Computational Imaging Researcher

Kitware achieves CMMC Level 2 assessment, reinforcing commitment to secure software development. October 1, 2026 This certification demonstrates Kitware's commitment to protecting Controlled Unclassified Information (CUI) and supporting the cybersecurity requirements of the Defense Industrial Base. Clifton Park, NY - October 1, 2026 - Kitware, a leader in software R&D and advanced AI, has achieved CMMC Level 2 (C3PAO) certification, reinforcing the company's commitment to protecting Controlled Unclassified Information (CUI) and supporting the cybersecurity requirements of the U.S. Department of War (DoW). The CMMC Program validates compliance with rigorous cybersecurity requirements for organizations that develop technologies or handle sensitive information on behalf of the Department of War. As cyber threats targeting defense agencies continue to grow in both frequency and sophistication, CMMC provides assurance that contractors have implemented and maintain the security controls necessary to safeguard Controlled Unclassified Information. Kitware officially received its CMMC Level 2 certification on June 24, 2026, following a comprehensive independent assessment by a C3PAO. At the time, only about 2% of eligible organizations had successfully achieved CMMC Level 2 (C3PAO) certification, making Kitware part of a select group of organizations recognized for meeting the DoW's rigorous cybersecurity requirements. "Achieving CMMC Level 2 certification reflects years of investment in secure processes and protecting sensitive information for our government customers," said Lisa Avila, CEO and co-founder of Kitware. "For a software R&D company of our size, this accomplishment demonstrates that we can deliver innovative software solutions while meeting some of the highest cybersecurity standards required by the DoW." Although the CMMC Phase 2 (C3PAO) certification requirement has been temporarily paused, securely managing CUI remains a critical factor for organizations supporting DoW programs. By proactively achieving certification, Kitware demonstrates both the maturity of its cybersecurity program and its readiness to support customers with demanding security and compliance requirements. About kitware. Kitware advances science and technology to make a meaningful difference in the world. CMake Feabhas Limited deliver high-impact software solutions built on open source foundations, combining deep technical expertise with a collaborative, people-first approach. Trusted by commercial, government, and academic organizations, Kitware partners closely with customers to understand their goals and integrate robust, sustainable technology into real-world scenarios. CMake Feabhas Limited build solutions that endure by prioritizing transparency, long-term value, and positive impact. Founded in 1998, Kitware is 100% employee-owned. Visit CMake Feabhas Limited at kitware.com or on Twitter, LinkedIn, and YouTube.

Kitware and UNC collaborate on robotic stroke care project with ARPA-H funding. UNC School of Medicine announced on Sep. 3 a collaboration with Kitware and several universities to advance robotic stroke care, supported by up to $17.5 million in funding from the Advanced Research Projects Agency for Health (ARPA-H). The initiative, called the Testbed for Autonomous Interventions and Robotics (AIR), aims to develop an open-source virtual testing platform for robotic interventions in endovascular stroke treatment. The project brings together researchers from Kitware, UNC School of Medicine, Johns Hopkins University, University of North Carolina, University of Pittsburgh, Florida State University, and Lightside Surgical, Inc. The funding will be used to create a simulation environment designed to test and evaluate robotic algorithms that assist with minimally invasive procedures inside the brain's blood vessels. Yueh Lee, MD, PhD, professor of radiology at UNC School of Medicine and clinical lead for the project, said this simulation software is expected to accelerate development of robotic tools that could improve access and expedite care for patients experiencing strokes or other brain blood vessel disorders. "That's one of the reasons we are excited to help develop open-source software tools to reduce barriers to entry," said Lee. "More importantly, this will help accelerate the development of these tools, which could substantially expand access to stroke thrombectomy for patients. Imagine a robot that could perform the procedure at any hospital without requiring the patient to be transferred to a major medical center." James Ho, MD, assistant professor of neurology and director of UNC Medical Center's Comprehensive Stroke Center as well as co-investigator on the project, said: "A stroke occurs when there is a blockage of the blood vessels in the brain, usually from a blood clot. The longer that blood clot stays in place, the more brain tissue loses oxygen and nutrients it needs to survive. It's estimated that every minute during a stroke nearly 2 million brain cells die... This has made a huge impact on patients." Ho added that timely access remains challenging because only highly trained specialists can perform these interventions: "This project has the potential to enhance a Neurointerventionalist's ability to take care of patients regardless of where they had their stroke." The team will work with faculty at other institutions such as University of Pittsburgh who will contribute data supporting digital intervention testing. Lee said this effort builds upon strong clinical care provided by UNC Hospitals Comprehensive Stroke Center as well as its commitment toward high-quality imaging and neurovascular research. A statement accompanying the announcement noted: "This research is funded in part by ARPA-H... The views and conclusions contained in this document are those of the authors and should not be interpreted as representing official policies...of the U.S. Government."

BlueTIDE 2026. August 13, 2026 BlueTIDE 2026 | august 27, 2026 | Newport, rhode island. Kitware is excited to be part of this year's BlueTIDE 2026 event. Hosted by Polaris Tech Bridge in collaboration with the U.S. Navy and the Naval Undersea Warfare Center Division Newport, BlueTIDE is an annual technology demonstration event. It brings together government, industry, academia, and investors to accelerate the development of maritime and dual-use technologies. At BlueTIDE, Kitware'll highlight its research in underwater acoustic analysis, including technologies for passive acoustic monitoring and underwater acoustic target recognition. Its work addresses challenges in underwater acoustic machine learning, from developing foundation models with limited labeled data to improving model evaluation through benchmark datasets and open source software for acoustic data analysis. Learning from unlabeled acoustic data. As part of the Maritime Acoustic Recognition and Identification with Novel Algorithms (MARINA) project, funded by DARPA, Kitware is developing AI foundation models for underwater acoustic environments. The underwater domain presents several challenges for machine learning, including complex propagation effects, expensive data collection, and limited labeled datasets. To address these challenges, Kitware applies hierarchical pretraining. The approach begins with out-of-domain data and progresses through increasingly relevant acoustic domains. By leveraging publicly available unlabeled acoustic data, hierarchical pretraining supports few-shot learning for underwater acoustic classification. The resulting feature representations support downstream tasks including semantic search and underwater sound classification. Kitware develops and optimizes foundation models for different computing platforms. Model distillation and pruning create smaller models that meet size, weight, and power requirements for deployment on resource-constrained underwater vehicles. The work also expands Kitware's open source software capabilities for acoustic data analysis. These capabilities include sound classification using established taxonomies, semantic search, automated labeling, and visualization for underwater acoustic data. In addition to developing foundation models for underwater acoustic analysis, Kitware is advancing benchmark datasets that reduce data leakage and support more reliable evaluation of underwater acoustic machine learning models. Reducing data leakage in model evaluation. UniqueShip is a benchmark dataset for underwater acoustic target recognition that is planned for open release and will be presented at the upcoming OCEANS 2026 conference in Monterey, CA. It includes more than 2,474 hours of audio from 4,222 unique vessel sources across 11 vessel classes and a background class. Existing ship-classification datasets can contain data leakage when recordings from the same vessel appear in both the training and test sets. This can produce falsely optimistic test results and significant performance declines during real-world deployment. UniqueShip minimizes this leakage by separating individual vessels, identified by Maritime Mobile Service Identity, across data partitions. It also groups ambient or noise-dominated recordings by calendar date and provides explicit partitions that follow these constraints. The reported results demonstrate the effect of leakage on model evaluation. The highest class-averaged accuracy was 66.8% without leakage and 80.5% when leakage was introduced. Across the evaluated architectures and input representations, data leakage increased class-averaged accuracy by 9% to 14%. These findings show that leakage can distort estimates of model generalizability. Connect with its team. If you would like to schedule a demo of its technology or speak with its technical developers, please contact its team.