Semi-automatic tract dissection for tissue analysis and identification of microstructural white matter biomarkers of therapy outcome in catatonia

• Applicants: Professor Dr. Dusan Hirjak; Dr. Peter Neher
• Subject Area: Medical Informatics and Medical Bioinformatics
• Term: since 2021
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 470518062

Tract-specific analysis of brain tissue properties using longitudinal diffusion-weighted magnetic resonance imaging (dMRI) based tractometry enables noninvasive characterization of pathological changes and facilitates research of the joint development of psychiatric disorders as well as the relation of their clinical manifestations to distinct anatomical structures. Particularly for less prominent fiber bundles, tract-specific analysis involves the manual extraction of the tract of interest from a huge whole brain tractography result (tractogram), which is a time-consuming and difficult to reproduce task. Therefore, this interdisciplinary project has two main objectives: First, we will facilitate this process by developing and implementing a new method for semi-automatic fiber tract delineation using active learning. By training supportive machine learning algorithms on the fly that are custom tailored to the respective analysis pipeline used to obtain the tractogram as well as to the tract of interest, we plan to streamline and speed up this tedious and error-prone task while at the same time increasing reproducibility and robustness of the extraction process. Second, we will apply and validate the developed method in a longitudinal analysis of 100 patients with catatonia according to ICD-11. The clinical goal is to develop robust neuroimaging biomarkers of therapy outcome based on white matter tracts underlying catatonia as well as an in-depth understanding of (patho)physiologically-relevant mechanisms that are essential for advancing precision-medicine–informed treatment options for catatonia.

• DFG Programme: Research Grants