Junru Zhong

My research

Recent Activities

  • Singapore! ISMRM 2024
    Growing up in southern China, Singapore has always been one of the most popular travel destinations. With the latest Sino-Singapore visa-exemption programme, Chinese MRI researchers like me can travel easily, unlike in Toronto last year. Or it will become worse in 2025?! Interestingly enough, I was arranged to use a traditional poster section rather than… Read more: Singapore! ISMRM 2024

Projects

I participate various research projects since college.

Fast knee quantitative mri

2023.10 – present

This is an ongoing project focus on how to accelerate knee cartilage quantitative MRI.

Automated Post-Processing for Compositional Knee MRI

2023.07 – present

This work-in-progress pipeline gathers various advanced, deep-learning-based techniques for generating regional compositional reports for quantitative analysis of knee OA.

Related publications

  • Zhong J, Yao Y, Xiao F, Ho KKW, Ong MTY, Griffith JF, Chen W. A systematic automated post-processing approach for quantitative analysis of 3D T1ρ knee MRI. In arXiv:2409.12600. Available at https://arxiv.org/abs/2409.12600
  • Zhong J, Yao Y, Xiao F, Ho KKW, Ong MTY, Griffith JF, Chen W. A systematic automated post-processing approach for quantitative analysis of 3D T1ρ knee MRI. In: Proceeding of the International Society for Magnetic Resonance in Medicine. Singapore; 2024.
  • Yao Y, Zhong J, Zhang L, Khan S, Chen W. CartiMorph: A framework for automated knee articular cartilage morphometrics. Medical Image Analysis. 2024 Jan 1;91:103035.
Knee Osteoarthritis Phenotyping with Unsupervised Domain Adaptation

2021.08 – 2023.10

We developed a deep-learning method that transfers latent knowledge from a large public dataset to our locally collected small dataset. The proposed method was evaluated with a knee OA phenotyping task on 3D TSE MRI. Related papers were published in ISMRM and QIMS.

Related publications

Knee MRI Segmentation

2020.08 – 2021.08

We developed a novel deep learning structure on MRI to segment knee structures (femoral bone, femoral cartilage, tibial bone, and tibial cartilage). This novel deep learning structure improves segmentation performance at edge slices where ROI areas are small.

Related publications