[Data processing in secure data processing environments using the example of MRI brain scans-a simultaneous plea for a legal provision for data processing for scientific research purposes]. / Datenverarbeitung in sicheren Verarbeitungsumgebungen am Beispiel von MRT-Gehirnscans ­ zugleich ein Plädoyer für eine rechtssichere Forschungsgrundlage.

The use of data for medical scientific research offers great potential for society as a whole, as the evaluation of large volumes of data with machine learning methods can result in new research approaches as well as new methods of diagnostics or treatment. However, the use of such data often fails due to high prerequisites or unclear requirements of data protection law.Processing of radiology data, such as MRI brain scans, is tied to specific risks for data subjects. This complicates the processing of such data for research purposes. Data trustees can help to reduce these risks through offering independent anonymization and pseudonymization services as well as secure processing environments in which health data is stored only for the time required for processing and analysis and is subsequently deleted.Thus, the use of data trustees can help to comply with data protection law, with risk-reduction being considered in favor of processing in decisions weighing the interests for and against data processing as necessary to comply with Art. 9 Para. 2 lit. j, Art. 89 Para 1 of the General Data Protection Regulation (GPDR) in conjunction with national law, or when assessing the compatibility of the secondary purpose of the processing with the purpose of collection. In this respect, the use of data trust models can contribute to the reduction of hurdles for the data processing of health data for scientific research purposes.

An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II.

Automated detection of lesions using artificial intelligence creates new standards in medical imaging. For people with epilepsy, automated detection of focal cortical dysplasias (FCDs) is widely used because subtle FCDs often escape conventional neuroradiological diagnosis. Accurate recognition of FCDs, however, is of outstanding importance for affected people, as surgical resection of the dysplastic cortex is associated with a high chance of postsurgical seizure freedom. Here, we make publicly available a dataset of 85 people affected by epilepsy due to FCD type II and 85 healthy control persons. We publish 3D-T1 and 3D-FLAIR, manually labeled regions of interest, and carefully selected clinical features. The open presurgery MRI dataset may be used to validate existing automated algorithms of FCD detection as well as to create new approaches. Most importantly, it will enable comparability of already existing approaches and support a more widespread use of automated lesion detection tools.