Hang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hang Zhang has a total of 140 co-authors. Here are the top co-authors by number of shared publications:
- Yi Wang
Department of Radiology Weill Cornell Medicine New York New York USA
10 shared publications - Pascal Spincemaille
Department of Radiology, Weill Cornell Medical College, New York, New York, USA
8 shared publications Renjiu Hu
Cornell University
8 shared publications- Thanh Duc Nguyen
Department of Radiology Weill Cornell Medicine New York New York USA
8 shared publications - Jinwei Zhang
Cornell University
7 shared publications Gaolei Li
Shanghai Jiao Tong University
6 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 3-11
Unsupervised MR-US Multimodal Image Registration with Multilevel Correlation Pyramidal Optimization
- 2 July 2026
- Published by Springer Nature
- p. 3-11
Unsupervised MR-US Multimodal Image Registration with Multilevel Correlation Pyramidal Optimization
- 23 June 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 113, 104175
Beyond the LUMIR challenge: The pathway to foundational registration models
- 23 June 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 113, 104175
Beyond the LUMIR challenge: The pathway to foundational registration models
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (02780062) , 1
Neural Optimization for Image Registration via Joint Modeling of Global Affine and Local Deformation Transformations
Conventional registration approaches frequently underperform when applied to sparse feature alignment (e.g., retinal vessels and filamentous collagen fibers in second-harmonic generation (SHG) and bright-field (BF) images), as these tasks demand simultaneous handling of global affine registration and local deformation correction. End-to-end learning-based approaches struggle with minimal effective gradients from loss back-propagation of these sparse features, while descriptor matching methods, though helpful, lack fidelity loss and fail to adapt to local deformation. To address these issues, we propose Neural Affine Optimization (NeOn), which implicitly approximates discrete optimization using a few neural network layers, combined with a sampling-regression layer to handle affine transformations. NeOn allows iterative refinement with fidelity loss and provides a flexible transition between a purely affine configuration and a linear weighted blend of affine and deformation fields. NeOn’s performance was validated on four public datasets. In multi-modal SHG-BF microscopy registration, NeOn achieved top rankings on the validation leaderboard for Task 3 of the Learn2Reg Challenge 2024. For retinal image registration, NeOn outperformed existing methods on both mono-modal and multi-modal datasets, reducing target registration error from 6.3 to 2.1 pixels in mono-modal and from 2.6 to 1.8 pixels in multi-modal registration. Furthermore, NeOn demonstrates strong generalization and can be effectively extended to 3D multi-modality image registration scenarios.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (02780062) , 1
Neural Optimization for Image Registration via Joint Modeling of Global Affine and Local Deformation Transformations
Conventional registration approaches frequently underperform when applied to sparse feature alignment (e.g., retinal vessels and filamentous collagen fibers in second-harmonic generation (SHG) and bright-field (BF) images), as these tasks demand simultaneous handling of global affine registration and local deformation correction. End-to-end learning-based approaches struggle with minimal effective gradients from loss back-propagation of these sparse features, while descriptor matching methods, though helpful, lack fidelity loss and fail to adapt to local deformation. To address these issues, we propose Neural Affine Optimization (NeOn), which implicitly approximates discrete optimization using a few neural network layers, combined with a sampling-regression layer to handle affine transformations. NeOn allows iterative refinement with fidelity loss and provides a flexible transition between a purely affine configuration and a linear weighted blend of affine and deformation fields. NeOn’s performance was validated on four public datasets. In multi-modal SHG-BF microscopy registration, NeOn achieved top rankings on the validation leaderboard for Task 3 of the Learn2Reg Challenge 2024. For retinal image registration, NeOn outperformed existing methods on both mono-modal and multi-modal datasets, reducing target registration error from 6.3 to 2.1 pixels in mono-modal and from 2.6 to 1.8 pixels in multi-modal registration. Furthermore, NeOn demonstrates strong generalization and can be effectively extended to 3D multi-modality image registration scenarios.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8862-8873
Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8862-8873
Open AccessEgocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 7035-7049
Encoder-Only Image Registration
Learning-based techniques have significantly improved the accuracy and speed of deformable image registration. However, challenges such as reducing computational complexity and handling large deformations persist. To address these challenges, we analyze how convolutional neural networks (ConvNets) influence registration performance using the Horn-Schunck optical flow equation. Supported by prior studies and our empirical experiments, we observe that ConvNets play two key roles in registration: linearizing local intensities and harmonizing global contrast variations. Guided by these insights, we propose the Encoder-Only Image Registration (EOIR) framework comprising five modifications to existing approaches, to achieve a better accuracy-efficiency trade-off. EOIR separates feature learning from flow estimation, employing only a 3-layer ConvNet for feature extraction and a set of 3-layer flow estimators to construct a Laplacian feature pyramid, progressively composing diffeomorphic deformations under a large-deformation model. Results on six datasets across different modalities and anatomical regions demonstrate EOIR’s effectiveness, achieving superior accuracy-efficiency and accuracy-smoothness trade-offs. With comparable accuracy, EOIR provides better efficiency and smoothness, and vice versa. The source code of EOIR is available on Github.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 7035-7049
Encoder-Only Image Registration
Learning-based techniques have significantly improved the accuracy and speed of deformable image registration. However, challenges such as reducing computational complexity and handling large deformations persist. To address these challenges, we analyze how convolutional neural networks (ConvNets) influence registration performance using the Horn-Schunck optical flow equation. Supported by prior studies and our empirical experiments, we observe that ConvNets play two key roles in registration: linearizing local intensities and harmonizing global contrast variations. Guided by these insights, we propose the Encoder-Only Image Registration (EOIR) framework comprising five modifications to existing approaches, to achieve a better accuracy-efficiency trade-off. EOIR separates feature learning from flow estimation, employing only a 3-layer ConvNet for feature extraction and a set of 3-layer flow estimators to construct a Laplacian feature pyramid, progressively composing diffeomorphic deformations under a large-deformation model. Results on six datasets across different modalities and anatomical regions demonstrate EOIR’s effectiveness, achieving superior accuracy-efficiency and accuracy-smoothness trade-offs. With comparable accuracy, EOIR provides better efficiency and smoothness, and vice versa. The source code of EOIR is available on Github.
- 19 September 2025
- Published by Springer Nature
- p. 218-228
Gaussian Primitive Optimized Deformable Retinal Image Registration
- 19 September 2025
- Published by Springer Nature
- p. 218-228
Gaussian Primitive Optimized Deformable Retinal Image Registration
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 619-627
GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models
Graph learning models have been empirically proven to be vulnerable to backdoor threats, wherein adversaries submit trigger-embedded inputs to manipulate the model predictions. Current graph backdoor defenses manifest several limitations: 1) dependence on model-related details, 2) necessitation of additional fine-tuning, and 3) reliance on extra explainability tools, all of which are infeasible under stringent privacy policies. To address those limitations, we propose GraphProt, a certified black-box defense method to suppress backdoor attacks on GNN-based graph classifiers. Our GraphProt operates in a model-agnostic manner and solely leverages graph input. Specifically, GraphProt first introduces designed topology-feature-filtration to mitigate graph anomalies. Subsequently, subgraphs are sampled via a formulated strategy integrating topology and features, followed by a robust model inference through a majority vote-based subgraph prediction ensemble. Our results across benchmark attacks and datasets show GraphProt effectively reduces attack success rates while preserving regular graph classification accuracy.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 619-627
Open AccessGraphProt: Certified Black-Box Shielding Against Backdoored Graph Models
Graph learning models have been empirically proven to be vulnerable to backdoor threats, wherein adversaries submit trigger-embedded inputs to manipulate the model predictions. Current graph backdoor defenses manifest several limitations: 1) dependence on model-related details, 2) necessitation of additional fine-tuning, and 3) reliance on extra explainability tools, all of which are infeasible under stringent privacy policies. To address those limitations, we propose GraphProt, a certified black-box defense method to suppress backdoor attacks on GNN-based graph classifiers. Our GraphProt operates in a model-agnostic manner and solely leverages graph input. Specifically, GraphProt first introduces designed topology-feature-filtration to mitigate graph anomalies. Subsequently, subgraphs are sampled via a formulated strategy integrating topology and features, followed by a robust model inference through a majority vote-based subgraph prediction ensemble. Our results across benchmark attacks and datasets show GraphProt effectively reduces attack success rates while preserving regular graph classification accuracy.
- Open Access
Gaussian Primitive Optimized Deformable Retinal Image Registration
Deformable retinal image registration is notoriously difficult due to large homogeneous regions and sparse but critical vascular features, which cause limited gradient signals in standard learning-based frameworks. In this paper, we introduce Gaussian Primitive Optimization (GPO), a novel iterative framework that performs structured message passing to overcome these challenges. After an initial coarse alignment, we extract keypoints at salient anatomical structures (e.g., major vessels) to serve as a minimal set of descriptor-based control nodes (DCN). Each node is modelled as a Gaussian primitive with trainable position, displacement, and radius, thus adapting its spatial influence to local deformation scales. A K-Nearest Neighbors (KNN) Gaussian interpolation then blends and propagates displacement signals from these information-rich nodes to construct a globally coherent displacement field; focusing interpolation on the top (K) neighbors reduces computational overhead while preserving local detail. By strategically anchoring nodes in high-gradient regions, GPO ensures robust gradient flow, mitigating vanishing gradient signal in textureless areas. The framework is optimized end-to-end via a multi-term loss that enforces both keypoint consistency and intensity alignment. Experiments on the FIRE dataset show that GPO reduces the target registration error from 6.2\,px to ~2.4\,px and increases the AUC at 25\,px from 0.770 to 0.938, substantially outperforming existing methods. The source code can be accessed via https://github.com/xintian-99/GPOreg.
Open AccessGaussian Primitive Optimized Deformable Retinal Image Registration
Deformable retinal image registration is notoriously difficult due to large homogeneous regions and sparse but critical vascular features, which cause limited gradient signals in standard learning-based frameworks. In this paper, we introduce Gaussian Primitive Optimization (GPO), a novel iterative framework that performs structured message passing to overcome these challenges. After an initial coarse alignment, we extract keypoints at salient anatomical structures (e.g., major vessels) to serve as a minimal set of descriptor-based control nodes (DCN). Each node is modelled as a Gaussian primitive with trainable position, displacement, and radius, thus adapting its spatial influence to local deformation scales. A K-Nearest Neighbors (KNN) Gaussian interpolation then blends and propagates displacement signals from these information-rich nodes to construct a globally coherent displacement field; focusing interpolation on the top (K) neighbors reduces computational overhead while preserving local detail. By strategically anchoring nodes in high-gradient regions, GPO ensures robust gradient flow, mitigating vanishing gradient signal in textureless areas. The framework is optimized end-to-end via a multi-term loss that enforces both keypoint consistency and intensity alignment. Experiments on the FIRE dataset show that GPO reduces the target registration error from 6.2\,px to ~2.4\,px and increases the AUC at 25\,px from 0.770 to 0.938, substantially outperforming existing methods. The source code can be accessed via https://github.com/xintian-99/GPOreg.
- 3 October 2024
- Published by Springer Nature
- p. 671-681
MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters
- 3 October 2024
- Published by Springer Nature
- p. 671-681
MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters
- 20 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 12925-12936
Spatially Covariant Image Registration With Text Prompts
Medical images are often characterized by their structured anatomical representations and spatially inhomogeneous contrasts. Leveraging anatomical priors in neural networks can greatly enhance their utility in resource-constrained clinical settings. Prior research has harnessed such information for image segmentation, yet progress in deformable image registration has been modest. Our work introduces textSCF, a novel method that integrates spatially covariant filters and textual anatomical prompts encoded by visual-language models, to fill this gap. This approach optimizes an implicit function that correlates text embeddings of anatomical regions to filter weights. textSCF not only boosts computational efficiency but can also retain or improve registration accuracy. By capturing the contextual interplay between anatomical regions, it offers impressive interregional transferability and the ability to preserve structural discontinuities during registration. textSCF’s performance has been rigorously tested on intersubject brain magnetic resonance imaging (MRI) and abdominal computerized tomography (CT) registration tasks, outperforming existing state-of-the-art models in the MICCAI Learn2Reg 2021 challenge and leading the leaderboard. In abdominal registrations, textSCF’s larger model variant improved the Dice score by 11.3% over the second-best model, while its smaller variant maintained similar accuracy but with an 89.13% reduction in network parameters and a 98.34% decrease in computational operations.
- 20 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 12925-12936
Spatially Covariant Image Registration With Text Prompts
Medical images are often characterized by their structured anatomical representations and spatially inhomogeneous contrasts. Leveraging anatomical priors in neural networks can greatly enhance their utility in resource-constrained clinical settings. Prior research has harnessed such information for image segmentation, yet progress in deformable image registration has been modest. Our work introduces textSCF, a novel method that integrates spatially covariant filters and textual anatomical prompts encoded by visual-language models, to fill this gap. This approach optimizes an implicit function that correlates text embeddings of anatomical regions to filter weights. textSCF not only boosts computational efficiency but can also retain or improve registration accuracy. By capturing the contextual interplay between anatomical regions, it offers impressive interregional transferability and the ability to preserve structural discontinuities during registration. textSCF’s performance has been rigorously tested on intersubject brain magnetic resonance imaging (MRI) and abdominal computerized tomography (CT) registration tasks, outperforming existing state-of-the-art models in the MICCAI Learn2Reg 2021 challenge and leading the leaderboard. In abdominal registrations, textSCF’s larger model variant improved the Dice score by 11.3% over the second-best model, while its smaller variant maintained similar accuracy but with an 89.13% reduction in network parameters and a 98.34% decrease in computational operations.