Xia Li
Xia Li 李夏

Doctoral student

ETH Zurich

About Me

I’m now a joint doctoral student of ETH Zurich and Paul Sherrer Institut, supervised by Prof. Joachim Buhmann, Prof. Antony Lomax and Dr. Ye Zhang. Previously, I obtained my Master’s and Bachlor’s degree from Peking University and Beijing University of Posts and Telecommunications, respectively. During my postgrade, I was fortunate to work with Prof. Hong Liu and Prof. Zhouchen Lin.

Download CV
Interests
  • Medical Imaging
  • Radiotherapy
  • Computer Vision
Education

  • PhD Computer Science

    ETH Zurich

  • MSc Computer Science

    Peking University

📚 My Research
Now my research interest lies in the intersection of image processing technique and radiation therapy. My ultimate goal of my research is to reducing the cost of proton therapy from the algorithm perspective, and make it affordable by average people. Before studying medical image processing, I mainly work on image and video segmentation. I also have experience on image restoration and data mining.
Recent News
Featured Publications
Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction
Uncertainty-aware MR-based CT synthesis for robust proton therapy planning of brain tumour
Expectation Maximization Attention Networks for Semantic Segmentation
Recent Publications
CPT-Interp: Continuous sPatial and Temporal Motion Modeling for 4D Medical Image Interpolation
Deformable Image Registration

CPT-Interp: Continuous sPatial and Temporal Motion Modeling for 4D Medical Image Interpolation

In this work, we introduce a novel Continuous sPatial and Temporal (CPT) modeling approach for 4D medical image interpolation, addressing the limitations of discrete motion modeling in both spatial and temporal domains. By leveraging implicit neural representations and integrating an ODE solver, our method achieves superior accuracy and speed without requiring extensive training datasets or domain-specific fine-tuning. Through comprehensive experiments and ablation studies, we demonstrated the contributions of spatial and temporal continuity, as well as the robustness of our method across different datasets. CPT-Interp not only outperforms state-of-the-art methods but also exhibits remarkable generalization ability, making it a promising solution for clinical applications.

Gaussian Representation for Deformable Image Registration
Diffusion Schrödinger Bridge Models for High-Quality MR-to-CT Synthesis for Head and Neck Proton Treatment Planning
Mr-Guided Proton Therapy

Diffusion Schrödinger Bridge Models for High-Quality MR-to-CT Synthesis for Head and Neck Proton Treatment Planning

In this study, we propose the Diffusion Schrödinger Bridge Models (DSBM) which enhances the performance of MRto-CT image synthesis, both in quality and efficiency. By learning the nonlinear diffusion processes between MR and CT data distributions and initiating synthesis from a prior distribution, DSBM outperforms traditional methods, as validated in our head and neck cancer case studies. This approach has demonstrated its value through comprehensive evaluations at both the image and dosimetric levels. DSBM can improve the accuracy and efficiency of MR-based treatment planning in proton therapy, which could potentially reduce imaging-related dose and improve patient outcomes in radiotherapy.

Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction
See all publications
Recent & Upcoming Talks
ICCR 2024 Rising Star Competition
ESTRO 2024 Proffered Paper
ESTRO 2023 Mini-Oral
ICCV 2019 Oral