The MICCAI Conference annual brings together world-leading scientists, engineers, and clinicians from a wide range of disciplines associated with medical imaging and computer assisted surgery. The 15th annual MICCAI Conference will be held October 1 through October 5 in Nice, France.
MICCAI showcases the depth and breadth of the impact of our research and software toolkits in diverse application areas: computer-aided diagnosis of diseases, robotics for surgical procedures, patient-specific treatment planing, informatics and population modeling, and the exploration of new algorithms for image segmentation and registration. It is also a time for us to meet with collaborators, old and new, to discuss emerging opportunities and ongoing projects. We also have found MICCAI to be an outstanding venue for discovering future Kitware employees.
- Kitware is a bronze-level sponsor
- Kitware is also proud to again sponsor the MICCAI Young Scientist Publication Impact Award.
- This annual award recognizes a MICCAI publication from the past five years, made by a young scientist, that has subsequently had a significant impact on the field.
- Roland Kwitt will give an oral presentation on his paper “Recognition in Ultrasound Videos: Where Am I?” at 11:30am, Thursday, October 4: Oral Session 6: Image Acquisition, Segmentation and Registration.
- Abstract: While many developed western countries have immediate access to expensive imaging modalities, such as MRI or CT, rural parts of the world or developing countries usually do not possess that kind of advanced imaging equipment. For that reason, ultrasound (US) imaging has become increasingly popular in these areas, especially with the emergence of portable probes that can be hooked-up to mobile phones or tablet PCs. Since experienced radiologists are usually unavailable as well, it has been proposed to have supporting staff perform ultrasound examinations. This can be problematic, though, for one particular reason: Locating an organ or an area of interest is hard for inexperienced personnel, mainly due to variation in human anatomy and high noise levels in ultrasound images. In this talk, we discuss an approach to guide the localization of interesting regions by modeling appearance changes in ultrasound video sequences by a generative model and comparing that model to an atlas of previously acquired key locations. We argue that the change of appearance of a particular anatomical structure as we move the ultrasound probe is more distinctive than a single, still image of the same area. Technically, we draw on recent advances in action recognition literature and model the appearance changes as a non- linear dynamical system. Similarity among US video sequences is then defined as similarity in the parameter space of that model. We present several experiments on US sequences acquired on a handmade noodle-phantom and a 3-D abdominal phantom. We further show preliminary results on the impact of anatomical variations, simulated by (non-linear) spatial distortion of the video material.
- Kitware is participating in the student career event on Monday October 1st from 6:00-7:30pm. Come and meet with
- Danielle Pace: active in our surgical guidance, orthopedics, and advanced registration work
- Roland Kwitt: hired at MICCAI 2011 and active in our video processing and scene understanding work
- Andinet Enquobahrie: leader of the surgical guidance and simulation team at Kitware
- Stephen Aylward: leader of Kitware’s office in North Carolina, with research in vascular image analysis
- Stephen Aylward has been nominated for the MICCAI Board of Directors. If you are a MICCAI member, please cast your vote for him!
- Andinet Enquobahrie is a co-chair of the Fifth International Workshop on Systems and Architectures for Computer Assisted Interventions (SACAI). He will also present Kitware’s da Vinci Robot AR work with Johns Hopkins University, titled “Robot assisted prostate surgery using augmented reality with deformable models.”
- Danielle Pace is on the program committees for the “MICCAI 2012 Workshop on Clinical Image-based Procedures: From Planning to Intervention” and the “Workshop on Computational and Clinical Applications in Abdominal Imaging.”
- Kitware’s Midas Platform is being used to host the BRATS 2012: Multimodal Brain Tumor Segmentation Challenge data. Participants are able to submit results directly to Midas and have them automatically scored for the challenge. For more information, see the BRATS challenge site, or visit the Midas community to download the data.