Craig Jones, PhD

Personal Website: https://imagingai.org

Curriculum Vitæ

Contact Overview Announcements Publications Links

Contact

ENG Biomedical Engineering

Email: cjones7@ualberta.ca
Address: Donadeo Innovation Centre For Engineering
9211 116 St

Edmonton AB

T6G 2H5

Overview

Area of Study / Keywords

medical imaging artificial intelligence machine learning ophthalmology longitudinal uncertainty

About

I completed an undergraduate degree in Mathematics and Computing Science at Simon Fraser University, followed by an MSc in Medical Biophysics at the University of Western Ontario and a PhD in Physics at the University of British Columbia. My postdoctoral training and subsequent early career were based in Baltimore, Maryland.

I am a Professor in Biomedical Engineering and a Fellow at the Alberta Machine Intelligence Institute.

I love being challenged by difficult problems and thinking carefully through potential solutions, and I am equally excited about encouraging and mentoring students in their work and engaging closely with them as they develop as scientists. If you are someone who likes to be challenged by problems, loves reading and is inquisitive please fill out this form https://forms.gle/N6q7gh2gHfGnPGvG6.

Research

I am a medical imaging and artificial intelligence researcher focused on building automated systems that genuinely improve clinical care. My work centers on deep learning methods for image-based disease diagnosis, monitoring, and decision support, with an emphasis on robustness, reliability, and real-world deployment. A core theme of my research is explainable and uncertainty-aware AI. I design models that quantify both epistemic and aleatoric uncertainty, enabling clinicians to understand when to trust algorithmic outputs and when to be cautious. This includes work on uncertainty in 3D U-Net segmentation, evidential uncertainty estimation for deformable registration fields, and one-shot uncertainty estimation in deep learning-based image reconstruction.

Methodologically, my projects span unsupervised image analysis, shape analysis, longitudinal modeling, artifact detection, and multi-modal imaging pipelines. I have developed algorithms and complete workflows for tasks such as automated segmentation and radiomic analysis of venous malformations, AI-based detection of pancreatic cancer from endoscopic ultrasound, deep-learning–based tumor segmentation on multi-modal MRI with missing data, and federated learning for rare cancer boundary detection.

Another major focus of my work is imaging for surgery and interventional procedures, where I integrate physics-based models with deep learning. I contribute to methods for deformable registration between MR, CT, and cone-beam CT, real-time 3D neuroendoscopic guidance, and robot-assisted ultrasound probe positioning using deep reinforcement learning. These projects aim to provide accurate, uncertainty-aware guidance in complex operative environments, improving safety and precision.

I am also deeply engaged in ophthalmic AI, including deep learning for predicting visual outcomes from multimodal fundus images, robust OCT/OCTA alignment and registration, and interpretable models and transformers for retinal image analysis. Across these projects, I prioritize artifact-robust pipelines that can handle noisy, imperfect clinical data while still producing interpretable and clinically useful outputs.

In parallel to my research, I lead and participate in initiatives that promote collaborative, clinically grounded AI development, including work on large-scale datasets, federated learning, and global medical foundation models. I am committed to mentoring students at all levels and to building multidisciplinary teams that bring together technical innovation, clinical insight, and rigorous evaluation to translate AI-driven medical imaging methods into impactful tools for patient care.

Announcements

If you are interested in medical imaging AI projects and are a person who is inquisitive and curious I am happy to talk. The best way to do that is to fill out the form https://forms.gle/N6q7gh2gHfGnPGvG6 so I can learn about your background, interests and time commitment. If you have questions you can email me at cjones7 @ ualberta.ca.

Featured Publications

Emergent Language Symbolic Autoencoder (ELSA) with weak supervision to model hierarchical brain networks

Ammar Ahmed Pallikonda Latheef, Alberto Santamaria-Pang, Craig K. Jones, Haris I. Sair

Computers in Biology and Medicine. 2026 March; 10.1016/j.compbiomed.2026.111533

Unsupervised quality assessment with generative adversarial networks for 3D OCTA microvascular imaging

Edmund Sumpena, Andrew Cornelio, Ana Collazo, Shu Jie Ting, Tim Kowalczyk, Xuejuan Jiang, Alexa Beiser, Sudha Seshadri, Amir H. Kashani, Craig K. Jones

Biomedical Optics Express. 2026 January; 10.1364/BOE.573843

Self-Supervised Feature Detection and 3D Reconstruction for Real-Time Neuroendoscopic Guidance

Prasad Vagdargi, Ali Uneri, Stephen Z. Liu, Craig K. Jones, Alejandro Sisniega, Junghoon Lee, Patrick A. Helm, Ryan P. Lee, Mark G. Luciano, Gregory D. Hager, Jeffrey H. Siewerdsen

IEEE Transactions on Biomedical Engineering. 2025 July; 10.1109/TBME.2025.3538683

Atlas-Based Labeling of Resting-State fMRI

Hrishikesh Kambli, Alberto Santamaria-Pang, Ivan Tarapov, Elham Beheshtian, Licia P. Luna, Haris Sair, Craig Jones

Brain Connectivity. 2024 August; 10.1089/brain.2023.0080

Comparative analysis of alignment algorithms for macular optical coherence tomography imaging.

Jones CK, Li B, Wu JH, Nakaguchi T, Xuan P, Liu TYA

International journal of retina and vitreous. 2023 October; 10.1186/s40942-023-00497-2

Real-Time 3-D Video Reconstruction for Guidance of Transventricular Neurosurgery

Prasad Vagdargi, Ali Uneri, Xiaoxuan Zhang, Craig K. Jones, Pengwei Wu, Runze Han, Alejandro Sisniega, Junghoon Lee, Patrick Helm, Mark Luciano, William S. Anderson, Gregory D. Hager, Jeffrey H. Siewerdsen

IEEE Transactions on Medical Robotics and Bionics. 2023 August; 10.1109/TMRB.2023.3292450

Brain Tumor Segmentation for Multi-Modal MRI with Missing Information.

Feng X, Ghimire K, Kim DD, Chandra RS, Zhang H, Peng J, Han B, Huang G, Chen Q, Patel S, Bettagowda C, Sair HI, Jones C, Jiao Z, Yang L, Bai H

Journal of digital imaging. 2023 June; 10.1007/s10278-023-00860-7

Optical Coherence Tomography Angiography, Artificial Intelligence, and the Missing Capillaries.

Kashani AH, Liu TYA, Jones C

JAMA ophthalmology. 2023 May; 10.1001/jamaophthalmol.2023.1829

Combining physics-based models with deep learning image synthesis and uncertainty in intraoperative cone-beam CT of the brain.

Zhang X, Sisniega A, Zbijewski WB, Lee J, Jones CK, Wu P, Han R, Uneri A, Vagdargi P, Helm PA, Luciano M, Anderson WS, Siewerdsen JH

Medical physics. 2023 March; 10.1002/mp.16351

Interrater Reliability of Cervical Neural Foraminal Stenosis Using Traditional and Splayed Reconstructions: Analysis of One Hundred Scans.

Hersh AM, Zahoor A, Livingston D, Galinato A, Recht H, Hostetter J, Jones CK, Lubelski D, Sair HI

World neurosurgery. 2023 March; 10.1016/j.wneu.2023.03.079

Deep Labeling of fMRI Brain Networks

arXiv. 2023 January; 10.48550/arXiv.2305.03814

Active Learning in Brain Tumor Segmentation with Uncertainty Sampling, Annotation Redundancy Restriction, and Data Initialization

arXiv. 2023 January; 10.48550/arXiv.2302.10185

Real-Time 3D Neuroendoscopic Guidance Using SLAM: First Clinical Studies

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2023 January; 10.1117/12.2654595

Multi-Modality Registration of Preoperative MR and Intraoperative Long-Length Tomosynthesis Using GAN Synthesis and 3D-2D Registration

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2023 January; 10.1117/12.2654329

View additional publications