/ RESEARCH & TECHNICAL WORK

Systems, research, and public evidence.

Current work centers on frontier-model post-training. Earlier public research covers 3D medical imaging, MRI reconstruction, super-resolution, and segmentation.

/ CURRENT

Post-training systems

I turn capability gaps into trainable, verifiable systems.

READ THE PUBLIC SYSTEM OVERVIEW →

/ RESEARCH RECORD

My earlier work in 3D MRI reconstruction, super-resolution, and segmentation has been cited more than 1,000 times.

I am a co-inventor on patent applications covering deep-learning MRI reconstruction and calcium-free CT angiography.

Earlier research includes peer-reviewed work at MICCAI, ISBI, Medical Physics, and WACV.

/ SELECTED PUBLICATIONS

MICCAI 2018

Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network

A GAN with a 3D densely-connected generator that recovers high-resolution detail from low-resolution MRI — sharper scans without more scan time.

Y Chen, F Shi, AG Christodoulou, Y Xie, Z Zhou, D Li

PAPER RECORD →
Brain-MRI super-resolution: nearest-neighbour and bicubic interpolation through FSRCNN, SRResNet, mDCSRN, and our mDCSRN-GAN, next to the ground-truth reference.
4× super-resolution vs. baselines (arXiv:1803.01417)

ISBI 2018

Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks

3D deep densely-connected networks for brain-MRI super-resolution — the earlier study the MICCAI work built on.

Y Chen, Y Xie, Z Zhou, F Shi, AG Christodoulou, D Li

PAPER RECORD →

Medical Physics 2020

Fully Automated Multi-Organ Segmentation in Abdominal Magnetic Resonance Imaging with Deep Neural Networks

Deep networks that automatically delineate multiple organs across abdominal MRI — replacing slow manual contouring.

Y Chen, D Ruan, J Xiao, L Wang, B Sun, R Saouaf, W Yang, D Li, Z Fan

PAPER RECORD →
3D renderings of automatically segmented abdominal organs — liver, spleen, kidneys and pancreas — from manual labels through the network variants.
Automated multi-organ segmentation, 3D view (PMC7722015, Medical Physics 2020)

WACV 2020

Enhanced Generative Adversarial Network for 3D Brain MRI Super-Resolution

An enhanced adversarial network for 3D brain-MRI super-resolution (co-first author).

J Wang, Y Chen, Y Wu, J Shi, J Gee

PAPER RECORD →
Axial brain-MRI super-resolution across FSRCNN, SRResNet, mDCSRN, RRDB and the RRDB patch-GAN, beside the ground-truth reference.
Brain super-resolution vs. baselines (arXiv:1907.04835)

PREPRINT

MRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and Better

Journal extension of the super-resolution work — a smaller, faster model with better image quality.

Y Chen, AG Christodoulou, Z Zhou, F Shi, Y Xie, D Li

PAPER RECORD →

MICCAI 2019

Deep Learning Within a Priori Temporal Feature Spaces for Large-Scale Dynamic MR Image Reconstruction

Reconstructs large-scale dynamic (5D) MRI fast by learning inside a low-dimensional temporal-feature subspace.

Y Chen, JL Shaw, Y Xie, D Li, AG Christodoulou

PAPER RECORD →
FULL RECORD ON GOOGLE SCHOLAR →