There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
Principal Investigator | |
Principal Investigator's Name: | Marco Duering |
Institution: | Medical Image Analysis Center |
Department: | Research |
Country: | |
Proposed Analysis: | Deep learning-based brain segmentation methods are of increasing interest for clinical routine use in memory clinics to quantify structural/morphological brain changes for diagnostic or monitoring purposes. Deep learning-based algorithms can deliver high-quality results in short time, making quantitative results available to the radiologist directly after the scanning. To obtain a clearance for clinical routine use (either by FDA or according to the EU Medical Device Regulation) algorithms must be (among other aspects) sufficiently validated in terms of clinical and technical aspects. We will apply deep learning-based brain segmentation models to segment the whole brain, regions-of-interest or lesions. Segmentation quality will be benchmarked against goldstandard methods or quality controlled by trained raters. The detected change over time (e.g. expressed as percent volume change) will be estimated using different segmentation methods and used to estimated sample sizes for hypothetical clinical trials for each segmentation method. |
Additional Investigators | |
Investigator's Name: | Benno Gesierich |
Proposed Analysis: | Takes part in main project described above |
Investigator's Name: | Lukas Pirpamer |
Proposed Analysis: | Takes part in main project described above |