Direkt zum Inhalt springen
login.png Login    |
de | en
MyTUM-Portal
Technical University of Munich

Technical University of Munich

Sitemap > Bulletin Board > Diplomarbeiten, Bachelor- und Masterarbeiten > Master’s thesis: AI based Cochlear Implant Insertion Depth Estimation
up   Back to  News Board    previous   Browse in News  next    

Master’s thesis: AI based Cochlear Implant Insertion Depth Estimation

19.09.2024, Diplomarbeiten, Bachelor- und Masterarbeiten

Cochlear implants (CIs) are effective neuroprostheses for patients with hearing loss. Knowing the position of CI electrodes can improve the hearing outcome for the patient. In this project, you will implement and test different deep learning techniques in an explorative dataset to estimate cochlear implant electrode insertion depth based on CT scans and impedance recordings from the cochlear implant.

Background

Cochlear implants (CIs) are effective neuroprostheses for patients with hearing loss. Knowing the position of CI electrodes can improve the hearing outcome for the patient. While postoperative radiographs like computed tomography (CT) accurately determine position, they are costly and expose patients to radiation. To address these concerns, an alternative technique without radiation exposure is required in clinical routine. CIs possess impedance telemetry capabilities, providing data on electrode contacts and allowing insights into intracochlear positions. However, existing methods fail to capture the complex relationships between impedance measurements and CT images. Deep neural networks offer a promising solution to overcome this limitation.

Aim

In this project, you will implement and test different deep learning techniques in an explorative dataset to estimate cochlear implant electrode insertion depth based on CT scans and impedance recordings from the cochlear implant.

Your Tasks

  • Basic research (10%): Literature research is conducted on existing work for the application of deep learning in the field of cochlear implantation.
  • Algorithm implementation and experiments (70%): Based on the literature research and your ideas, you will implement suitable neural networks to estimate electrode insertion depth (e.g., supervised autoencoders, CNN). Training data consists of about 100 pre- and postoperative CT scans of the temporal bone, with labels of the electrodes and cochlea, and impedance recordings from the implants.
  • Results analysis (20%): Analysis of regression results and comparison with benchmark statistical machine learning methods (e.g., XGBoost, Support Vector Regression).

Your Profile

Master’s student in the field of biomedical engineering, electrical engineering, computer science or a similar area
Basic Python programming knowledge (PyTorch as a bonus)
Strong motivation and scientific curiosity

We Offer

  • Opportunity to engage in innovative clinical research as part of an interdisciplinary team
  • Collaboration with experts from the Bern University Hospital, Switzerland
  • Participation in a young, welcoming and interdisciplinary research group
  • Continuous supervision and mentorship on site for the whole duration of the project
  • Workspace at the Klinikum rechts der Isar at Max-Weber-Platz with good accessibility by public transportation

Application

If you’re interested in the topic, don’t hesitate to send us an email with your application documents (e.g., CV and transcript of records).

Prof. Dr. Wilhelm Wimmer Prof. Dr. Björn Schuller Stephan Schraivogel
Professor of Experimental Audiology Chair of Health Informatics PhD Candidate
wilhelm.wimmer@tum.de schuller@tum.de stephan.schraivogel@unibe.ch
+49 89 4140 1134

Experimental Audiology Lab (exalab)

Department of Otorhinolaryngology
Klinikum rechts der Isar
Trogerstraße 32, 81675 Munich
www.exa-lab.org

Kontakt: wilhelm.wimmer@tum.de

More Information

http://www.exa-lab.org

CI_AI Master’s thesis: AI based Cochlear Implant Insertion Depth Estimation, (Type: application/pdf, Size: 401.3 kB) Save attachment