UNIVERSITY DEPARTMENT OF NEUROLOGY

Core research areas

The MedDigit team pursues the goal of a continuous registration and quantitative analysis of brain structure and function of all patients with neurological and neuropsychiatric disorders in Saxony-Anhalt. The team develops a fully automated digital system for processing clinical brain data from the Department of Neurology and external caregivers (MRI/MEG/EEG) as well as for deriving biomarkers for defined neurological disorders. The system comprises components for ensuring comparability of data that were acquired in a non-standardized way, for the automated digital analysis and enhancement of data quality, the automated feature extraction and data classification as well as the determination of clinically relevant, quantitative biomarkers.

Comparable results utilizing non-standardized data acquisition

Standardized acquisition of MRI/EEG/MEG data

→ Definition of minimum requirements 

 

Variability of data and data acquisition

→ Definition of metrics

Automated digital analysis of data quality

Focus on definition of:

  • Quality criteria
  • Target area
  • Control mechanisms
  • Control metrics

 

Goal:

  • Compilation of quality reports
Automated enhancement of data quality

Focus on image data:

  • Imputation/Synthesis missing sequences
  • Denoising
  • Correction of movement artifacts
Automated feature extraction and data classification

Focus on image data: 

  • Robust, automated extraction of quantitative features from Big Image Data
  • Classification of data based on:
    • extracted features
    • classified training samples without previous feature extraction (Deep Learning)

 

Goal:

  • Assistance in diagnose and therapy
Determination of clinically relevant, quantitative biomarkers

Focus: 

  • Radiomics of image features
  • Integrated Visual Analytics of patient data and of image features

 

Goal: 

  • Identification of disease/symptom-relevant biomarkers and computation of risk factors and factor interactions
  • Identification of different phenotypes in patient cohorts

Last Modification: 08.09.2022 - Contact Person:

Sie können eine Nachricht versenden an: Webmaster
Sicherheitsabfrage:
Captcha
 
Lösung: