Medical Image Analysis
Chest X-ray, retinal, and MRI analysis for clinical diagnosis — including lung disease classification, airway segmentation, and retinal structure analysis.
Medical Image Analysis · Computational Imaging
Junzhi Ning
I am a research assistant working on medical image analysis for clinical applications, currently affiliated with GMAI Group (General Medical AI), Shanghai Artificial Intelligence Laboratory. My research covers medical image analysis, medical image translation, and computational imaging, with a focus on chest X-ray, retinal, and MRI imaging in clinical contexts.
Before this position I completed an MRes (Distinction) at Imperial College London (Sep 2023 – Oct 2024), with a research project on chest X-ray image analysis for lung diagnosis, supervised by Dr. Matthieu Komorowski and Dr. Guang Yang.
My earlier studies include a Bachelor of Science (Honours) in Data Science with University Medal from The University of Sydney, a concurrent Diploma in Computing, and a Bachelor of Science in Mathematics and Statistics from The University of Melbourne (First-Class Honours).
Clinical Imaging · Medical Image Translation
Portrait of a man in quest of the unknown, yet satisfied.
MRes (Distinction) at Imperial College London. Research across medical image analysis, medical image translation, and computational imaging for clinical applications.
Research Overview
Medical Image Analysis & Computational Imaging
My work focuses on medical image analysis, medical image translation, and computational imaging for clinical applications — turning imaging data into clinically useful signals for diagnosis and downstream care.
Medical Image Translation
Cross-domain image translation for clinical data quality and diagnostic support — chest X-ray opacity handling, cross-sequence MRI translation, and fine-grained retinal image synthesis for clinical dataset diversity.
Computational Imaging for Clinical Applications
Methods that turn imaging data into clinically useful signals — robust segmentation, cross-domain adaptation, and image-quality handling for real-world clinical datasets.
MICCAI 2025
2×
Medical imaging
Journals & venues
6
PRL · ISBI · WACV · MICCAI · arXiv
Focus
Clinical imaging
Analysis · Translation · Computational imaging
Highlights
Publications, Awards & Opportunities
A snapshot of selected publications, academic recognition, and current goals.
Publications summary
2× MICCAI 2025 · 1× WACV 2025 · 1× ISBI 2025 · 1× Pattern Recognition Letters · 1× arXiv preprint — across chest X-ray, retinal, and MRI imaging.
Research Focus
Medical image analysis
Medical image translation
Computational imaging
Awards & recognition
- University Medal, BSc (Hons) in Data Science, University of Sydney (2023)
- Dean's Honours List for Data Science, University of Sydney (2023)
- Melbourne International Undergraduate Scholarship, University of Melbourne (2022)
- Dean's Honours List, University of Melbourne (2019)
Research interests
My research sits at the intersection of medical image analysis, medical image translation, and computational imaging — with published work on chest X-ray, retinal, and MRI imaging in clinical contexts.
Open to discussing medical image analysis and clinical imaging collaborations.
"Positivity is the essence of progress. In every challenge, I see an opportunity for learning and growth."
Publications
Selected publications
Selected work across medical image analysis, medical image translation, and computational imaging for clinical applications.
First-author Publications
RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions
Fine-grained retinal image synthesis for clinical dataset diversity. RetinaLogos produces high-resolution retinal fundus images conditioned on detailed clinical captions, supporting controlled variation over pathological features, vessel structures, and optic disc characteristics — enabling robust dataset diversification for downstream diagnostic analysis.
Unpaired Translation of Chest X-ray Images for Lung Opacity Diagnosis via Adaptive Activation Masks and Cross-Domain Alignment
Lung opacity in chest X-rays often obscures diagnostic features, complicating disease assessment. We propose an unpaired image-to-image translation framework that handles opacity artefacts while preserving critical diagnostic content. The method uses adaptive activation masks and cross-domain consistency to learn robust mappings between normal and opacity-affected images without paired training data, improving downstream segmentation and classification across lung disease datasets.
Unveiling the Capabilities of Latent Diffusion Models for Classification of Lung Diseases in Chest X-Rays
Investigates how image-synthesis approaches can be adapted for zero-shot lung-disease classification in chest X-rays. The intermediate representations learned during the denoising process encode rich diagnostic information, producing interpretable lesion localisations that align with radiological findings without explicit classification supervision.
Collaborations
Multi-modal MRI Translation via Evidential Regression and Distribution Calibration
Cross-sequence MRI translation for clinical diagnosis. The framework reformulates multi-modal MRI translation as an evidential regression problem with distribution calibration, providing reliable uncertainty estimates and robustness when deployed across different medical centres. Validated on three datasets from the BraTS2023 challenge.
DMRN: A Dynamical Multi-Order Response Network for the Robust Lung Airway Segmentation
Robust airway segmentation from CT scans. DMRN introduces a dynamical multi-order response architecture that adaptively adjusts its receptive fields to capture both fine-grained bronchiolar details and large-scale airway topology, achieving strong performance across clinical datasets including COPD, COVID-19, and lung-cancer cohorts.
Open World MRI Reconstruction with Bias-Calibrated Adaptation
Robust MRI reconstruction under distribution shift, with bias-calibrated adaptation for clinical deployment across heterogeneous scanners and patient populations.
For the latest list of publications, please see my Google Scholar profile.
Expertise
Skills & Expertise
Core competencies in medical image analysis, medical image translation, and computational imaging.
Research Areas
- Medical Image Analysis
- Medical Image Translation
- Computational Imaging for Clinical Applications
- Chest X-ray, Retinal, MRI & CT Imaging
- Clinical Data Curation
Technical Skills
- Medical Imaging: Chest X-ray, Retinal, MRI, CT
- Image Segmentation & Classification
- Image Translation & Synthesis
- PyTorch, TensorFlow
- Python, NumPy, Pandas
Tools & Platforms
- High-Performance Computing (HPC)
- Clinical Imaging Data Pipelines
- Version Control: Git, GitHub
- Experiment Tracking: Weights & Biases
- SLURM, Docker
Recognition
Awards & Honors
Academic achievements and recognitions throughout my research journey.
University Medal, University of Sydney
Awarded University Medal in Bachelor of Science (Honours) for achieving the highest academic distinction (WAM 89.5) in Data Science Honours program. The honour thesis on night-to-day image translation was subsequently accepted at the Australasian Database Conference.
Melbourne International Undergraduate Scholarship
Received merit-based scholarship from University of Melbourne in recognition of academic excellence in Mathematics and Statistics (Overall WAM: 86.8/First Class Honours).
Dean's Honours List, University of Melbourne
Placed on Dean's Honours List for First Year Bachelor of Science students for exceptional academic performance among the entire cohort.
News
Recent milestones
A lightweight lab notebook – recent papers, positions, and project updates.
Papers accepted at MICCAI 2025
Two papers accepted at MICCAI 2025 — RetinaLogos (first co-author) on fine-grained retinal image synthesis for clinical dataset diversity, and a co-authored paper on cross-sequence MRI translation for clinical diagnosis.
First-author paper published in Pattern Recognition Letters
Unpaired chest X-ray translation method for lung opacity diagnosis published in Pattern Recognition Letters, improving segmentation and classification across clinical lung disease datasets.
First-author paper accepted at ISBI 2025
First-author paper on image-synthesis-based approaches for lung disease classification in chest X-rays accepted at IEEE ISBI 2025.
Co-authored paper accepted at WACV 2025
DMRN — a dynamical multi-order response network for robust lung airway segmentation from CT scans — accepted at WACV 2025.
Completed MRes at Imperial College London (Distinction)
Completed MRes (Distinction) with a research project on chest X-ray image analysis for lung diagnosis, supervised by Dr. Matthieu Komorowski and Dr. Guang Yang.
Honours thesis accepted at Australasian Database Conference 2023
Honours thesis on semantic-prior night-to-day image translation accepted at the Australasian Database Conference 2023, alongside graduation with University Medal (BSc Honours in Data Science, University of Sydney).
Academic path
Affiliations & training
Research training across the University of Melbourne, the University of Sydney, and Imperial College London — a path through data science, mathematics, and medical imaging.
Academic Service
📝 Reviewer Service
Reviewer - Journals
TMI
Reviewer - Conferences
ICLR, ISBI, MICCAI 2026
Gratitude
🙏 Acknowledgments
I am deeply grateful to my supervisors Dr. Guang Yang (Imperial College London), Dr. Matthieu Komorowski (Imperial College London), Prof. Mingming Gong (The University of Melbourne), and Dr. Junjun He (GMAI Group, Shanghai Artificial Intelligence Laboratory) for their invaluable guidance, mentorship, and support throughout my research journey. Their insights and encouragement have been instrumental in shaping my academic growth.
I also extend my sincere thanks to my collaborators Lihao Liu (University of Cambridge), Sheng Zhang (Imperial College London), Xiaodan Xing (Imperial College London), Yingying Fang (Imperial College London), and many others. Their expertise, dedication, and teamwork have been essential to our research achievements.
Contact
Say hello
Open to discussing medical image analysis and clinical imaging collaborations.
Collaborations
If you work on medical image analysis, medical image translation, or computational imaging for clinical applications, I would love to connect.
- GitHub github.com/junzhin
- LinkedIn linkedin.com/in/junzhin
- Google Scholar Google Scholar profile
Quick profile
- Current Research Assistant, GMAI Group (General Medical AI), Shanghai Artificial Intelligence Laboratory
- MRes Imperial College London (Distinction)
- BSc (Hons) Data Science, University of Sydney (University Medal)
- Interests Medical image analysis · Medical image translation · Computational imaging