MSc Thesis: Multi-Plane Cardiac View Synthesis from Cardiac Scout MRI

 

Background

Scout MRI images, while lower in quality, offer a high density of slices through the cardiac volume, making them a valuable yet underutilized source for advanced image generation. This project focuses on developing methods to synthesize arbitrary or novel cardiac planes—including oblique or anatomically standard views (e.g., 4-chamber, short-axis)—from scout acquisitions. The goal is to enable view synthesis and plane interpolation, possibly powered by generative models, to support planning, diagnosis, or even act as a substitute for software-based acquisitions in time-constrained scenarios.

Your tasks

  • Development of generative or neural-hybrid models for novel plane synthesis
  • Exploitation of dense scout stack data for 3D representation learning
  • Evaluation of spatial and anatomical accuracy of generated planes

What we offer

  • Access to a  rich and novel scout dataset.
  • Guidance from both clinical and AI experts in a collaborative, interdisciplinary research setting.
  • Opportunity to contribute to ongoing research and potential publication in medical imaging journals or conferences.
  • Exposure to cutting-edge AI tools and frameworks for 3D medical image generation.

Details

The student will first explore the landscape of generation-based novel view synthesis. After concepting the core task is the implement a novel methodology for generating novel views through the cardiac scout images.

References

Bourigault, Emmanuelle, Abdullah Hamdi, and Amir Jamaludin. "X-diffusion: Generating detailed 3d mri volumes from a single image using cross-sectional diffusion models." (2024).
Liu, Ruoshi, et al. "Zero-1-to-3: Zero-shot one image to 3d object." Proceedings of the IEEE/CVF international conference on computer vision. 2023.

 

Contact
 Sevgi Gokce Kafali
Sevgi Gokce Kafali