Heran Yang
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
Heran Yang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Jian Sun
Xi’an Jiaotong University
8 shared publications Zongben Xu
School of Mathematics and Statistics, Xian Jiaotong University, Xian, China
4 shared publications- Aaron Carass
Johns Hopkins University
1 shared publication - Can Zhao
NVIDIA, Santa Clara, CA, USA
1 shared publication - Changzheng Chen
School of Mechanical Engineering, Shenyang University of Technology, Shenyang, China
1 shared publication - Chunfeng Lian
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China
1 shared publication
Latest Publications
- 20 September 2025
- Published by Springer Nature
- p. 392-401
MRI Motion Artifact Correction via Frequency-Assisted Artifact Disentanglement and Confidence-Guided Knowledge Distillation
- 20 September 2025
- Published by Springer Nature
- p. 392-401
MRI Motion Artifact Correction via Frequency-Assisted Artifact Disentanglement and Confidence-Guided Knowledge Distillation
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (11) , 4131-4142
Domain-Generalized Discrete Diffusion Model for Cross-Domain Medical Image Segmentation
Domain shift is a significant challenge in medical image segmentation, primarily due to variations in image acquisition protocols, modalities, etc. Domain shift often causes models trained on a source domain to perform poorly on unseen target domains. In this work, we introduce the Domain-Generalized Discrete Diffusion Model for Segmentation (DG-DDM-Seg), a diffusion-based generative model designed for single-source domain generalization in medical image segmentation. DG-DDM-Seg generates discrete conditional distributions of segmentation masks. To ensure domain independence, we employ two key strategies: 1) We extract robust features from conditional images to enhance the domain independence of diffusion model. 2) We use both conditional images and pseudo-labels as inputs to improve cross-domain segmentation performance. Along this idea, we propose a two-path reverse diffusion process during training, utilizing Robust Feature Extraction Subnet and Mask-Generation Transformer to learn a domain-generalized discrete conditional distribution based on robust image features and pseudo-labels. This learned distribution is then used to generate segmentation masks for unseen target domains. Experimental results demonstrate that DG-DDM-Seg achieves state-of-the-art performance in cross-domain medical image segmentation, with domain shifts in modality, sequence, and site. The code is available at https://github.com/HeranYang/DG-DDM-Seg.
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (11) , 4131-4142
Domain-Generalized Discrete Diffusion Model for Cross-Domain Medical Image Segmentation
Domain shift is a significant challenge in medical image segmentation, primarily due to variations in image acquisition protocols, modalities, etc. Domain shift often causes models trained on a source domain to perform poorly on unseen target domains. In this work, we introduce the Domain-Generalized Discrete Diffusion Model for Segmentation (DG-DDM-Seg), a diffusion-based generative model designed for single-source domain generalization in medical image segmentation. DG-DDM-Seg generates discrete conditional distributions of segmentation masks. To ensure domain independence, we employ two key strategies: 1) We extract robust features from conditional images to enhance the domain independence of diffusion model. 2) We use both conditional images and pseudo-labels as inputs to improve cross-domain segmentation performance. Along this idea, we propose a two-path reverse diffusion process during training, utilizing Robust Feature Extraction Subnet and Mask-Generation Transformer to learn a domain-generalized discrete conditional distribution based on robust image features and pseudo-labels. This learned distribution is then used to generate segmentation masks for unseen target domains. Experimental results demonstrate that DG-DDM-Seg achieves state-of-the-art performance in cross-domain medical image segmentation, with domain shifts in modality, sequence, and site. The code is available at https://github.com/HeranYang/DG-DDM-Seg.
- 7 March 2025
- Published by Elsevier in Pattern Recognition
- Vol. 164
Meta-learning of pseudo force field generation and estimation for enhancing 3D molecular property prediction
- 7 March 2025
- Published by Elsevier in Pattern Recognition
- Vol. 164
Meta-learning of pseudo force field generation and estimation for enhancing 3D molecular property prediction
- 30 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 9 (25730436) , 1018-1030
MD-GraphFormer: A Model-Driven Graph Transformer for Fast Multi-Contrast MR Imaging
In magnetic resonance imaging (MRI), multi-contrast pulse sequences are routinely acquired, providing complementary information for medical diagnosis. Compared with the single-contrast MR image reconstruction, the multi-contrast MR imaging could further accelerate data acquisition and improve reconstruction quality by leveraging the complementary information of multi-contrast MR images. In this paper, we propose a model-driven graph transformer (MD-GraphFormer) for fast multi-contrast MR imaging, which incorporates the physical constraints of MRI and investigates the complementary information among multi-contrast MR images using graph structure and attention mechanism. The MD-GraphFormer consists of graph-attention-based interaction modules (GAB-IM) and multi-contrast data consistency modules (MC-DCM). GAB-IM learns and interacts the features of multi-contrast MR images over the graph with nodes representing MR contrasts. MC-DCM enforces the consistency between the reconstructed multi-contrast MR images and their corresponding measurements in k-space. Extensive experiments are conducted on the collected raw uMR and SMS brain MRI datasets under different sampling patterns and sampling rates. The results demonstrate that the proposed MD-GraphFormer outperforms the previous multi-contrast MRI reconstruction methods in multi-coil imaging settings.
- 30 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 9 (25730436) , 1018-1030
MD-GraphFormer: A Model-Driven Graph Transformer for Fast Multi-Contrast MR Imaging
In magnetic resonance imaging (MRI), multi-contrast pulse sequences are routinely acquired, providing complementary information for medical diagnosis. Compared with the single-contrast MR image reconstruction, the multi-contrast MR imaging could further accelerate data acquisition and improve reconstruction quality by leveraging the complementary information of multi-contrast MR images. In this paper, we propose a model-driven graph transformer (MD-GraphFormer) for fast multi-contrast MR imaging, which incorporates the physical constraints of MRI and investigates the complementary information among multi-contrast MR images using graph structure and attention mechanism. The MD-GraphFormer consists of graph-attention-based interaction modules (GAB-IM) and multi-contrast data consistency modules (MC-DCM). GAB-IM learns and interacts the features of multi-contrast MR images over the graph with nodes representing MR contrasts. MC-DCM enforces the consistency between the reconstructed multi-contrast MR images and their corresponding measurements in k-space. Extensive experiments are conducted on the collected raw uMR and SMS brain MRI datasets under different sampling patterns and sampling rates. The results demonstrate that the proposed MD-GraphFormer outperforms the previous multi-contrast MRI reconstruction methods in multi-coil imaging settings.
- 4 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (12) , 3678-3689
Learning Unified Hyper-Network for Multi-Modal MR Image Synthesis and Tumor Segmentation With Missing Modalities
Accurate segmentation of brain tumors is of critical importance in clinical assessment and treatment planning, which requires multiple MR modalities providing complementary information. However, due to practical limits, one or more modalities may be missing in real scenarios. To tackle this problem, existing methods need to train multiple networks or a unified but fixed network for various possible missing modality cases, which leads to high computational burdens or sub-optimal performance. In this paper, we propose a unified and adaptive multi-modal MR image synthesis method, and further apply it to tumor segmentation with missing modalities. Based on the decomposition of multi-modal MR images into common and modality-specific features, we design a shared hyper-encoder for embedding each available modality into the feature space, a graph-attention-based fusion block to aggregate the features of available modalities to the fused features, and a shared hyper-decoder for image reconstruction. We also propose an adversarial common feature constraint to enforce the fused features to be in a common space. As for missing modality segmentation, we first conduct the feature-level and image-level completion using our synthesis method and then segment the tumors based on the completed MR images together with the extracted common features. Moreover, we design a hypernet-based modulation module to adaptively utilize the real and synthetic modalities. Experimental results suggest that our method can not only synthesize reasonable multi-modal MR images, but also achieve state-of-the-art performance on brain tumor segmentation with missing modalities.
- 4 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (12) , 3678-3689
Learning Unified Hyper-Network for Multi-Modal MR Image Synthesis and Tumor Segmentation With Missing Modalities
Accurate segmentation of brain tumors is of critical importance in clinical assessment and treatment planning, which requires multiple MR modalities providing complementary information. However, due to practical limits, one or more modalities may be missing in real scenarios. To tackle this problem, existing methods need to train multiple networks or a unified but fixed network for various possible missing modality cases, which leads to high computational burdens or sub-optimal performance. In this paper, we propose a unified and adaptive multi-modal MR image synthesis method, and further apply it to tumor segmentation with missing modalities. Based on the decomposition of multi-modal MR images into common and modality-specific features, we design a shared hyper-encoder for embedding each available modality into the feature space, a graph-attention-based fusion block to aggregate the features of available modalities to the fused features, and a shared hyper-decoder for image reconstruction. We also propose an adversarial common feature constraint to enforce the fused features to be in a common space. As for missing modality segmentation, we first conduct the feature-level and image-level completion using our synthesis method and then segment the tumors based on the completed MR images together with the extracted common features. Moreover, we design a hypernet-based modulation module to adaptively utilize the real and synthetic modalities. Experimental results suggest that our method can not only synthesize reasonable multi-modal MR images, but also achieve state-of-the-art performance on brain tumor segmentation with missing modalities.
- 16 September 2022
- Published by Springer Nature
- p. 183-192
Modality-Adaptive Feature Interaction for Brain Tumor Segmentation with Missing Modalities
- 16 September 2022
- Published by Springer Nature
- p. 183-192
Modality-Adaptive Feature Interaction for Brain Tumor Segmentation with Missing Modalities
- Top Cited Papers
- 11 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39 (12) , 4249-4261
Unsupervised MR-to-CT Synthesis Using Structure-Constrained CycleGAN
Synthesizing a CT image from an available MR image has recently emerged as a key goal in radiotherapy treatment planning for cancer patients. CycleGANs have achieved promising results on unsupervised MR-to-CT image synthesis; however, because they have no direct constraints between input and synthetic images, cycleGANs do not guarantee structural consistency between these two images. This means that anatomical geometry can be shifted in the synthetic CT images, clearly a highly undesirable outcome in the given application. In this paper, we propose a structure-constrained cycleGAN for unsupervised MR-to-CT synthesis by defining an extra structure-consistency loss based on the modality independent neighborhood descriptor. We also utilize a spectral normalization technique to stabilize the training process and a self-attention module to model the long-range spatial dependencies in the synthetic images. Results on unpaired brain and abdomen MR-to-CT image synthesis show that our method produces better synthetic CT images in both accuracy and visual quality as compared to other unsupervised synthesis methods. We also show that an approximate affine pre-registration for unpaired training data can improve synthesis results.
- 11 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39 (12) , 4249-4261
Top Cited PapersUnsupervised MR-to-CT Synthesis Using Structure-Constrained CycleGAN
Synthesizing a CT image from an available MR image has recently emerged as a key goal in radiotherapy treatment planning for cancer patients. CycleGANs have achieved promising results on unsupervised MR-to-CT image synthesis; however, because they have no direct constraints between input and synthetic images, cycleGANs do not guarantee structural consistency between these two images. This means that anatomical geometry can be shifted in the synthetic CT images, clearly a highly undesirable outcome in the given application. In this paper, we propose a structure-constrained cycleGAN for unsupervised MR-to-CT synthesis by defining an extra structure-consistency loss based on the modality independent neighborhood descriptor. We also utilize a spectral normalization technique to stabilize the training process and a self-attention module to model the long-range spatial dependencies in the synthetic images. Results on unpaired brain and abdomen MR-to-CT image synthesis show that our method produces better synthetic CT images in both accuracy and visual quality as compared to other unsupervised synthesis methods. We also show that an approximate affine pre-registration for unpaired training data can improve synthesis results.
- 28 June 2019
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 30 (8) , 085006
An on-machine precision measurement method for API threads
The difficulty in assembling or disassembling a long and heavy drill pipe makes it unsuitable to measure parameters of the American Petroleum Institute (API) threads at both ends of the drill pipe. Accordingly, in this paper we propose an on-machine precision measurement method based on a laser displacement sensor (LDS), and then successfully apply it to a certain API thread-repairing machine tool. This method leverages a NC tool rest to drive the LDS so as to acquire the data of the thread axial section contours. Then, the data are reconstructed using a B-spline curve approximation; that is to say, to make the parameterized data better reflect the features of the thread surface, a knot parameterization factor t is introduced to parameterize the LDS data, and the parameterized data are approximated by a B-spline curve using an improved elitist clonal selection algorithm (ECSA). Finally, feature points are extracted using a reconstruction curve, and thread parameters are calculated in real time to determine the machining quality of API threads. Simulation results indicate that the data reconstruction method with parameterization factor t and improved ECSA have high precision in terms of knots adjustment for B-spline curve approximation. A contrastive experiment of NC50 API thread measurement demonstrates that the proposed fitting method can better reflect the features of the thread surface, thereby effectively improving the accuracy of data reconstruction; meanwhile, the experiment also exhibits that the proposed measurement method can complete the on-machine precision measurement of API threads, with a measurement accuracy of ±2 µm and a measurement time of 14.62 s for a 10 mm long thread.
- 28 June 2019
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 30 (8) , 085006
An on-machine precision measurement method for API threads
The difficulty in assembling or disassembling a long and heavy drill pipe makes it unsuitable to measure parameters of the American Petroleum Institute (API) threads at both ends of the drill pipe. Accordingly, in this paper we propose an on-machine precision measurement method based on a laser displacement sensor (LDS), and then successfully apply it to a certain API thread-repairing machine tool. This method leverages a NC tool rest to drive the LDS so as to acquire the data of the thread axial section contours. Then, the data are reconstructed using a B-spline curve approximation; that is to say, to make the parameterized data better reflect the features of the thread surface, a knot parameterization factor t is introduced to parameterize the LDS data, and the parameterized data are approximated by a B-spline curve using an improved elitist clonal selection algorithm (ECSA). Finally, feature points are extracted using a reconstruction curve, and thread parameters are calculated in real time to determine the machining quality of API threads. Simulation results indicate that the data reconstruction method with parameterization factor t and improved ECSA have high precision in terms of knots adjustment for B-spline curve approximation. A contrastive experiment of NC50 API thread measurement demonstrates that the proposed fitting method can better reflect the features of the thread surface, thereby effectively improving the accuracy of data reconstruction; meanwhile, the experiment also exhibits that the proposed measurement method can complete the on-machine precision measurement of API threads, with a measurement accuracy of ±2 µm and a measurement time of 14.62 s for a 10 mm long thread.
- 1 October 2018
- Published by Elsevier in Medical Image Analysis
- Vol. 49, 60-75
Neural multi-atlas label fusion: Application to cardiac MR images
- 1 October 2018
- Published by Elsevier in Medical Image Analysis
- Vol. 49, 60-75
Neural multi-atlas label fusion: Application to cardiac MR images