Medical Computing

Kitware’s Medical Computing team is a leader in the creation, integration, and support of state-of-the-art medical data visualization and analysis technology. We leverage open-source software to develop customized solutions for research and clinical endeavors. We work collaboratively to provide cutting-edge solutions in every aspect of patient management and care and for every step of medical product development: from basic research, to pre-clinical trials, and to regulatory-approved application development.

We have participated in some of the largest and most successful medical software development projects around the world. Kitware began with the development of the Visualization Toolkit (VTK) that is used in commercial surgical navigation systems as well as a multitude of imaging applications such as Osirix. We were lead architects in the design and development of the Insight Toolkit (ITK), and we continue to maintain the project today. We are the primary developers of the 3D Slicer application with the National Alliance of Medical Image Computing (NA-MIC). Additionally, we are a founding collaborator on the Open Source Electronic Health Record Agent (OSEHRA) project that is paired with the Vista application for driving critical advances in health informatics technologies.

Complimenting our software development expertise, we are leaders in wide range of basic and applied research areas, including: surgical and biophysical simulation, computer-aided diagnosis, low-cost ultrasound systems, visualization and management for digital pathology, and numerous other domains.

What Kitware Can Do for You
Our medical computing consulting delivers all the advantages of open source, plus the vision, innovation, business risk mitigation, and support and maintenance that only a mature technology vendor can provide.
  • Rapidly create tailored medical applications that package your innovation into a user-friendly, clinically-integrative demonstration application that allows investors and customers to see its full potential.
  • Re-invigorate your existing medical software with high-quality software practices that extend and broaden its utility.
  • Provide cutting-edge data analysis, fusion, and visualization expertise, integrating the best of academia and industry.
  • Deliver state-of-the-art data analysis algorithms for your research or clinical application.
Featured Case Study:
Ultrasound Angiography for Tumor Microenvironment Quantification
Ultrasound is a relatively safe, low cost, portable, real-time imaging device. However, its images are relatively poor for detecting and diagnosing tumors. New micro-bubble contrast agents have been developed that enhance the appearance of vessels within ultrasound images. UNC has developed a new ultrasound imaging probe that is tuned for capturing contrast-enhanced images. Kitware is working with them to integrate it with a novel vascular image analysis algorithm we have developed. Together, they are able to visualize the vasculature within tumors, make measurements on those vessels, and analyze those measurements to assess the malignancy of tumors and monitor their response to treatment.
Multimedia Materials

Medical Computing Capabilities
Bioinformatics Flyer
Image Gallery
GitHub Repository

Case Studies
Traumatic Brain Injury
This NIH-funded study with UNC and USC aims to develop and validate computational image analysis methods that yield quantitative measures to characterize injury, monitor pathology evolution, inform patient prognosis and optimize patient care workflows for traumatic brain injury (TBI) patients. This project addresses the current public health need for informative TBI measures and the technical need for image analysis tools that handle large, heterogenous pathologies that cause large brain deformations. Ultimately, the technical advances being proposed may yield an improved clinical ability to monitor brain responses to trauma in an integrative, longitudinal fashion.
Longitudinal Study of Lung Cancer
Clinicians use periodic medical imaging to monitor a patient’s disease and evaluate whether a treatment is effective. However, quantitatively measuring a pathology’s change in size or rate of growth is difficult because changes in image appearance make it difficult to accurately reproduce measurements on different scans. In collaboration with UNC and RIT and with funding from the NIH, we are developing a computer algorithm that, given a patient’s medical images, can recover a pathology’s deformation over time while accounting for the impact of background deformations, which will give clinicians more accurate metrics for determining a patient’s prognosis or deciding whether a patient should be switched to a new treatment protocol.
Ultrasound Localization
The problem of localizing specific anatomic structures using ultrasound (US) video is considered. This involves automatically determining when an US probe is acquiring images of a previously defined object of interest, during the course of an US examination. Localization using US is motivated by the increased availability of portable, low-cost US probes, which inspire applications where inexperienced personnel and even first-time users acquire US data that is then sent to experts for further assessment. This process is of particular interest for routine examinations in underserved populations as well as for patient triage after natural disasters and large-scale accidents, where experts may be in short supply. The proposed localization approach is motivated by research in the area of dynamic texture analysis and leverages several recent advances in the field of activity recognition. For evaluation, we introduce an annotated and publicly available database of US video, acquired on three phantoms. Several experiments reveal the challenges of applying video analysis approaches to US images and demonstrate that good localization performance is possible with the proposed solution.

Detecting abdominal bleeding post trauma, via ultrasound The Focused Assessment with Sonography for Trauma (FAST) procedure is an ultrasound-based examination for rapidly detecting blood in the abdomen, particularly after blunt abdominal trauma, which is common, for example, with car accidents. The challenge is that the FAST procedure requires expertise and equipment which is not commonly available at level 3 and 4 trauma centers that serve rural populations. With InnerOptic and Washington University in St. Louis, we have NIH funding to develop the hardware and image analysis algorithms necessary for novice ultrasound operators to perform lifesaving FAST procedures. The proposed system will consist of a low-cost, hand-held ultrasound probe, connected to a ruggedize tablet computer, running innovative computer vision algorithms, embedded in an easy-to-follow software application.
Ultrasound Angiography for Tumor Microenvironment Quantification
Ultrasound is a relatively safe, low cost, portable, real-time imaging device; however its images are relatively poor for detecting and diagnosing tumors. New micro-bubble contrast agents have been developed that enhance the appearance of vessels within ultrasound images. UNC has developed a new ultrasound imaging probe that is tuned for capturing contrast-enhanced ultrasound images, and herein we are working with them to integrate it with a novel vascular image analysis algorithm we have developed. Together they are able to visualize the vasculature within tumors, make measurements on those vessels, and analyze those measurements to assess the malignancy of tumors and monitor their response to treatment.
3D Slicer Collaboration
Customer challenge: The National Alliance for Medical Image Computing (NA-MIC) community wanted to adopt a new software development process to ensure consistent quality across its software projects.
Kitware Solution: As a member of the NA-MIC team, Kitware assisted with the integration of our high-quality software process, which was used during the development phase of Slicer v4. The improvements during development were noticed by the technical team, and vetted by the Slicer community. Slicer version 4 has been downloaded more than all prior versions of Slicer combined, due to a dramatically improved code base. This improved code base has fewer crashes, improved test coverage, and a modern interface that is more functional with fewer lines of code.
Automated Tracking of Leukocytes
Customer challenge: Portola Pharmaceuticals required a method for analyzing the behavior of human leukocytes in blood.
Kitware solution: Kitware developed an automated technique that detects and tracks the recruitment or leukocytes, enabling ehnanced understanding of the behavior of blood without coutnless hours of manual analysis.