Geng Chen
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
Geng Chen has a total of 245 co-authors. Here are the top co-authors by number of shared publications:
- Dinggang Shen
ShanghaiTech University
22 shared publications - Pew-Thian Yap
University of North Carolina at Chapel Hill
12 shared publications - Tao Zhou
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu, China
11 shared publications - Huazhu Fu
Agency for Science, Technology and Research (A*STAR)
9 shared publications - Ling Shao
University of Chinese Academy of Sciences
7 shared publications - Yi Zhou
School of Computer Science and Engineering, Southeast University, Nanjing, China
7 shared publications
Latest Publications
- 20 November 2026
- Published by Elsevier in Medical Image Analysis
ECDM: Efficient Collaborative Diffusion Model for self-supervised diffusion MRI denoising
- 20 November 2026
- Published by Elsevier in Medical Image Analysis
ECDM: Efficient Collaborative Diffusion Model for self-supervised diffusion MRI denoising
- 24 September 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 184
Deep diffusion prior for unsupervised super-resolution of diffusion-weighted images
- 24 September 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 184
Deep diffusion prior for unsupervised super-resolution of diffusion-weighted images
- Open Access
- 10 July 2026
- Published by Springer Nature in npj Digital Medicine
- Vol. 9 (1)
BrainSeg: a generalized framework for comprehensive multimodal brain tissue segmentation, parcellation, and lesion labeling
Precise brain segmentation is fundamental for quantitative neuroimaging analysis. However, most existing methods lack generalization across the human lifespan and diverse imaging modalities, limiting their utility for Comprehensive Brain Segmentation (CBS) (i.e., tissue segmentation, parcellation, and lesion labeling). To address this, we propose BrainSeg, a novel unified framework, for CBS by using large-scale datasets spanning the entire lifespan, with adaptability to diverse uni- and multimodal input scenarios without the need for retraining or finetuning. Comprehensive experiments are conducted on lifespan data ranging from 14 gestational weeks to 100 years of age, consisting of 45,998 multimodal scans from 26 datasets, which are further augmented by our proposed synthesis strategy. Systematic validation and in-depth analysis demonstrate that our BrainSeg can achieve state-of-the-art performance across all three core CBS tasks, with the averaged Dice ratios reaching up to 96.94% for tissue segmentation, 94.25% for brain parcellation, and 91.06% for lesion labeling in the internal validations. It maintains similarly high accuracy in external validations, with averaged Dice ratios achieving 94.01% for tissue segmentation, and 91.20% for brain parcellation, underscoring its robustness and generalizability across diverse conditions. In summary, BrainSeg serves as a versatile foundation tool, providing flexible and reliable analysis for large-scale neuroimaging studies.
- 10 July 2026
- Published by Springer Nature in npj Digital Medicine
- Vol. 9 (1)
Open AccessBrainSeg: a generalized framework for comprehensive multimodal brain tissue segmentation, parcellation, and lesion labeling
Precise brain segmentation is fundamental for quantitative neuroimaging analysis. However, most existing methods lack generalization across the human lifespan and diverse imaging modalities, limiting their utility for Comprehensive Brain Segmentation (CBS) (i.e., tissue segmentation, parcellation, and lesion labeling). To address this, we propose BrainSeg, a novel unified framework, for CBS by using large-scale datasets spanning the entire lifespan, with adaptability to diverse uni- and multimodal input scenarios without the need for retraining or finetuning. Comprehensive experiments are conducted on lifespan data ranging from 14 gestational weeks to 100 years of age, consisting of 45,998 multimodal scans from 26 datasets, which are further augmented by our proposed synthesis strategy. Systematic validation and in-depth analysis demonstrate that our BrainSeg can achieve state-of-the-art performance across all three core CBS tasks, with the averaged Dice ratios reaching up to 96.94% for tissue segmentation, 94.25% for brain parcellation, and 91.06% for lesion labeling in the internal validations. It maintains similarly high accuracy in external validations, with averaged Dice ratios achieving 94.01% for tissue segmentation, and 91.20% for brain parcellation, underscoring its robustness and generalizability across diverse conditions. In summary, BrainSeg serves as a versatile foundation tool, providing flexible and reliable analysis for large-scale neuroimaging studies.
- 3 July 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 126
MSAF-Net: Multi-scale attention fusion network for fetal brain tissue segmentation
- 3 July 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 126
MSAF-Net: Multi-scale attention fusion network for fetal brain tissue segmentation
- 22 May 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Unlocking shared-specific features of multi-modal brain graphs for accurate psychiatric diagnosis
- 22 May 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Unlocking shared-specific features of multi-modal brain graphs for accurate psychiatric diagnosis
- 8 April 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 176
Laplacian-guided contextual instance learning for whole slide image classification
- 8 April 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 176
Laplacian-guided contextual instance learning for whole slide image classification
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (4) , 1584-1595
An Integrated Automatic Framework for Super-Resolution Reconstruction of Motion-Corrupted Fetal Brain MRI With Prior Anatomical Knowledge
Super-resolution reconstruction (SRR) from motion-corrupted thick-slice stacks of fetal brain MR images is essential for comprehensive prenatal examination and precise quantification of fetal brain development. Conventional approaches for fetal brain SRR require human intervention to extract cerebral structures from 2D slices, and their performance is often limited by blurred and less informative acquisitions due to fast scanning or irregular fetal movement. In order to overcome these challenges, we propose an automatic fetal brain SRR framework by integrating both individual- and group-level priors of fetal brain MRI for improved SRR. Specifically, we develop a robust fetal brain extraction approach based on Segment Anything Model (SAM). The extracted fetal brain region is segmented into brain tissues to serve as anatomical prior for the follow-up SRR. The SRR is performed based on an iterative optimization scheme by alternatingly performing slice-to-volume registration and volumetric reconstruction. Specifically, we ingeniously integrate anatomical priors obtained by tissue segmentation into both slice-to-volume registration and volumetric reconstruction, which emphasizes boundary alignment during registration and mitigates misalignment stemming from indistinct boundaries of cerebral tissues. Furthermore, we harness the available longitudinal fetal brain atlases to serve as specific guidance for volumetric reconstruction, thereby enriching structural details of the reconstructed images and also circumventing reconstruction of outliers. Experimental results on 184 clinical fetal brain MR images show that our proposed framework largely outperforms state-of-the-art methods for fetal brain SRR quantitatively and qualitatively.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (4) , 1584-1595
An Integrated Automatic Framework for Super-Resolution Reconstruction of Motion-Corrupted Fetal Brain MRI With Prior Anatomical Knowledge
Super-resolution reconstruction (SRR) from motion-corrupted thick-slice stacks of fetal brain MR images is essential for comprehensive prenatal examination and precise quantification of fetal brain development. Conventional approaches for fetal brain SRR require human intervention to extract cerebral structures from 2D slices, and their performance is often limited by blurred and less informative acquisitions due to fast scanning or irregular fetal movement. In order to overcome these challenges, we propose an automatic fetal brain SRR framework by integrating both individual- and group-level priors of fetal brain MRI for improved SRR. Specifically, we develop a robust fetal brain extraction approach based on Segment Anything Model (SAM). The extracted fetal brain region is segmented into brain tissues to serve as anatomical prior for the follow-up SRR. The SRR is performed based on an iterative optimization scheme by alternatingly performing slice-to-volume registration and volumetric reconstruction. Specifically, we ingeniously integrate anatomical priors obtained by tissue segmentation into both slice-to-volume registration and volumetric reconstruction, which emphasizes boundary alignment during registration and mitigates misalignment stemming from indistinct boundaries of cerebral tissues. Furthermore, we harness the available longitudinal fetal brain atlases to serve as specific guidance for volumetric reconstruction, thereby enriching structural details of the reconstructed images and also circumventing reconstruction of outliers. Experimental results on 184 clinical fetal brain MR images show that our proposed framework largely outperforms state-of-the-art methods for fetal brain SRR quantitatively and qualitatively.
- 26 March 2026
- Published by Elsevier in Neural Networks
- Vol. 201, 108895
Meta-path and context-aware learning for attribute completion in heterogeneous graphs
- 26 March 2026
- Published by Elsevier in Neural Networks
- Vol. 201, 108895
Meta-path and context-aware learning for attribute completion in heterogeneous graphs
- 12 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Super-resolved microstructure estimation with 3D dual-conditioned latent diffusion model
- 12 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Super-resolved microstructure estimation with 3D dual-conditioned latent diffusion model
- 3 February 2026
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 128, 102720
Learning geometric and visual features for medical image segmentation with vision GNN
- 3 February 2026
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 128, 102720
Learning geometric and visual features for medical image segmentation with vision GNN