Shuo Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shuo Han has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
- Jerry L. Prince
Johns Hopkins University
7 shared publications - Aaron Carass
Johns Hopkins University
6 shared publications Jerry L. Prince
Department of Biomedical Engineering, The Johns Hopkins University, Baltimore, MD 21218
5 shared publicationsAaron Carass
Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218
4 shared publications- Peter Arthur Calabresi
Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
3 shared publications Yufan He
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA
3 shared publications
Latest Publications
- Open Access
- 1 March 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (02) , 1-17
ECLARE: efficient cross-planar learning for anisotropic resolution enhancement
PurposeIn clinical imaging, magnetic resonance (MR) image volumes are often acquired as stacks of 2D slices with decreased scan times, improved signal-to-noise ratio, and image contrasts unique to 2D MR pulse sequences. Although this is sufficient for clinical evaluation, automated algorithms designed for 3D analysis perform poorly on multislice 2D MR volumes, especially those with thick slices and gaps between slices. Superresolution (SR) methods aim to address this problem, but previous methods do not address all of the following: slice profile shape estimation, slice gap, domain shift, and noninteger or arbitrary upsampling factors.ApproachWe propose ECLARE (Efficient Cross-planar Learning for Anisotropic Resolution Enhancement), a self-SR method that addresses each of these factors. ECLARE uses a slice profile estimated from the multislice 2D MR volume, trains a network to learn the mapping from low-resolution to high-resolution in-plane patches from the same volume, performs SR with antialiasing, and respects the image FOV during resampling. We compared ECLARE with cubic B-spline interpolation, SMORE, and other contemporary SR methods. We used realistic and representative simulations on human head MR volumes so that quantitative performance against ground truth can be computed. Specifically, healthy T1-w and people with MS T2-w FLAIR datasets were used for evaluations. We used the peak signal-to-noise ratio and structural similarity index measure as signal recovery metrics. We additionally used two independent brain parcellation algorithms, SLANT and SynthSeg, to compute the consistency Dice similarity coefficient and the R2 coefficient of determination, respectively, as comparison metrics.ResultsFor images with up to 5 mm of slice thickness and up to 1.5 mm of gap, ECLARE achieves greater mean PSNR and SSIM compared with other methods. In representative regions of interest, such as the ventricles, caudate, cerebral white matter, and cerebellar white matter, ECLARE performs comparably or better than other approaches. These trends are similar for both investigated datasets.ConclusionsThe use of slice profile estimation, FOV-aware resampling, and self-SR allowed ECLARE to robustly superresolve anisotropic images without the need for external training data. Future work will investigate the utility of ECLARE on other organs, species, modalities, and resolutions. Our code is open-source and available at https://www.github.com/sremedios/eclare.
- 1 March 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (02) , 1-17
Open AccessECLARE: efficient cross-planar learning for anisotropic resolution enhancement
PurposeIn clinical imaging, magnetic resonance (MR) image volumes are often acquired as stacks of 2D slices with decreased scan times, improved signal-to-noise ratio, and image contrasts unique to 2D MR pulse sequences. Although this is sufficient for clinical evaluation, automated algorithms designed for 3D analysis perform poorly on multislice 2D MR volumes, especially those with thick slices and gaps between slices. Superresolution (SR) methods aim to address this problem, but previous methods do not address all of the following: slice profile shape estimation, slice gap, domain shift, and noninteger or arbitrary upsampling factors.ApproachWe propose ECLARE (Efficient Cross-planar Learning for Anisotropic Resolution Enhancement), a self-SR method that addresses each of these factors. ECLARE uses a slice profile estimated from the multislice 2D MR volume, trains a network to learn the mapping from low-resolution to high-resolution in-plane patches from the same volume, performs SR with antialiasing, and respects the image FOV during resampling. We compared ECLARE with cubic B-spline interpolation, SMORE, and other contemporary SR methods. We used realistic and representative simulations on human head MR volumes so that quantitative performance against ground truth can be computed. Specifically, healthy T1-w and people with MS T2-w FLAIR datasets were used for evaluations. We used the peak signal-to-noise ratio and structural similarity index measure as signal recovery metrics. We additionally used two independent brain parcellation algorithms, SLANT and SynthSeg, to compute the consistency Dice similarity coefficient and the R2 coefficient of determination, respectively, as comparison metrics.ResultsFor images with up to 5 mm of slice thickness and up to 1.5 mm of gap, ECLARE achieves greater mean PSNR and SSIM compared with other methods. In representative regions of interest, such as the ventricles, caudate, cerebral white matter, and cerebellar white matter, ECLARE performs comparably or better than other approaches. These trends are similar for both investigated datasets.ConclusionsThe use of slice profile estimation, FOV-aware resampling, and self-SR allowed ECLARE to robustly superresolve anisotropic images without the need for external training data. Future work will investigate the utility of ECLARE on other organs, species, modalities, and resolutions. Our code is open-source and available at https://www.github.com/sremedios/eclare.
- Open Access
A Core Pattern of Cerebellar and Brainstem Degeneration and Reduced Cerebrocerebellar Structural Covariance in Spinocerebellar Ataxia Type 3 (SCA3): MRI Volumetrics from ENIGMA-Ataxia
Objective: Spinocerebellar ataxia type 3 (SCA3) is a rare, inherited neurodegenerative disease. Here, we profile the spatial spread of atrophy across the whole brain, determine whether brain degeneration preferentially maps onto specific functional networks, and investigate the relationship between cerebellar and cerebral anatomical changes. Methods: Whole-brain grey and white matter (GM and WM) voxel-based morphometry was performed on 408 individuals with SCA3 (82 pre-ataxic) and 293 controls. The SCA3 cohort was stratified by ataxia severity to investigate disease progression, with cerebellar GM atrophy mapped onto a task-based functional atlas. Volume was correlated with disease duration and intensity. Cerebrocerebellar volumetric covariance was assessed to determine whether atrophy was coupled between infra- and supratentorial regions. Results: The pattern of atrophy is spatially consistent but progressive in magnitude across the disease course. The greatest atrophy was found in the pons, cerebellar WM, and cerebellar peduncles; correlations with disease severity and duration were also strongest in these regions. Cerebellar GM atrophy was greatest in functional regions associated with motor execution and planning, attention, and emotional processing. Sparse cerebral cortical atrophy appears only in the most severe disease subgroup, while striatal atrophy begins in the earliest stages. Reduced cerebrocerebellar structural covariance is observed in SCA3 participants versus controls. Interpretation: While cerebellar and brainstem atrophy become more severe, the pattern of atrophy remains largely consistent as SCA3 progresses. Cerebellar GM degeneration occurs in regions associated with motor, cognitive, and affective control, in line with clinical presentation. Cerebellar atrophy is not directly mirrored by cerebral changes.
Open AccessA Core Pattern of Cerebellar and Brainstem Degeneration and Reduced Cerebrocerebellar Structural Covariance in Spinocerebellar Ataxia Type 3 (SCA3): MRI Volumetrics from ENIGMA-Ataxia
Objective: Spinocerebellar ataxia type 3 (SCA3) is a rare, inherited neurodegenerative disease. Here, we profile the spatial spread of atrophy across the whole brain, determine whether brain degeneration preferentially maps onto specific functional networks, and investigate the relationship between cerebellar and cerebral anatomical changes. Methods: Whole-brain grey and white matter (GM and WM) voxel-based morphometry was performed on 408 individuals with SCA3 (82 pre-ataxic) and 293 controls. The SCA3 cohort was stratified by ataxia severity to investigate disease progression, with cerebellar GM atrophy mapped onto a task-based functional atlas. Volume was correlated with disease duration and intensity. Cerebrocerebellar volumetric covariance was assessed to determine whether atrophy was coupled between infra- and supratentorial regions. Results: The pattern of atrophy is spatially consistent but progressive in magnitude across the disease course. The greatest atrophy was found in the pons, cerebellar WM, and cerebellar peduncles; correlations with disease severity and duration were also strongest in these regions. Cerebellar GM atrophy was greatest in functional regions associated with motor execution and planning, attention, and emotional processing. Sparse cerebral cortical atrophy appears only in the most severe disease subgroup, while striatal atrophy begins in the earliest stages. Reduced cerebrocerebellar structural covariance is observed in SCA3 participants versus controls. Interpretation: While cerebellar and brainstem atrophy become more severe, the pattern of atrophy remains largely consistent as SCA3 progresses. Cerebellar GM degeneration occurs in regions associated with motor, cognitive, and affective control, in line with clinical presentation. Cerebellar atrophy is not directly mirrored by cerebral changes.
- Open Access
- 16 January 2025
- Published by MDPI AG in Brain Sciences
- Vol. 15 (1) , 77
Cerebellar Volume Measures Differentiate Multiple Sclerosis Fallers from Non-Fallers
Introduction: The cerebellum is a common lesion site in persons with multiple sclerosis (PwMS). Physiologic and anatomic studies have identified a topographic organization of the cerebellum including functionally distinct motor and cognitive areas. In this study, a recent parcellation algorithm was applied to a sample of PwMS and healthy controls to examine the relationships among specific cerebellar regions, fall status, and common clinical measures of motor and cognitive functions. Methods: Thirty-one PwMS and twenty-nine age- and sex-matched controls underwent an MRI scan and motor and cognitive testing. The parcellation algorithm was applied to all images and divided the cerebellum into 28 regions. Mann–Whitney U tests were used to compare cerebellar volumes among PwMS and controls, and MS fallers and MS non-fallers. Relationships between cerebellar volumes and motor and cognitive function were evaluated using Spearman correlations. Results: PwMS performed significantly worse on functional measures compared to controls. We found significant differences in volumetric measures between PwMS and controls in the corpus medullare, lobules I–III, and lobule V. Volumetric differences seen between the PwMS and controls were primarily driven by the MS fallers. Finally, functional performance on motor and cognitive tasks was associated with cerebellar volumes. Conclusions: Using the parcellation tool, our results showed that the volumes of motor and cognitive lobules impact both motor and cognitive performance, and that functional performance and cerebellar volumes distinguishes the MS fallers from non-fallers. Future studies should explore the potential of cerebellar imaging to predict falls in PwMS.
- 16 January 2025
- Published by MDPI AG in Brain Sciences
- Vol. 15 (1) , 77
Open AccessCerebellar Volume Measures Differentiate Multiple Sclerosis Fallers from Non-Fallers
Introduction: The cerebellum is a common lesion site in persons with multiple sclerosis (PwMS). Physiologic and anatomic studies have identified a topographic organization of the cerebellum including functionally distinct motor and cognitive areas. In this study, a recent parcellation algorithm was applied to a sample of PwMS and healthy controls to examine the relationships among specific cerebellar regions, fall status, and common clinical measures of motor and cognitive functions. Methods: Thirty-one PwMS and twenty-nine age- and sex-matched controls underwent an MRI scan and motor and cognitive testing. The parcellation algorithm was applied to all images and divided the cerebellum into 28 regions. Mann–Whitney U tests were used to compare cerebellar volumes among PwMS and controls, and MS fallers and MS non-fallers. Relationships between cerebellar volumes and motor and cognitive function were evaluated using Spearman correlations. Results: PwMS performed significantly worse on functional measures compared to controls. We found significant differences in volumetric measures between PwMS and controls in the corpus medullare, lobules I–III, and lobule V. Volumetric differences seen between the PwMS and controls were primarily driven by the MS fallers. Finally, functional performance on motor and cognitive tasks was associated with cerebellar volumes. Conclusions: Using the parcellation tool, our results showed that the volumes of motor and cognitive lobules impact both motor and cognitive performance, and that functional performance and cerebellar volumes distinguishes the MS fallers from non-fallers. Future studies should explore the potential of cerebellar imaging to predict falls in PwMS.
- Open Access
- 21 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (12) , 3686-3698
Disentangled Representation Learning for OCTA Vessel Segmentation With Limited Training Data
Optical coherence tomography angiography (OCTA) is an imaging modality that can be used for analyzing retinal vasculature. Quantitative assessment of en face OCTA images requires accurate segmentation of the capillaries. Using deep learning approaches for this task faces two major challenges. First, acquiring sufficient manual delineations for training can take hundreds of hours. Second, OCTA images suffer from numerous contrast-related artifacts that are currently inherent to the modality and vary dramatically across scanners. We propose to solve both problems by learning a disentanglement of an anatomy component and a local contrast component from paired OCTA scans. With the contrast removed from the anatomy component, a deep learning model that takes the anatomy component as input can learn to segment vessels with a limited portion of the training images being manually labeled. Our method demonstrates state-of-the-art performance for OCTA vessel segmentation.
- 21 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (12) , 3686-3698
Open AccessDisentangled Representation Learning for OCTA Vessel Segmentation With Limited Training Data
Optical coherence tomography angiography (OCTA) is an imaging modality that can be used for analyzing retinal vasculature. Quantitative assessment of en face OCTA images requires accurate segmentation of the capillaries. Using deep learning approaches for this task faces two major challenges. First, acquiring sufficient manual delineations for training can take hundreds of hours. Second, OCTA images suffer from numerous contrast-related artifacts that are currently inherent to the modality and vary dramatically across scanners. We propose to solve both problems by learning a disentanglement of an anatomy component and a local contrast component from paired OCTA scans. With the contrast removed from the anatomy component, a deep learning model that takes the anatomy component as input can learn to segment vessels with a limited portion of the training images being manually labeled. Our method demonstrates state-of-the-art performance for OCTA vessel segmentation.
- Open Access
- 4 April 2022
- Published by SPIE-Intl Soc Optical Eng in Proceedings of SPIE
- Vol. 12032, 43
Cranial meninges reconstruction based on convolutional networks and deformable models: applications to longitudinal study of normal aging
SPIE Digital Library Proceedings
- 4 April 2022
- Published by SPIE-Intl Soc Optical Eng in Proceedings of SPIE
- Vol. 12032, 43
Open AccessCranial meninges reconstruction based on convolutional networks and deformable models: applications to longitudinal study of normal aging
SPIE Digital Library Proceedings
- 14 June 2021
- Published by Springer Nature
- p. 108-119
MR Slice Profile Estimation by Learning to Match Internal Patch Distributions
- 14 June 2021
- Published by Springer Nature
- p. 108-119
MR Slice Profile Estimation by Learning to Match Internal Patch Distributions
- 13 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 27, 145-149
Slice Profile Estimation From 2D MRI Acquisition Using Generative Adversarial Networks
To save time and maintain an adequate signal-to-noise ratio, magnetic resonance (MR) images are often acquired with better in-plane than through-plane resolutions in 2D acquisition. To improve image quality, recent work has focused on using deep learning to super-resolve the through-plane resolution. To create training data, images can be degraded in an in-plane direction to match the through-plane resolution. To do this correctly, the slice selection profile (SSP) should be known, but this is rarely possible since precise details of signal excitation are usually unknown. Therefore, estimating the SSP of an image volume is desired. In this work, we first show that a relative SSP can be estimated from the difference between in- and through-plane image patches. We further propose an algorithm that uses generative adversarial networks (GAN) to estimate the SSP. In this algorithm, the GAN’s generator blurs in-plane patches in one direction using an estimated relative SSP then downsamples them. The GAN’s discriminator distinguishes the generator’s output from real through-plane patches. The proposed method was validated using numerical simulations and phantom and brain scans. To our knowledge, it is the first work to estimate the SSP from a single MR image. The code is available at https://github.com/shuohan/espreso.
- 13 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 27, 145-149
Slice Profile Estimation From 2D MRI Acquisition Using Generative Adversarial Networks
To save time and maintain an adequate signal-to-noise ratio, magnetic resonance (MR) images are often acquired with better in-plane than through-plane resolutions in 2D acquisition. To improve image quality, recent work has focused on using deep learning to super-resolve the through-plane resolution. To create training data, images can be degraded in an in-plane direction to match the through-plane resolution. To do this correctly, the slice selection profile (SSP) should be known, but this is rarely possible since precise details of signal excitation are usually unknown. Therefore, estimating the SSP of an image volume is desired. In this work, we first show that a relative SSP can be estimated from the difference between in- and through-plane image patches. We further propose an algorithm that uses generative adversarial networks (GAN) to estimate the SSP. In this algorithm, the GAN’s generator blurs in-plane patches in one direction using an estimated relative SSP then downsamples them. The GAN’s discriminator distinguishes the generator’s output from real through-plane patches. The proposed method was validated using numerical simulations and phantom and brain scans. To our knowledge, it is the first work to estimate the SSP from a single MR image. The code is available at https://github.com/shuohan/espreso.
- Top Cited Papers
- 1 April 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 69, 101950
CHAOS Challenge - combined (CT-MR) healthy abdominal organ segmentation
- 1 April 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 69, 101950
Top Cited PapersCHAOS Challenge - combined (CT-MR) healthy abdominal organ segmentation
- Open Access
- 1 October 2020
- Published by Elsevier in NeuroImage
- Vol. 220, 117062
Longitudinal analysis of regional cerebellum volumes during normal aging
- 1 October 2020
- Published by Elsevier in NeuroImage
- Vol. 220, 117062
Open AccessLongitudinal analysis of regional cerebellum volumes during normal aging
- 29 September 2020
- Published by Springer Nature
- p. 404-413
Inhomogeneity Correction in Magnetic Resonance Images Using Deep Image Priors
- 29 September 2020
- Published by Springer Nature
- p. 404-413
Inhomogeneity Correction in Magnetic Resonance Images Using Deep Image Priors