Bin Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bin Shi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Chuman Xiao
Medical Psychological Center, Second Xiangya Hospital of Central South University, Changsha, China
1 shared publication - Jialong Li
Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
1 shared publication - Kangning Li
The Second Xiangya Hospital of Central South University
1 shared publication - Lijuan Wang
Longdong University
1 shared publication Lixiang Tan
College of Artificial Intelligence and Computer Science, Northwest Normal University
1 shared publication- Qiangli Dong
Department of Mental Health, The Second Hospital of Lanzhou University, Lanzhou 730000, China
1 shared publication
Latest Publications
- Open Access
- 10 March 2026
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 17, 1806780
Reference-guided MRI super-resolution with dual attention aggregation network
Magnetic resonance imaging (MRI) super-resolution aims to enhance spatial resolution from low-resolution acquisitions while preserving anatomically meaningful structures. Conventional single-image super-resolution methods are fundamentally limited by the lack of high-frequency information in the input and often fail to recover fine anatomical details under large upscaling factors. In many MRI scenarios, additional reference images acquired under similar imaging protocols are naturally available and can provide complementary structural information, yet effectively leveraging such references without introducing anatomically inconsistent artifacts remains challenging. In this work, we propose a reference-guided MRI super-resolution framework, termed Dual Attention Aggregation Super-Resolution (DAASR), which explicitly balances structural modeling and controlled reference integration in a hierarchical manner. DAASR employs a channel-wise attention mechanism to reinforce global anatomical coherence in low-resolution features and a structure-aware alignment strategy to selectively incorporate consistent reference information while suppressing unreliable transfers. Extensive experiments on a public MRI benchmark and a clinical brain MRI dataset demonstrate that the proposed method consistently outperforms state-of-the-art MRI super-resolution approaches across multiple scaling factors in terms of PSNR and SSIM. The proposed DAASR further achieves improved structural similarity and visual consistency, indicating better preservation of fine anatomical structures and tissue boundaries.
- 10 March 2026
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 17, 1806780
Open AccessReference-guided MRI super-resolution with dual attention aggregation network
Magnetic resonance imaging (MRI) super-resolution aims to enhance spatial resolution from low-resolution acquisitions while preserving anatomically meaningful structures. Conventional single-image super-resolution methods are fundamentally limited by the lack of high-frequency information in the input and often fail to recover fine anatomical details under large upscaling factors. In many MRI scenarios, additional reference images acquired under similar imaging protocols are naturally available and can provide complementary structural information, yet effectively leveraging such references without introducing anatomically inconsistent artifacts remains challenging. In this work, we propose a reference-guided MRI super-resolution framework, termed Dual Attention Aggregation Super-Resolution (DAASR), which explicitly balances structural modeling and controlled reference integration in a hierarchical manner. DAASR employs a channel-wise attention mechanism to reinforce global anatomical coherence in low-resolution features and a structure-aware alignment strategy to selectively incorporate consistent reference information while suppressing unreliable transfers. Extensive experiments on a public MRI benchmark and a clinical brain MRI dataset demonstrate that the proposed method consistently outperforms state-of-the-art MRI super-resolution approaches across multiple scaling factors in terms of PSNR and SSIM. The proposed DAASR further achieves improved structural similarity and visual consistency, indicating better preservation of fine anatomical structures and tissue boundaries.
- Open Access
- 20 July 2023
- Published by MDPI AG in Brain Sciences
- Vol. 13 (7) , 1098
Altered Relationship between Functional Connectivity and Fiber-Bundle Structure in High-Functioning Male Adults with Autism Spectrum Disorder
Autism spectrum disorder (ASD) is a pervasive neurodevelopmental disorder characterized by abnormalities in structure and function of the brain. However, how ASD affects the relationship between fiber-bundle microstructures and functional connectivity (FC) remains unclear. Here, we analyzed structural and functional images of 26 high-functioning adult males with ASD, alongside 26 age-, gender-, and full-scale IQ-matched typically developing controls (TDCs) from the BNI dataset in the ABIDE database. We utilized fixel-based analysis to extract microstructural information from fiber tracts, which was then used to predict FC using a multilinear model. Our results revealed that the structure–function relationships in both ASD and TDC cohorts were strongly aligned in the primary cortex but decoupled in the high-order cortex, and the ASD patients exhibited reduced structure–function relationships throughout the cortex compared to the TDCs. Furthermore, we observed that the disrupted relationships in ASD were primarily driven by alterations in FC rather than fiber-bundle microstructures. The structure–function relationships in the left superior parietal cortex, right precentral and inferior temporal cortices, and bilateral insula could predict individual differences in clinical symptoms of ASD patients. These findings underscore the significance of altered relationships between fiber-bundle microstructures and FC in the etiology of ASD.
- 20 July 2023
- Published by MDPI AG in Brain Sciences
- Vol. 13 (7) , 1098
Open AccessAltered Relationship between Functional Connectivity and Fiber-Bundle Structure in High-Functioning Male Adults with Autism Spectrum Disorder
Autism spectrum disorder (ASD) is a pervasive neurodevelopmental disorder characterized by abnormalities in structure and function of the brain. However, how ASD affects the relationship between fiber-bundle microstructures and functional connectivity (FC) remains unclear. Here, we analyzed structural and functional images of 26 high-functioning adult males with ASD, alongside 26 age-, gender-, and full-scale IQ-matched typically developing controls (TDCs) from the BNI dataset in the ABIDE database. We utilized fixel-based analysis to extract microstructural information from fiber tracts, which was then used to predict FC using a multilinear model. Our results revealed that the structure–function relationships in both ASD and TDC cohorts were strongly aligned in the primary cortex but decoupled in the high-order cortex, and the ASD patients exhibited reduced structure–function relationships throughout the cortex compared to the TDCs. Furthermore, we observed that the disrupted relationships in ASD were primarily driven by alterations in FC rather than fiber-bundle microstructures. The structure–function relationships in the left superior parietal cortex, right precentral and inferior temporal cortices, and bilateral insula could predict individual differences in clinical symptoms of ASD patients. These findings underscore the significance of altered relationships between fiber-bundle microstructures and FC in the etiology of ASD.