large-scale medical image computing such as signal reconstruction, segmentation, classification and retrieval, and will be the venue for papers which potentially involve interdisciplinary researchers from all the fields connected to large-scale medical image computing. Our goal is to help advance the scientific research within the broad field of large-scale medical image computing. The special issue will consist of previously unpublished, contributed, and invited papers, and we are looking for original, high-quality submissions on innovative research and development in the analysis of scalable methods on medical image data.
The topics include but are not limited to:
(a) Scalable machine learning methods for medical image computing
(b) Efficient and scalable optimization methods, such as compressed sensing methods, and their applications in medical imaging, such as compressed sensing, e.g., MRI reconstruction
(c) Content-based medical image retrieval in large database
(d) Efficient and scalable methods for segmentation, registration, classification, detection, shape modeling, etc.
(e) Methods dealing with incomplete-, weak- or noisy annotation of training examples
(f) Generative models of 3D image scenes relying on, or complementing, population atlases of anatomy or function
(g) Features engineering methods, e.g., deep learning methods, to classify different diseases or detect region of interests, such as cell detection in histopathological images.
Timeline
Submission due: January 15, 2016
Results of first round: March 15, 2016
Revised paper due: May 15, 2016
Final Decisions: July 25, 2016
Camera ready August 25, 2016
Issue Publication (tentative): September, 2016 Submission Instruction
Authors should prepare their manuscript according to the Guide for Authors available from the online submission page of the Neurocomputing journal at http://www.journals.elsevier.com/neurocomputing/. Authors should choose “SI: SCMIA” under Article Type. All the papers will be peer-reviewed following the Neurocomputing reviewing procedures.
Guest Editors Shaoting Zhang , UNC Charlotte
Yuanjie Zheng , Shandong Normal University
Junzhou Huang , UT Arlington
Weidong Cai, The University of Sydney
| 
发表于 2015-10-3 09:20:36