Computer Vision Approaches to Medical Image Analysis

Medical imaging and medical image analysis are developing rapidly. While m- ical imaging has already become a standard of modern medical care, medical image analysis is still mostly performed visually and qualitatively. The ev- increasing volume of acquired data makes it impossible to utilize them in full. Equally important, the visual approaches to medical image analysis are known to su?er from a lack of reproducibility. A signi?cant researche?ort is devoted to developing algorithms for processing the wealth of data available and extracting the relevant information in a computerized and quantitative fashion. Medical imaging and image analysis are interdisciplinary areas combining electrical, computer, and biomedical engineering; computer science; mathem- ics; physics; statistics; biology; medicine; and other ?elds. Medical imaging and computer vision, interestingly enough, have developed and continue developing somewhat independently. Nevertheless, bringing them together promises to b- e?t both of these ?elds. This was the second time that a satellite workshop,solely devoted to medical image analysis issues, was held in conjunction with the European Conference on Computer Vision (ECCV), and we are optimistic that this will become a tradition at ECCV. We received 38 full-length paper submissions to the second Computer Vision Approaches to Medical Image Analysis (CVAMIA) Workshop, out of which 10 were accepted for oral and 11 for poster presentation after a rigorous peer-review process. In addition, the workshop included three invited talks. The ?rst was given by Maryellen Giger from the University of Chicago, USA titled Multi-Modality Breast CADx.

Inhalt
Clinical Applications.- Melanoma Recognition Using Representative and Discriminative Kernel Classifiers.- Detection of Connective Tissue Disorders from 3D Aortic MR Images Using Independent Component Analysis.- Comparing Ensembles of Learners: Detecting Prostate Cancer from High Resolution MRI.- Accurate Measurement of Cartilage Morphology Using a 3D Laser Scanner.- Image Registration.- Quantification of Growth and Motion Using Non-rigid Registration.- Image Registration Accuracy Estimation Without Ground Truth Using Bootstrap.- SIFT and Shape Context for Feature-Based Nonlinear Registration of Thoracic CT Images.- Consistent and Elastic Registration of Histological Sections Using Vector-Spline Regularization.- Image Segmentation and Analysis.- Comparative Analysis of Kernel Methods for Statistical Shape Learning.- Segmentation of Dynamic Emission Tomography Data in Projection Space.- A Framework for Unsupervised Segmentation of Multi-modal Medical Images.- Poster Session.- An Integrated Algorithm for MRI Brain Images Segmentation.- Spatial Intensity Correction of Fluorescent Confocal Laser Scanning Microscope Images.- Quasi-conformal Flat Representation of Triangulated Surfaces for Computerized Tomography.- Bony Structure Suppression in Chest Radiographs.- A Minimally-Interactive Watershed Algorithm Designed for Efficient CTA Bone Removal.- Automatic Reconstruction of Dendrite Morphology from Optical Section Stacks.- Modeling the Activity Pattern of the Constellation of Cardiac Chambers in Echocardiogram Videos.- A Study on the Influence of Image Dynamics and Noise on the JPEG 2000 Compression Performance for Medical Images.- Fast Segmentation of the Mitral Valve Leaflet in Echocardiography.- Three Dimensional Tissue Classifications in MR Brain Images.- 3-D UltrasoundProbe Calibration for Computer-Guided Diagnosis and Therapy.