A5058226952- Data Quality and Management
- Research Data Management Practices
- Scientific Computing and Data Management
- Privacy-Preserving Technologies in Data
- Cutaneous Melanoma Detection and Management
- AI in cancer detection
- Data Mining Algorithms and Applications
- Big Data and Business Intelligence
- Distributed systems and fault tolerance
- Legal, Health, Environmental and COVID-19 Challenges
- Nonmelanoma Skin Cancer Studies
- Digitalization, Law, and Regulation
RWTH Aachen University
2022-2023
Fraunhofer Institute for Applied Information Technology
2021-2023
The constant upward movement of data-driven medicine as a valuable option to enhance daily clinical practice has brought new challenges for data analysts get access but sensitive due privacy considerations. One solution most these are Distributed Analytics (DA) infrastructures, which technologies fostering collaborations between healthcare institutions by establishing privacy-preserving network sharing. However, in order participate such network, lot technical and administrative...
In recent years, implementations enabling Distributed Analytics (DA) have gained considerable attention due to their ability perform complex analysis tasks on decentralised data by bringing the data. These concepts propose privacy-enhancing alternatives centralisation approaches, which restricted applicability in case of sensitive ethical, legal or social aspects. Nevertheless, immanent problem DA-enabling architectures is black-box-alike behaviour highly distributed components originating...
The exponential growth in data production has led to increasing demand for high-quality data-driven services. Additionally, the benefits of analysis are vast and have significantly propelled research many fields. Data sharing scientific advancement, as it promotes transparency, collaboration, accelerates aids making informed decisions. European strategy aims create a single market that ensures Europe's global competitiveness sovereignty. Common Spaces ensure from different sources available...
The principles of data spaces for sovereign exchange across trusted organizations have so far mainly been adopted in business-to-business settings, and recently scaled to cloud environments. Meanwhile, research established distributed infrastructures, respecting the principle that must be FAIR, i.e., findable, accessible, interoperable reusable. For mutual benefit these two communities, FAIR Data Spaces project aims connect them towards vision a common, cloud-based space industry research....
Skin cancer is the most common type. Usually, patients with suspicion of are treated by doctors without any aided visual inspection. At this point, dermoscopy has become a suitable tool to support physicians in their decision-making. However, clinicians need years expertise classify possibly malicious skin lesions correctly. Therefore, research applied image processing and analysis tools improve treatment process. In order perform train model on dermoscopic images data needs be centralized....
With the generation of personal and medical data at several locations, science faces unique challenges when working on distributed datasets. Growing protection requirements in recent years drastically limit use personally identifiable information. Distributed analysis aims to provide solutions for securely highly sensitive while minimizing risk information leaks, which would not be possible same degree a centralized approach. A novel concept this field is Personal Health Train (PHT),...
Data privacy and ownership are significant in social data science, raising legal ethical concerns. Sharing analyzing is difficult when different parties own parts of it. An approach to this challenge apply de-identification or anonymization techniques the before collecting it for analysis. However, can reduce utility increase risk re-identification. To address these limitations, we present PADME-SoSci, a distributed analytics tool that federates model implementation training. PADME-SoSci...
Data privacy and ownership are significant in social data science, raising legal ethical concerns. Sharing analyzing is difficult when different parties own parts of it. An approach to this challenge apply de-identification or anonymization techniques the before collecting it for analysis. However, can reduce utility increase risk re-identification. To address these limitations, we present PADME, a distributed analytics tool that federates model implementation training. PADME uses federated...