bigMCV 2014 - Workshop on Medical Computer Vision: Algorithms for Big Data (bigMCV)

With the ever-increasing amount of annotated medical data, large-scale, data-driven methods provide the promise of bridging the semantic gap between images and diagnoses. The goal of this workshop is to explore the use of “big data” algorithms in tasks such as automatic segmentation and registration, localization of anatomical features and detection of anomalies. We will emphasize questions of harvesting, organizing and learning from large-scale medical imaging data sets and general-purpose automatic understanding of medical images. We are especially interested in modern, scalable and efficient algorithms which generalize well to previously unseen images and which can be applied to large-scale data sets that are arising, for example, from studies with significant populations, through the use of wide-field-of-view imaging sequences at high spatial resolution, or when compiling hospital-scale databases.
We encourage the submission of original papers that propose new methodology strongly motivated by a clinical application. Submissions will be at the interface of big data algorithms, computer vision, machine learning and medical image analysis. Of particular interest is work that fosters the understanding of the specific challenges, assumptions, and constraints that computer vision approaches can overcome in the medical domain.
The event is in continuation of earlier MCV workshops at MICCAI 2010, CVPR 2012, MICCAI 2012, MICCAI 2013.
The bigMCV'14 will host a "VISCERAL" session for presentation and discussion of methods for anatomical structure segmentation and localization. The session will highlight the results of the VISCERALanatomy2 challenge, and will provide a forum to discuss the individual approaches and their comparative evaluation.
Possible topics
We encourage the submissions about methodological contributions dealing with:
Computer vision approaches that are scalable to big data
Methods dealing with incomplete-, weak- or noisy annotation of training examples
Data driven and exploratory models for image segmentation and quantitative description
Learning approaches for registration, calibration and related image transforms
Anatomical structure localization through object recognition and categorization
Developing 3D image descriptors and interest points for object localization
Generative models of 3D image scenes relying on, or complementing, population atlases of anatomy or function
Features and algorithms dealing with image acquisition variations, such as CT scan plan or MR pulse sequence variations, with/without contrast agents
We also encourage submissions on applications of these technologies, for example:
Semantic anatomy parsing, semantic navigation and visualization
Applications of web-driven techniques to structure medical data sets
Image indexing, data organization, data harvesting