SAFE AI ENGINEERING
AI engineering ensures safety of AI components for autonomous, connected driving
OKTI
AI-based software detects and corrects motion artifacts in OCT images.
Start: 03.2025
End: 10.2025
Uncontrolled eye movements can impair the quality of optical coherence tomography (OCT) images, making diagnosis more difficult. Currently, expensive eye-tracking hardware is required to counteract this issue. The OKTI project is developing software that can detect and efficiently correct motion artefacts without the need for additional hardware.
Millions of people worldwide are affected by eye diseases such as age-related macular degeneration (AMD), glaucoma and diabetic retinopathy. More precise and less expensive OCT systems can significantly improve diagnosis and treatment. The OKTI project (correction of motion artefacts in optical coherence tomography images using AI) enables the precise, hardware-independent correction of eye movement artefacts in sensitive applications. The software-based solution is designed for OCT manufacturers, ophthalmologists, and clinics. It saves hardware costs in the manufacture of OCT devices and opens up potential for new products and markets. OCT manufacturers can thus strengthen their market position, while ophthalmologists benefit from improved image quality, leading to more accurate diagnoses. The plan is to use deep learning methods to detect optical flow in OCT data. For this purpose, a synthetic data set with artificially generated artefacts will be used. Real data will also be collected to validate and optimize the model.
Role of the FZI
- Assumption of operational project management, including control, progress monitoring, and quality assurance
- Conducting data collection and preparation, and providing synthetic training data
- Developing, implementing, and validating AI algorithms for artifact correction in OCT image data, including model selection, training, and optimization using modern methods such as transfer learning and data augmentation
- Integration of all developed components into an overall system, compatibility testing, and execution of tests in realistic application scenarios
- Preparation for integration of the software solution into existing systems
Contact
Julia Konle
Staff
Division: Embedded Systems and Sensors Engineering
- +49 721 9654-766
- julia.konle@fzi.de
- Headquarters Karlsruhe
Research Focus
Applied Artificial Intelligence
In this research focus, the FZI concentrates on practical research into the key technology of Artificial Intelligence (AI). Innovative AI solutions are developed and transferred to application areas such as mobility, robotics, healthcare technology, logistics, production, and supply and disposal on behalf of our partners and customers.
Funding notice:
The OKTI project is funded by the Baden-Württemberg Ministry of Economic Affairs, Labour and Tourism.
More projects
SouveMed
Data trustee model protects use of individual health data in research
OKTI
AI-based software detects and corrects motion artifacts in OCT images.
BeACTIVE
More exercise in everyday life: Self-learning real-time system recognizes behavior patterns and recommends customized activities
RISE
AI assistant serves as first point of contact for legal questions
MAD Urban
AI engineering empowering security reasoning throughout the entire lifecycle of an AI function
SDI4ECom
Secure and self-determined digital identities in e-commerce
CaMinoBW
Co-design for application-specific microelectronics with innovative chiplets in Baden-Württemberg
regioKArgoTramTrain
Jointly moving people and goods
PathoBot
Stopping pathogen transmission in hospitals quickly, reliably, and comprehensively using AI.