Medical AI Researcher
I develop computational methods at the frontier of medical image analysis, AI, computer vision, and deep learning. My research advances how machines understand and interact with clinical imaging data, from skull reconstruction to dental morphology to intelligent diagnostic pipelines. In particular, my research focuses on deep generative models, explainable AI, and computationally efficient shape-based methods for medical applications, with a strong track record of publications in top journals of his field.
Open to collaborations on papers & grants, research discussions, and Bachelor/Master thesis supervision.
Background & Education
Jianning Li is a researcher specializing in the application of computer vision and deep learning to medical image analysis. He holds a Ph.D. and M.S. in Computer Science (both with distinction) and a B.S. in Biomedical Engineering (with distinction), reflecting a career built at the unique intersection of engineering and clinical science.
His work develops intelligent systems for analyzing medical imagery, including cranial reconstruction, automated tooth segmentation, root canal morphology, and brain tumor analysis. A core thread throughout his research is clinical translation: building tools that not only advance science but improve care.
Beyond core research, Jianning actively contributes to the scientific community through peer review, workshop organization, and mentoring the next generation of researchers. He is particularly passionate about interpretable AI, models that clinicians can understand, trust, and use.
Education
Latest
Updates
Multiple Master's thesis topics available in medical image analysis and deep learning. Check the prospective students page for details.
We were looking for a research student assistant. This position is now closed.
Attended MICCAI 2023 in Vancouver, Canada (Oct 8β15).
Actively seeking collaborators for joint papers and grant proposals in AI-powered clinical imaging. Reach out to discuss!
Research
Projects
MONAI Skull Reconstruction
Open-source skull reconstruction pipeline built on MONAI. Provides a reproducible, community-friendly framework for cranial implant design.
View Project βSparse CNN for Shape Completion & Super-resolution
Sparse convolutional neural networks for high-resolution skull shape completion and shape super-resolution from low-resolution inputs.
View Project βRegistration-based Shape Completion
A registration-driven approach to skull shape completion, leveraging image registration to complete missing anatomical regions.
View Project βCoarse-to-Fine Shape Completion
A coarse-to-fine (C2F) framework for high-resolution skull shape completion, enabling detailed implant design from CT scans.
View Project βCloud Deployment for Shape Completion
Deploying deep learning skull shape completion models to the cloud β a practical example of clinical AI deployment.
View Project βPatch-wise Skull Reconstruction
Patch-based approach to skull reconstruction, enabling scalable processing of large volumetric CT data for cranioplasty planning.
View Project βSelected
Publications
MedShapeNet β a large-scale dataset of 3D medical shapes for computer vision.
Biomedical Engineering / Biomedizinische Technik, Volume 70, Issue 1
Why is the winner the best?
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19955β19966
How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation.
BraTS 2023 β First Place
The HoloLens in medicine: A systematic review and taxonomy.
Medical Image Analysis, Volume 85, p. 102757
Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the AutoImplant 2021 cranial implant design challenge.
Medical Image Analysis, Volume 88, August 2023, 102865
Anatomy Completor: A Multi-class Completion Framework for 3D Anatomy Reconstruction.
International Workshop on Shape in Medical Imaging (ShapeMI 2023), pp. 1β14. Springer.
Inside-Out Instrument Tracking for Surgical Navigation in Augmented Reality.
27th ACM Symposium on Virtual Reality Software and Technology, pp. 1β11
Detection, segmentation, simulation and visualization of aortic dissections: A review.
Medical Image Analysis (MedIA), 65, p. 101773
Medical image segmentation in oral-maxillofacial surgery.
Computer-Aided Oral and Maxillofacial Surgery, pp. 1β27
Books &
Proceedings
Shape in Medical Imaging
International Workshop, ShapeMI 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023.
Editor / Organizer View on Springer βMedical Applications with Disentanglements
First MICCAI Workshop, MAD 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022.
Editor / Organizer View on Springer βTowards the Automatization of Cranial Implant Design in Cranioplasty II
Second Challenge, AutoImplant 2021, held in conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021.
Editor / Challenge Lead View on Springer βTowards the Automatization of Cranial Implant Design in Cranioplasty I
First Challenge, AutoImplant 2020, held in conjunction with MICCAI 2020, Lima, Peru, October 8, 2020.
Editor / Challenge Lead View on Springer βPresentations
& Talks
Disentanglement in Neuroimage Analysis
Oral Presentation
VAE-based Skull Shape Completion
Poster Presentation
Invited Talk
Lecture
A Baseline Approach for AutoImplant: the MICCAI 2020 Cranial Implant Design Challenge
Conference Presentation
Academic
Service
Challenge Lead Organizer
- AutoImplant I @ MICCAI 2020
- AutoImplant II @ MICCAI 2021
Workshop / Tutorial Co-organizer
- MedShapeNet Tutorial @ MICCAI 2024
- ShapeMI 2023 @ MICCAI 2023
- MAD 2022 @ MICCAI 2022
Program Committee
- SEG.A 2023 @ MICCAI 2023
Reviewer
- MICCAI β Medical Image Computing & Computer Assisted Intervention
- Medical Image Analysis (MedIA)
- IEEE ISBI β International Symposium on Biomedical Imaging
- Computers in Biology and Medicine
- Artificial Intelligence in Medicine
- Pattern Recognition Letters
Editorial
- Proceedings, Shape in Medical Imaging
- Proceedings, Medical Applications with Disentanglements
- Proceedings, Towards the Automatization of Cranial Implant Design II
- Proceedings, Towards the Automatization of Cranial Implant Design I
Memberships
Teaching &
Mentoring
Courses Taught
Thesis Supervision
Offering Bachelor's and Master's thesis topics in:
- Medical image segmentation
- Interpretable AI in radiology
- 3D reconstruction from scans
- Generative models for augmentation
Prospective Students
Interested in a thesis or research collaboration? Reach out with your CV and a brief description of your interests.
jianningli.me@gmail.com