Jiangjie Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiangjie Wu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Hongjiang Wei
School of Physics, Zhejiang University, Hangzhou, China
3 shared publications - Yuyao Zhang
ShanghaiTech University
2 shared publications - Bingqing Xia
The International Peace Maternity and Child Health Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Feifei Qu
Siemens Healthineers (China), Pudong, China
1 shared publication - Lihui Wang
Key Laboratory of Advanced Medical Imaging and Intelligent Computing of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guizhou, China
1 shared publication - Ling Jiang
The International Peace Maternity and Child Health Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
1 shared publication
Latest Publications
- 26 August 2025
- Published by Springer Nature in Pediatric Radiology
- Vol. 55 (12) , 2539-2549
Magnetic resonance imaging based quantitative analysis of placenta and fetal brain in small-for-gestational-age pregnancies: a feasibility study
Background Small-for-gestational-age (SGA) pregnancy is often associated with impaired placental function, which would lead to neurodevelopmental deficits. Objective To utilize the geometric properties of cortical development for quantitative analysis of the relationship between impaired placental function and fetal brain development in pregnancies with SGA fetuses. Materials and methods This retrospective study included 41 pregnant women with appropriate gestational age (GA) (range, 23–38.6 weeks) and 26 pregnant women with SGA pregnancies (range, 23.3–36.3 weeks). After the exclusion of 25 participants with normal fetal brain data but noticeable motor artifacts, 29 fetal brains from the normal group and 16 fetal brains from the SGA group were included in this analysis. Examinations were conducted using a 1.5-T magnetic resonance imaging (MRI) system. Fetal brain cortical thickness and regional volume were calculated for each participant according to a standardized anatomical atlas. Placental intravoxel incoherent motion (IVIM) imaging and T2* mapping were performed. IVIM parameters (perfusion fraction (f), perfusion diffusivity coefficient (D*), and tissue diffusivity (D)) and T2* parameters were subsequently analyzed. Results T2* and f values were significantly lower in SGA pregnancies than in the control group (P < 0.05), indicating impaired placental growth. Nine regions of cortical thickness exhibited significant differences (P<0.05) between the normal and the SGA groups. In the control group, 30 of 86 brain regions (34.88%) exhibited moderate or strong correlations between cortical thickness and T2* values. Among these regions, 19 were in the right hemisphere, whereas 11 were in the left hemisphere. Conclusion Quantitative assessment of changes in placental function and fetal brain cortical thickness is feasible and may provide valuable pathophysiological insights. Cortical thickness variations may act as potential biomarkers, assisting clinicians in early identification of SGA fetuses at risk of neurodevelopmental challenges. Graphical Abstract
- 26 August 2025
- Published by Springer Nature in Pediatric Radiology
- Vol. 55 (12) , 2539-2549
Magnetic resonance imaging based quantitative analysis of placenta and fetal brain in small-for-gestational-age pregnancies: a feasibility study
Background Small-for-gestational-age (SGA) pregnancy is often associated with impaired placental function, which would lead to neurodevelopmental deficits. Objective To utilize the geometric properties of cortical development for quantitative analysis of the relationship between impaired placental function and fetal brain development in pregnancies with SGA fetuses. Materials and methods This retrospective study included 41 pregnant women with appropriate gestational age (GA) (range, 23–38.6 weeks) and 26 pregnant women with SGA pregnancies (range, 23.3–36.3 weeks). After the exclusion of 25 participants with normal fetal brain data but noticeable motor artifacts, 29 fetal brains from the normal group and 16 fetal brains from the SGA group were included in this analysis. Examinations were conducted using a 1.5-T magnetic resonance imaging (MRI) system. Fetal brain cortical thickness and regional volume were calculated for each participant according to a standardized anatomical atlas. Placental intravoxel incoherent motion (IVIM) imaging and T2* mapping were performed. IVIM parameters (perfusion fraction (f), perfusion diffusivity coefficient (D*), and tissue diffusivity (D)) and T2* parameters were subsequently analyzed. Results T2* and f values were significantly lower in SGA pregnancies than in the control group (P < 0.05), indicating impaired placental growth. Nine regions of cortical thickness exhibited significant differences (P<0.05) between the normal and the SGA groups. In the control group, 30 of 86 brain regions (34.88%) exhibited moderate or strong correlations between cortical thickness and T2* values. Among these regions, 19 were in the right hemisphere, whereas 11 were in the left hemisphere. Conclusion Quantitative assessment of changes in placental function and fetal brain cortical thickness is feasible and may provide valuable pathophysiological insights. Cortical thickness variations may act as potential biomarkers, assisting clinicians in early identification of SGA fetuses at risk of neurodevelopmental challenges. Graphical Abstract
- Open Access
SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction
High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for clinical diagnosis. Reliable slice-to-volume registration (SVR)-based motion correction and super-resolution reconstruction (SRR) methods are essential. Deep learning (DL) has demonstrated potential in enhancing SVR and SRR when compared to conventional methods. However, it requires large-scale external training datasets, which are difficult to obtain for clinical fetal MRI. To address this issue, we propose an unsupervised iterative SVR-SRR framework for isotropic HR volume reconstruction. Specifically, SVR is formulated as a function mapping a 2D slice and a 3D target volume to a rigid transformation matrix, which aligns the slice to the underlying location in the target volume. The function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the input slice. In SRR, a decoding network embedded within a deep image prior framework is incorporated with a comprehensive image degradation model to produce the high-resolution (HR) volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing loss between predicted slices and the observed slices. Comprehensive experiments conducted on large-magnitude motion-corrupted simulation data and clinical data demonstrate the superior performance of the proposed framework over state-of-the-art fetal brain reconstruction frameworks.
Open AccessSUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction
High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for clinical diagnosis. Reliable slice-to-volume registration (SVR)-based motion correction and super-resolution reconstruction (SRR) methods are essential. Deep learning (DL) has demonstrated potential in enhancing SVR and SRR when compared to conventional methods. However, it requires large-scale external training datasets, which are difficult to obtain for clinical fetal MRI. To address this issue, we propose an unsupervised iterative SVR-SRR framework for isotropic HR volume reconstruction. Specifically, SVR is formulated as a function mapping a 2D slice and a 3D target volume to a rigid transformation matrix, which aligns the slice to the underlying location in the target volume. The function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the input slice. In SRR, a decoding network embedded within a deep image prior framework is incorporated with a comprehensive image degradation model to produce the high-resolution (HR) volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing loss between predicted slices and the observed slices. Comprehensive experiments conducted on large-magnitude motion-corrupted simulation data and clinical data demonstrate the superior performance of the proposed framework over state-of-the-art fetal brain reconstruction frameworks.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (8) , 8404-8412
SVRMamba: Slice-to-Volume Reconstruction from Multiple MRI Stacks with Slice Sequence Guided Mamba
In fetal magnetic resonance imaging (MRI), slice-to-volume reconstruction (SVR) involves the computational creation of a 3D volume from multiple stacks of 2D slices. This process is challenging due to slice misalignment and image noise. Current state-of-the-art (SOTA) SVR methods typically employ coarse-to-fine techniques that iteratively refine slice-to-volume motion correction and 3D volume reconstruction. However, both processes are inherently inefficient, making these methods time-consuming and prone to errors. This often results in less robust and accurate outcomes, primarily due to insufficient modeling of the spatial relationships between slices. Typically, 2D fetal MRI slices are acquired using the interleave sequence, which first acquires the odd slices and then the even slices in one stack. To this end, we propose a novel Mamba-based framework called SVRMamba, which integrates slice-to-volume reconstruction with slice sequence-guided state space modeling. Specifically, our approach reformulates Mamba’s unidirectional scanning into a slice sequence-guided odd-even directional scanning method and marks the slice positions using sequence embedding tokens. This enables the network to learn the slice relationships and spatial sequences, enhancing fetal MRI SVR motion correction performance. We further integrate a convolutional neural network (CNN)-based interpolation network that generates a noise-suppressed 3D reconstruction by leveraging the predicted motion for each slice. This framework notably enhances 3D fetal brain SVR, delivering substantial improvements in both reconstruction speed and overall performance. Extensive experiments conducted on various benchmark and clinical datasets demonstrate that SVRMamba significantly outperforms existing SOTA methods, delivering comparable results with a remarkable sixtyfold increase in reconstruction speed.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (8) , 8404-8412
Open AccessSVRMamba: Slice-to-Volume Reconstruction from Multiple MRI Stacks with Slice Sequence Guided Mamba
In fetal magnetic resonance imaging (MRI), slice-to-volume reconstruction (SVR) involves the computational creation of a 3D volume from multiple stacks of 2D slices. This process is challenging due to slice misalignment and image noise. Current state-of-the-art (SOTA) SVR methods typically employ coarse-to-fine techniques that iteratively refine slice-to-volume motion correction and 3D volume reconstruction. However, both processes are inherently inefficient, making these methods time-consuming and prone to errors. This often results in less robust and accurate outcomes, primarily due to insufficient modeling of the spatial relationships between slices. Typically, 2D fetal MRI slices are acquired using the interleave sequence, which first acquires the odd slices and then the even slices in one stack. To this end, we propose a novel Mamba-based framework called SVRMamba, which integrates slice-to-volume reconstruction with slice sequence-guided state space modeling. Specifically, our approach reformulates Mamba’s unidirectional scanning into a slice sequence-guided odd-even directional scanning method and marks the slice positions using sequence embedding tokens. This enables the network to learn the slice relationships and spatial sequences, enhancing fetal MRI SVR motion correction performance. We further integrate a convolutional neural network (CNN)-based interpolation network that generates a noise-suppressed 3D reconstruction by leveraging the predicted motion for each slice. This framework notably enhances 3D fetal brain SVR, delivering substantial improvements in both reconstruction speed and overall performance. Extensive experiments conducted on various benchmark and clinical datasets demonstrate that SVRMamba significantly outperforms existing SOTA methods, delivering comparable results with a remarkable sixtyfold increase in reconstruction speed.