On the Horizon
We are constantly developing new and innovative algorithms and user experiences to empower doctors and patients. Together, Progenics and EXINI are reimagining the combination of diagnostics, treatments and information systems in cancer care to support the patient from referral to disease management and remission.
PSMA-AI is the first software in development by EXINI tailored to Progenics’ imaging agent pipeline – 1404 and DCFPyL. The imaging agents attach to a protein called Prostate-Specific Membrane Antigen (PSMA) which is overexpressed on the surface of prostate cancer cells. The agents are labeled with a radioactive molecule detectable by nuclear medicine cameras and used in conjunction with co-registered anatomical images to provide anatomical context to the functional images.
Central to PSMA-AI is the automatic and quantitative computation of assessments used to detect, localize, quantify and stage both localized and advanced prostate cancer lesions. The technology is based on deep learning and convolutional neural networks that determine a detailed anatomical context from the anatomical images. This information is combined with information from the corresponding PSMA-targeted functional image to assess cancer prevalence and growth. The performance of assessments in hybrid images on patients with prostate cancer by human experts have been statistically validated to improve when provided with the additional information retrieved with PSMA-AI1.
- K.Sjöstrand, L.Edenbrandt, N.Stambler, A.Opanowski, J.Richter, K.Gjertsson, K.Johnsson, V.Wong, J.Jensen, A.Anand: Automated Assessment of Prostatic PSMA Expression in SPECT/CT using Deep Convolutional Neural Networks-A Prospectively Planned Retrospective Analysis of Phase 3 Study MIP-1404-3301, SNMMI 2019.
If there is anything we have learned from two decades of developing and deploying AI systems in healthcare, it’s that algorithms and data must co-evolve. The quality of research, AI algorithms and ultimately the care that they support can only be as good as the data we have at our disposal.
In recognition of this, EXINI has invested heavily in a data-centric technology platform that we call CURE8. Central to this platform is high-capacity and high-performance storage of medical data. We support several different types of data with emphasis on imaging data. With high volumes of complex data comes the requirement to be able to find data using powerful search. CURE8 features customizable and scoped indexing of data on a per-project basis. To meet regulatory and clinical trial demands, detailed traceability and audit logging is available including full data versioning and tracking of all associated platform operations. On top of this, CURE8 offers all the functionality required for building secure, safe and powerful clinical applications.
- HIPAA and GDPR-compliant architecture
- Interoperability with compliant hospital equipment for seamless clinical workflows
- Granular access control
- Organization of work into projects and teams
- Advanced and project-specific query and analytics capabilities
- Optional data sharing between teams
Outside of clinical applications, CURE8 can be accessed using its own modern browser-based UI, or programmatically using our CURE8 Python SDK for high-powered and structured research.