Medical Image Computing and Computer Assisted Intervention (MICCAI) 2014 is the premier conference in the medical computing field, highlighting topics such as medical image computing, computer-assisted intervention, guidance systems and robotics, visualization and virtual reality, computer-aided diagnosis, bioscience and biology applications, specific imaging systems, and new imaging applications. Kitware will actively participate in MICCAI 2014, as well as the 7th Annual Image-Guided Therapy workshop, which will be held in conjunction with the conference.

Kitware’s participation in MICCAI 2014 includes:

  • Co-authoring a paper that will be presented on atlas-based anaysis of pathologies
  • Presenting work on FEM-based biomechanical anaysis
  • Attending the MICCAI Board meeting and the meeting for associate editors of IEEE Transactions on Medical Imaging
  • Attending student career event
  • Sponsoring the conference
  • Sponsoring the Young Scientist Publication Impact Award for a third year
  • Presenting a talk on ‘Building image-guidance systems from open-source components’
  • Serving on an academia and industry panel

Descriptions of the talks, presentations, and papers are provided below. To learn how Kitware can help you meet your current medical computing research challenges, please contact (518) 371-3971 or kitware@kitware.com.


‘Low-Rank to the Rescue – Atlas-based Analyses in the Presence of Pathologies’

By Xiaoxiao Liu, Marc Niethammer, Roland Kwitt, Matthew McCormick, and Stephen Aylward

Absract

Low-rank image decomposition has the potential to address a broad range of challenges that routinely occur in clinical practice. Its novelty and utility in the context of atlas-based analysis stems from its ability to handle images containing large pathologies and large deformations. Potential applications include atlas-based tissue segmentation and unbiased atlas building from data containing pathologies. In this paper we present atlas-based tissue segmentation of MRI from patients with large pathologies. Speci cally, a healthy brain atlas is registered with the low-rank components from the input MRIs, the low-rank components are then re-computed based on those registrations, and the process is then iteratively repeated. Preliminary evaluations are conducted using the brain tumor segmentation challenge data (BRATS ’12).

“Finite element based biomechanical analysis of cranial shapes for craniosynostosis surgical correction”
By Ricardo Ortiz, Andy Bauer, Andinet Enquobahrie, Nabile Safdar, Gary Rogers, and Marius Linguraru

Ricardo will present this work during the the 7th Annual Image-Guided Therapy workshop. The workshop will take place from September 18 to September 19, 2014.

Abstract

Currently, the decision of performing surgical correction for pediatric patients with craniosynostosis is typically based on subjective visual assessments. These decisions have a major impact on the management of these young patients requiring surgical intervention. In this paper. we present our preliminary work on biomechanical finite element modeling based on the physical properties of the bone. The computed shape and stresses can then be used to evaluate and compare individual bone correction plans without carrying out the actual surgeries. Our overall objective is to design, develop, and validate a virtual surgery system for optimal treatment planning of craniosynostosis correction.

‘Building image-guidance systems from open-source components’ Tutorial
Stephen Aylward is an invited speaker for this tutorial, which will take place on Thursday, September 18, 2014, from 8:30 am to 12:30 pm.

Abstract
Do you want the software from your students to inter-operate and to benefit your lab long after they have graduated? Do you want your software to have academic and/or commercial impact beyond your
dissertation? Do you want to complete your research faster and with fewer errors? Open-source software and high-quality software practices may be the answer.

Open-source software has matured and become commonplace in medical research and applications. The maturation and acceptance of open-source software has arisen from the widespread use of
high-quality software practices in projects ranging from a graduate student’s experiments to massive community-supported efforts.

This presentation will explore the impact, challenges, and opportunities of open-source software in medicine. Topics covered will include licensing terms, easy-to-use software development processes, and the practice of open science.

MICCAI Academia & Industry Event

Stephen Aylward will serve as one of five experts at this panel discussion, which will take place on September 15, 2014, from 5:00 pm to 7:00 pm. Roland Kwitt will participate as an invited guest as a former Kitware employees in round-table discussions with students following the panel.

Physical Event