Jiayang Shi

I'm currently in my fourth (final) year as a PhD student at Leiden University, located in Leiden, the Netherlands. My supervisors are Daan Pelt and Joost Batenburg.

My research is part of the Marie Curie project, xCTing. I focus on integrating machine learning with denoising and artifact reduction techniques for Computed Tomography (CT) imaging. This encompasses tomographic reconstruction and addressing inverse problems in general.

My PhD journey began in September 2021. Prior to this, I earned my bachelor's degree in 2013 from Hangzhou, China, and completed my master's in 2021 in Karlsruhe, Germany.

Email  /  Google Scholar  /  GitHub  /  LinkedIn

Research

A novel Bayesian framework for joint reconstruction of multiple objects from sparse-view CT scans using Implicit Neural Representations (INRs) to improve reconstruction quality. By capturing shared patterns across multiple objects with latent variables, our method enhances the reconstruction of each object, increases robustness to noise, and accelerates the learning process.

A self-supervised approach designed for edge illumination X-ray phase contrast micro-CT to enhance the resolution of anisotropic volumes.

A self-supervised approach utilizing off-axis training to improve the resolution of through-plane CT scans. This method is trained using in-plane images and applied to through-plane images, offering flexibility with any resolution and overlap.

A artifact reduction method for CT images based on deep learning. Three CNNs reduce artifacts in a subsequent manner, targeting different types of artifacts. This method is seamlessly integrated into existing CT pipelines.

A Benchmark Low-dose Industrial CT Dataset Tailored for Deep Learning: This work introduces a dataset specifically designed for industrial CT applications, emphasizing deep learning approaches. It features a comprehensive analysis comparing the effectiveness and efficiency of 2D, 2.5D, and 3D training methodologies in the context of denoising and image enhancement.

Unsupervised cross-domain graph level anomaly detection.

Graph neural network for log anomaly detection.

A novel method to reconstruct a spectral central view and its aligned disparity map from spatio-spectrally coded light fields using multi-task deep learning.

Teaching Assistant

Supervised Thesis

Donghang Lyu (master student): Res-Swin: Effective Combination of ResNet and Swin Transformer for LDCT Denoising
Omar Elkilany (master student@TUM & WayGate): Beam Hardening Correction using Implicit Neural Representations