Johann Berger

Johann Berger

Auto-generated profile, based on publicly available information

Johann Berger

Innovation Center Computer Assisted Surgery, University Leipzig, Leipzig , Germany

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2019 in International Journal of Computer Assisted Radiology and Surgery
Verified
Journal Article
Closed access
PDF file
JBJohann Berger
Johann Berger
MRMax Rockstroh
Max Rockstroh
ESErik Schreiber
Erik Schreiber
YYYukishige Yoshida
Yukishige Yoshida
JOJun Okamoto
Jun Okamoto
TNThomas Neumuth
Thomas Neumuth

1 October 2021 in Current Directions in Biomedical Engineering
Verified
Journal Article
Open access
PDF file
RBRichard Bieck
Richard Bieck
DBDavid Baur
David Baur
JBJohann Berger
Johann Berger
TSTim Stelzner
Tim Stelzner
AVAnna Völker
Anna Völker
TNThomas Neumuth
Thomas Neumuth
We introduce a system that allows the immediate identification and inspection of fat and muscle structures around the lumbar spine as a means of orthopaedic diagnostics before surgical treatment. The system comprises a backend component that accepts MRI data from a web-based interactive frontend as REST requests. The MRI data is passed through a U-net model, fine-tuned on lumbar MRI images, to generate segmentation masks of fat and muscle areas. The result is sent back to the frontend that functions as an inspection tool. For the model training, 4000 MRI images from 108 patients were used in a k-fold cross-validation study with k = 10. The model training was performed over 25-30 epochs. We applied shift, scale, and rotation operations as well as elastic deformation and distortion functions for image augmentation and a combined objective function using Dice and Focal loss. The trained models reached a mean dice score of 0.83 and 0.52 and a mean area error tissue of 0.1 and 0.3 for muscle and fat tissue, respectively. The interactive webbased frontend as an inspection tool was evaluated by clinicians to be suitable for the exploration of patient data as well as the assessment of segmentation results. We developed a system that uses semantic segmentation to identify fat and muscle tissue areas in MRI images of the lumbar spine. Further improvements should focus on the segmentation accuracy of fat tissue, as it is a determining factor in surgical decisionmaking. To our knowledge, this is the first system that automatically provides semantic information of the respective lumbar tissues.