gemeinsam einzigartig

IMT 36-2022 Bachelor or Master Thesis: Deep Learning for the prediction of Raser-MRI profiles

Organisationseinheit

Institut für Mikrostrukturtechnik (IMT)

Tätigkeitsbeschreibung

Nuclear magnetic resonance (NMR) and magnetic resonance imaging (MRI) have become indispensable in various research fields such as physics, chemistry and medicine. They provide a non-invasive and non-destructive method for characterizing or imaging of a wide range of samples.

Recently, Raser-MRI (a new contrast mechanism without radio frequency pulses) has been developed, allowing for inexpensive hardware, higher resolution, and imaging without external rf-excitation. However, the contrast is based on cooperative nonlinear interaction between all slices of the image.

To efficiently model and correct for image artefacts, deep learning methods could be utilized to process MRI images.

Your task: You will use deep learning techniques to map simulated and acquired free induction decay (FID) signals to (1D+2D) MRI images. Your task includes finding the most suitable architecture structure (e.g. convolutional vs fully-connected vs recurrent neural network) to correlate FIDs to 1D MRI profiles, and to implement a functioning pipeline in pytorch.

You will be part of Prof. Korvink’s research group where you can get support from members with expertise in NMR theory, methodology, hardware, and simulation.

Eintrittstermin

as soon as possible

Persönliche Qualifikation

  • Field of study: Computer Science/Engineering, Mathematics, Information technology or similar
  • Highly motivated student with excellent academic record
  • Excellent knowledge of programming language python (or similar)
  • Experience with deep learning algorithms and knowledge about state-of-the-art methods
  • Optional: Basics in NMR
  • Languages: English or German

Contract duration

6 Months

Contact person in line-management

For further information, please contact Moritz Becker, phone +49 721 608-23150, email: moritz.becker@kit.edu or Dr. Sören Lehmkuhl, phone + 49 721 608-22760, email: soeren.lehmkuhl@kit.edu.

Bitte bewerben Sie sich online über den unten stehenden Button für die Ausschreibungsnummer IMT 36-2022.

Ausschreibungsnummer: IMT 36-2022

Bei gleicher Eignung werden anerkannt schwerbehinderte Menschen bevorzugt berücksichtigt.

Kontakt

Bei allgemeinen Fragen zur Bewerbung:
Personalservice (PSE) - Personalbetreuung
Frau Carrasco Sanchez
Telefon: +49 721 608-42016,

Kaiserstr. 12, 76131 Karlsruhe