Lab Overview

Mission

The Intelligent MRI Lab develops AI and computational imaging methods for quantitative MRI, neuroimaging analysis, and clinically relevant imaging biomarkers.

Research Focus

Accelerated MRI acquisition and reconstruction
Quantitative susceptibility mapping
White matter lesion analysis
Longitudinal neuroimaging biomarkers
Machine learning for computational MRI

Open Positions

We welcome inquiries from prospective PhD students, postdocs, and research collaborators interested in MRI, inverse problems, and translational AI.

Resources

Publications

VAID: Valve Artifact Inpainting for Normal Pressure Hydrocephalus from a 3D MRI Diffusion Model

Wang, S., Wei, S., Remedios, S.W., Zhang, J., Dewey, B., Blitz, A., Luciano, M.G., Carass, A. and Prince, J. (2026). "VAID: Valve Artifact Inpainting for Normal Pressure Hydrocephalus from a 3D MRI Diffusion Model." IEEE ISBI (accepted).

Pipeline refinement on diffusion tractography and T1 tractography in the presence of multiple sclerosis lesions

Zhou, L., Bian, Z., Zhang, J., Saidha, S., Calabresi, P.A., Carass, A. and Prince, J.L. (2026). "Pipeline refinement on diffusion tractography and T1 tractography in the presence of multiple sclerosis lesions." SPIE Medical Imaging (accepted).

MRI Quantification of Liver Fibrosis Using Diamagnetic Susceptibility: An Ex Vivo Validation Study

Li, C., Zhang, J., Dimov, A.V., Koehne de González, A.K., Prince, M.R., Li, J., Romano, D., Spincemaille, P., Nguyen, T.D., Brittenham, G.M. and Wang, Y. (2026). "MRI Quantification of Liver Fibrosis Using Diamagnetic Susceptibility: An Ex Vivo Validation Study." Tomography, 12(4), 46.

Evidence of iron accumulation in cerebral adrenoleukodystrophy: a potential novel disease mechanism

Nemeth, C., Sisman, M., Zhang, J., Shin, H.-G., Li, X., Turk, B., Fatemi, A., Nguyen, T. and Mallack, E. (2026). "Evidence of iron accumulation in cerebral adrenoleukodystrophy: a potential novel disease mechanism." Annals of Clinical and Translational Neurology (accepted).

Feasibility of implicit neural representation learned motion compensation for 3D stack-of-spirals free-breathing cardiac quantitative susceptibility mapping

Li, J., Deng, A., Li, C., Villar-Calle, P., Zhang, J., Dimov, A.V., Kim, J., Nguyen, T.D., Wang, Y., Weinsaft, J.W. and Spincemaille, P. (2026). "Feasibility of implicit neural representation learned motion compensation for 3D stack-of-spirals free-breathing cardiac quantitative susceptibility mapping." Magnetic Resonance in Medicine (accepted).

Harmonizing MR Images Across 100+ Scanners: Multi-site Validation with Traveling Subjects and Real-world Protocols

Hays, S.P., Zuo, L., Chaudhary, M.F.A., Bartz, K.M., Remedios, S.W., Zhang, J., Zhuo, J., Bilgel, M., Saidha, S., Mowry, E.M., Newsome, S.D., Prince, J.L., Dewey, B.E. and Carass, A. (2026). "Harmonizing MR Images Across 100+ Scanners: Multi-site Validation with Traveling Subjects and Real-world Protocols." MIDL (accepted).

A Pipeline for DTI Indices and Connectivity Analysis Applied to a Longitudinal Multiple Sclerosis Cohort

Zhou, L., Bian, Z., Zhang, J., Dewey, B., Saidha, S., Calabresi, P., Carass, A. and Prince, J. (2026). "A Pipeline for DTI Indices and Connectivity Analysis Applied to a Longitudinal Multiple Sclerosis Cohort." IEEE ISBI (accepted).

Unsupervised deformable image registration with structural nonparametric smoothing

Zhang, H., Hu, R., Chen, X., Liu, M., Wang, Y., Wang, R., Zhang, J., Li, G., Cheng, X. and Duan, J. (2025). "Unsupervised deformable image registration with structural nonparametric smoothing." IPMI, 108-124.

An Unsupervised Approach for Artifact Severity Scoring in Multi-Contrast MR Images

Hays, S., Zuo, L., Dewey, B.E., Remedios, S., Zhang, J., Mowry, E.M., Newsome, S.D., Carass, A. and Prince, J.L. (2025). "An Unsupervised Approach for Artifact Severity Scoring in Multi-Contrast MR Images." MIDL.

Unique MS lesion identification from MRI

Rivas, C.A., Zhang, J., Wei, S., Remedios, S.W., Carass, A. and Prince, J.L. (2025). "Unique MS lesion identification from MRI." SPIE Medical Imaging, 13406, 592-599.

Bi-directional MS lesion filling and synthesis using denoising diffusion implicit model-based lesion repainting

Zhang, J., Zuo, L., Liu, Y., Remedios, S., Landman, B.A., Prince, J.L. and Carass, A. (2025). "Bi-directional MS lesion filling and synthesis using denoising diffusion implicit model-based lesion repainting." SPIE Medical Imaging, 13406, 217-223.

UNISELF: A Unified Network with Instance normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation

Zhang, J., Zuo, L., Dewey, B.E., Remedios, S.W., Liu, Y., Hays, S.P., Pham, D.L., Mowry, E.M., Newsome, S.D., Calabresi, P.A., Saidha, S., Carass, A. and Prince, J.L. (2025). "UNISELF: A Unified Network with Instance normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation." Medical Image Analysis, 103954.

The TRaditional versus Early Aggressive Therapy for MS (TREAT-MS) trial: Design and baseline characteristics of participants

Mowry, E.M., Qian, P., Meador, W., Lynch, S., Narayan, R., Borazanci, A., ... & treat-MS Trial Team (including Zhang, J.) (2025). "The TRaditional versus Early Aggressive Therapy for MS (TREAT-MS) trial: Design and baseline characteristics of participants." Contemporary Clinical Trials, 108117.

Spiral cardiac quantitative susceptibility mapping for differential cardiac chamber oxygenation—Initial validation in relation to invasive blood sampling

Li, J., Villar-Calle, P., Chiu, C., Reza, M., Narula, N., Li, C., Zhang, J., Nguyen, T.D., Wang, Y., Zhang, R.S. and Kim, J. (2025). "Spiral cardiac quantitative susceptibility mapping for differential cardiac chamber oxygenation—Initial validation in relation to invasive blood sampling." Magnetic Resonance in Medicine, 93(5), 2029-2039.

Technical Feasibility of Quantitative Susceptibility Mapping Radiomics for Predicting Deep Brain Stimulation Outcomes in Parkinson’s Disease

Roberts, A., Zhang, J., Tozlu, C., Romano, D., Akkus, S., Kim, H., Sabuncu, M., Spincemaille, P., Li, J., Wang, Y., Wu, X. and Kopell, B. (2025). "Technical Feasibility of Quantitative Susceptibility Mapping Radiomics for Predicting Deep Brain Stimulation Outcomes in Parkinson’s Disease." Neurosurgery.

Navigator motion-resolved MR fingerprinting using implicit neural representation (FINR): feasibility for free-breathing 3D whole-liver multiparametric mapping

Li, C., Li, J., Zhang, J., Solomon, E., Dimov, A.V., Spincemaille, P., Nguyen, T.D., Prince, M.R. and Wang, Y. (2025). "Navigator motion-resolved MR fingerprinting using implicit neural representation (FINR): feasibility for free-breathing 3D whole-liver multiparametric mapping." Magnetic Resonance in Medicine, 95(1), 613-627.

Encoder-Only Image Registration

Chen, X., Hu, R., Zhang, J., Zhang, Y., Yue, X., Liu, M., Wang, Y. and Zhang, H. (2025). "Encoder-Only Image Registration." IEEE Transactions on Circuits and Systems for Video Technology.

ECLARE: Efficient cross-planar learning for anisotropic resolution enhancement

Remedios, S.W., Wei, S., Han, S., Zhang, J., Guo, L., Carass, A., Schilling, K.G., Korotcov, A., Pham, D.L., Prince, J.L. and Dewey, B.E. (2025). "ECLARE: Efficient cross-planar learning for anisotropic resolution enhancement." Journal of Medical Imaging, 13(2), 024001.

Towards an accurate and generalizable multiple sclerosis lesion segmentation model using self-ensembled lesion fusion

Zhang, J., Zuo, L., Dewey, B.E., Remedios, S.W., Pham, D.L., Carass, A. and Prince, J.L. (2024). "Towards an accurate and generalizable multiple sclerosis lesion segmentation model using self-ensembled lesion fusion." IEEE ISBI.

Harmonization-enriched domain adaptation with light fine-tuning for multiple sclerosis lesion segmentation

Zhang, J., Zuo, L., Dewey, B.E., Remedios, S.W., Hays, S.P., Pham, D.L., Prince, J.L. and Carass, A. (2024). "Harmonization-enriched domain adaptation with light fine-tuning for multiple sclerosis lesion segmentation." SPIE Medical Imaging, 12930, 635-641.

Multi-Echo Complex Quantitative Susceptibility Mapping and Quantitative Blood Oxygen Level-Dependent Magnitude for Oxygen Extraction Fraction Mapping

Cho, J., Zhang, J., Spincemaille, P., Zhang, H., Nguyen, T.D., Zhang, S., Gupta, A. and Wang, Y. (2024). "Multi-Echo Complex Quantitative Susceptibility Mapping and Quantitative Blood Oxygen Level-Dependent Magnitude for Oxygen Extraction Fraction Mapping." Bioengineering, 11(2), 131.

mcLARO: Multi-contrast learned acquisition and reconstruction optimization for simultaneous quantitative multi-parametric mapping

Zhang, J., Nguyen, T.D., Solomon, E., Li, C., Zhang, Q., Li, J., Zhang, H., Spincemaille, P. and Wang, Y. (2024). "mcLARO: Multi-contrast learned acquisition and reconstruction optimization for simultaneous quantitative multi-parametric mapping." Magnetic Resonance in Medicine, 91(1), 344-356.

DEDA: Deep directed accumulator

Zhang, H., Wang, R., Hu, R., Zhang, J. and Li, J. (2023). "DEDA: Deep directed accumulator." MICCAI, 765-775.

Spatially Covariant Lesion Segmentation

Zhang, H., Wang, R., Zhang, J., Liu, D., Li, C., Li, J. (2023). "Spatially Covariant Lesion Segmentation." IJCAI, 1713-1721.

Quantitative susceptibility mapping using multi-channel convolutional neural networks with dipole-adaptive multi-frequency inputs

Si, W., Guo, Y., Zhang, Q., Zhang, J., Wang, Y. and Feng, Y. (2023). "Quantitative susceptibility mapping using multi-channel convolutional neural networks with dipole-adaptive multi-frequency inputs." Frontiers in Neuroscience, 17, 1165446.

LARO: Learned acquisition and reconstruction optimization to accelerate quantitative susceptibility mapping

Zhang, J., Spincemaille, P., Zhang, H., Nguyen, T.D., Li, C., Li, J., Kovanlikaya, I., Sabuncu, M.R. and Wang, Y. (2023). "LARO: Learned acquisition and reconstruction optimization to accelerate quantitative susceptibility mapping." NeuroImage, 268, 119886.

Subsecond accurate myelin water fraction reconstruction from FAST-T2 data with 3D UNET

Kim, J., Nguyen, T.D., Zhang, J., Gauthier, S.A., Marcille, M., Zhang, H., Cho, J., Spincemaille, P. and Wang, Y. (2022). "Subsecond accurate myelin water fraction reconstruction from FAST-T2 data with 3D UNET." Magnetic Resonance in Medicine, 87(6), 2979-2988.

QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps

Zhang, H., Nguyen, T.D., Zhang, J., Marcille, M., Spincemaille, P., Wang, Y., Gauthier, S.A. and Sweeney, E.M. (2022). "QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps." NeuroImage: Clinical, 34, 102979.

QQ-NET–using deep learning to solve quantitative susceptibility mapping and quantitative blood oxygen level dependent magnitude based oxygen extraction fraction mapping

Cho, J., Zhang, J., Spincemaille, P., Zhang, H., Hubertus, S., Wen, Y., Jafari, R., Zhang, S., Nguyen, T.D., Dimov, A.V. and Gupta, A. (2022). "QQ-NET–using deep learning to solve quantitative susceptibility mapping and quantitative blood oxygen level dependent magnitude based oxygen extraction fraction mapping." Magnetic Resonance in Medicine, 87(3), 1583-1594.

Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction

Zhang, J., Zhang, H., Li, C., Spincemaille, P., Sabuncu, M., Nguyen, T.D. and Wang, Y. (2021). "Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction." MICCAI.

Hybrid optimization between iterative and network fine-tuning reconstructions for fast quantitative susceptibility mapping

Zhang, J., Zhang, H., Spincemaille, P., Nguyen, T., Sabuncu, M.R. and Wang, Y. (2021). "Hybrid optimization between iterative and network fine-tuning reconstructions for fast quantitative susceptibility mapping." MIDL.

Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

Zhang, H., Zhang, J., Wang, R., Zhang, Q., Gauthier, S.A., Spincemaille, P., Nguyen, T.D. and Wang, Y. (2021). "Geometric Loss for Deep Multiple Sclerosis lesion Segmentation." IEEE ISBI.

Deep neural network for water/fat separation: supervised training, unsupervised training, and no training

Jafari, R., Spincemaille, P., Zhang, J., Nguyen, T.D., Luo, X., Cho, J., Margolis, D., Prince, M.R. and Wang, Y. (2021). "Deep neural network for water/fat separation: supervised training, unsupervised training, and no training." Magnetic Resonance in Medicine, 85(4), 2263-2277.

Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping

Zhang, J., Zhang, H., Sabuncu, M., Spincemaille, P., Nguyen, T. and Wang, Y. (2021). "Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping." Machine Learning for Biomedical Imaging, 1, 1-19.

Efficient Folded Attention for Medical Image Reconstruction and Segmentation

Zhang, H., Zhang, J., Wang, R., Zhang, Q., Spincemaille, P., Nguyen, T.D. and Wang, Y. (2021). "Efficient Folded Attention for Medical Image Reconstruction and Segmentation." AAAI, 35(12), 10868-10876.

ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation

Zhang, H., Zhang, J., Li, C., Sweeney, E.M., Spincemaille, P., Nguyen, T.D., Gauthier, S.A., Wang, Y. and Marcille, M. (2021). "ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation." NeuroImage: Clinical, 32, 102854.