Lihui Wang
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
Lihui Wang has a total of 138 co-authors. Here are the top co-authors by number of shared publications:
- Yue-Min Zhu
INSA Lyon, University Claude Bernard Lyon 1, CNRS, Inserm, CREATIS, UMR 5220
16 shared publications Jian Zhang
Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guiyang, China
5 shared publications- Qijian Chen
Key Laboratory of Advanced Medical Imaging and Intelligent Computing of Guizhou Province, Engineering Research Center of Text Computing, Ministry of Education, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
5 shared publications Yuemin Zhu
University Lyon, INSA Lyon, CNRS, Inserm, IRP Metislab CREATIS UMR5220, U1206 Lyon France
5 shared publications- Hongjiang Wei
School of Physics, Zhejiang University, Hangzhou, China
4 shared publications Li Wang
Guizhou University
4 shared publications
Latest Publications
- 18 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 343
A causal adversarial graph neural network for multi-center autism spectrum disorder identification
- 18 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 343
A causal adversarial graph neural network for multi-center autism spectrum disorder identification
- 26 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 19 (8) , 1955-1966
SAFFRON: A Physics-Informed, Label-Free Self-Supervised Deep Learning Framework for Fast and Accurate 3D Fetal Brain MRI Reconstruction
Fetal brain MRI has become indispensable in prenatal diagnosis, offering unique soft tissue contrast to evaluate cortical development and detect neurological abnormalities. While high-resolution 3D imaging can provide valuable anatomical information, clinical acquisitions are often inadequate for reliable volumetric reconstruction due to unpredictable fetal motion and thick-slice protocols. Conventional iterative reconstruction methods, though effective, are computationally intensive and struggle with severe motion artifacts, limiting their feasibility in fast-paced clinical workflows. At the same time, the scarcity of authentic 3D fetal brain volumes prevents supervised learning approaches from developing generalizable reconstruction models. To overcome these limitations, we introduce SAFFRON, a physics-informed, label-free self-supervised framework for efficient and high-fidelity 3D fetal brain MRI reconstruction. SAFFRON eliminates the need for ground-truth 3D volumes by combining physics-driven slice acquisition modeling with data-driven deep learning, thereby bridging model-based and learning-based paradigms. The reconstruction task is decomposed into two modules: (1) multi-stack motion estimation via an SVR network that aligns slices into a canonical space, and (2) 3D volume reconstruction via an SRR network. Reconstruction quality is further enhanced by two targeted constraints: a stack-level contextual consistency loss to guide more accurate alignment and a slice-level adversarial loss to promote anatomically realistic structures. Extensive experiments on simulated and clinical datasets demonstrate that SAFFRON substantially outperforms state-of-the-art methods, achieving superior reconstruction accuracy while delivering up to a 60× acceleration in processing speed.
- 26 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 19 (8) , 1955-1966
SAFFRON: A Physics-Informed, Label-Free Self-Supervised Deep Learning Framework for Fast and Accurate 3D Fetal Brain MRI Reconstruction
Fetal brain MRI has become indispensable in prenatal diagnosis, offering unique soft tissue contrast to evaluate cortical development and detect neurological abnormalities. While high-resolution 3D imaging can provide valuable anatomical information, clinical acquisitions are often inadequate for reliable volumetric reconstruction due to unpredictable fetal motion and thick-slice protocols. Conventional iterative reconstruction methods, though effective, are computationally intensive and struggle with severe motion artifacts, limiting their feasibility in fast-paced clinical workflows. At the same time, the scarcity of authentic 3D fetal brain volumes prevents supervised learning approaches from developing generalizable reconstruction models. To overcome these limitations, we introduce SAFFRON, a physics-informed, label-free self-supervised framework for efficient and high-fidelity 3D fetal brain MRI reconstruction. SAFFRON eliminates the need for ground-truth 3D volumes by combining physics-driven slice acquisition modeling with data-driven deep learning, thereby bridging model-based and learning-based paradigms. The reconstruction task is decomposed into two modules: (1) multi-stack motion estimation via an SVR network that aligns slices into a canonical space, and (2) 3D volume reconstruction via an SRR network. Reconstruction quality is further enhanced by two targeted constraints: a stack-level contextual consistency loss to guide more accurate alignment and a slice-level adversarial loss to promote anatomically realistic structures. Extensive experiments on simulated and clinical datasets demonstrate that SAFFRON substantially outperforms state-of-the-art methods, achieving superior reconstruction accuracy while delivering up to a 60× acceleration in processing speed.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (11) , 8256-8267
3D Isotropic High-Resolution Fetal Brain MRI Reconstruction From Motion Corrupted Thick Data Based on Physical-Informed Unsupervised Learning
High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for precise clinical diagnosis and advancing our understanding of fetal brain development. This necessitates reliable slice-to-volume registration (SVR) for motion correction and super-resolution reconstruction (SRR) techniques. Traditional approaches have their limitations, but deep learning (DL) offers the potential in enhancing SVR and SRR. However, most of DL methods require large-scale external 3D high-resolution (HR) training datasets, which is challenging in clinical fetal MRI. To address this issue, we propose an unsupervised iterative joint SVR and SRR DL framework for 3D isotropic HR volume reconstruction. Specifically, our method conceptualizes SVR as a function that maps a 2D slice and a 3D target volume to a rigid transformation matrix, aligning the slice to the underlying location within the target volume. This 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 actual input slice. For SRR, a decoding network embedded within a deep image prior framework, coupled with a comprehensive image degradation model, is used to produce the 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 the loss between the predicted slices and the acquired slices. Experiments on both large-magnitude motion-corrupted simulation data and clinical data have shown that our proposed method outperforms current state-of-the-art fetal brain reconstruction methods. The source code is available at https://github.com/DeepBMI/SUFFICIENT.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (11) , 8256-8267
3D Isotropic High-Resolution Fetal Brain MRI Reconstruction From Motion Corrupted Thick Data Based on Physical-Informed Unsupervised Learning
High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for precise clinical diagnosis and advancing our understanding of fetal brain development. This necessitates reliable slice-to-volume registration (SVR) for motion correction and super-resolution reconstruction (SRR) techniques. Traditional approaches have their limitations, but deep learning (DL) offers the potential in enhancing SVR and SRR. However, most of DL methods require large-scale external 3D high-resolution (HR) training datasets, which is challenging in clinical fetal MRI. To address this issue, we propose an unsupervised iterative joint SVR and SRR DL framework for 3D isotropic HR volume reconstruction. Specifically, our method conceptualizes SVR as a function that maps a 2D slice and a 3D target volume to a rigid transformation matrix, aligning the slice to the underlying location within the target volume. This 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 actual input slice. For SRR, a decoding network embedded within a deep image prior framework, coupled with a comprehensive image degradation model, is used to produce the 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 the loss between the predicted slices and the acquired slices. Experiments on both large-magnitude motion-corrupted simulation data and clinical data have shown that our proposed method outperforms current state-of-the-art fetal brain reconstruction methods. The source code is available at https://github.com/DeepBMI/SUFFICIENT.
- 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.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (7) , 2878-2891
Replace2Self: Self-Supervised Denoising Based on Voxel Replacing and Image Mixing for Diffusion MRI
Low signal to noise ratio (SNR) remains one of the limitations of diffusion weighted (DW) imaging. How to suppress the influence of noise on the subsequent analysis about the tissue microstructure is still challenging. This work proposed a novel self-supervised learning model, Replace2Self, to effectively reduce spatial correlated noise in DW images. Specifically, a voxel replacement strategy based on similar block matching in Q-space was proposed to destroy the correlations of noise in DW image along one diffusion gradient direction. To alleviate the signal gap caused by the voxel replacement, an image mixing strategy based on complementary mask was designed to generate two different noisy DW images. After that, these two noisy DW images were taken as input, and the non-correlated noisy DWimage after voxel replacement was taken as learning target, a denoising network was trained for denoising. To promote the denoising performance, a complementary mask mixing consistency loss and an inverse replacement regularization loss were also proposed. Through the comparisons against several existing DW image denoising methods on extensive simulation data with different noise distributions, noise levels and b-values, as well as the acquisition datasets and the ablation experiments, we verified the effectiveness of the proposed method. Regardless of the noise distribution and noise level, the proposed method achieved the highest PSNR, which was at least 1.9% higher than the suboptimal method when the noise level reaches 10%. Furthermore, our method has superior generalization ability due to the use of the proposed strategies.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (7) , 2878-2891
Replace2Self: Self-Supervised Denoising Based on Voxel Replacing and Image Mixing for Diffusion MRI
Low signal to noise ratio (SNR) remains one of the limitations of diffusion weighted (DW) imaging. How to suppress the influence of noise on the subsequent analysis about the tissue microstructure is still challenging. This work proposed a novel self-supervised learning model, Replace2Self, to effectively reduce spatial correlated noise in DW images. Specifically, a voxel replacement strategy based on similar block matching in Q-space was proposed to destroy the correlations of noise in DW image along one diffusion gradient direction. To alleviate the signal gap caused by the voxel replacement, an image mixing strategy based on complementary mask was designed to generate two different noisy DW images. After that, these two noisy DW images were taken as input, and the non-correlated noisy DWimage after voxel replacement was taken as learning target, a denoising network was trained for denoising. To promote the denoising performance, a complementary mask mixing consistency loss and an inverse replacement regularization loss were also proposed. Through the comparisons against several existing DW image denoising methods on extensive simulation data with different noise distributions, noise levels and b-values, as well as the acquisition datasets and the ablation experiments, we verified the effectiveness of the proposed method. Regardless of the noise distribution and noise level, the proposed method achieved the highest PSNR, which was at least 1.9% higher than the suboptimal method when the noise level reaches 10%. Furthermore, our method has superior generalization ability due to the use of the proposed strategies.
- 20 February 2025
- Published by Wiley in Medical Physics
- Vol. 52 (5) , 2976-2998
Self‐supervised arbitrary‐scale super‐angular resolution diffusion MRI reconstruction
Background: Diffusion magnetic resonance imaging (dMRI) is currently the unique noninvasive imaging technique to investigate the microstructure of in vivo tissues. To fully explore the complex tissue microstructure at sub‐voxel scale, diffusion weighted (DW) images along many diffusion gradient directions are usually acquired, this is undoubtedly time consuming and inhibits their clinical applications. How to estimate the tissue microstructure only from DW images acquired with few diffusion directions remains a challenge. Purpose: To address this challenge, we propose a self‐supervised arbitrary scale super‐angular resolution diffusion MRI reconstruction network (SARDI‐nn), which can generate DW images along any directions from few acquisitions, allowing to overcome the limits of diffusion direction number on exploring the tissue microstructure. Methods: SARDI‐nn is mainly composed of a diffusion direction‐specific DW image feature extraction (DWFE) module and a physics‐driven implicit expression and reconstruction (IRR) module. During training, dual downsampling operations are implemented. The first downsampling is used to produce the low‐angular resolution (LAR) DW images; the second downsampling is for constructing input and learning target of SARDI‐nn. The input LAR DW images pass through a DWFE module (composed of several residual blocks) to extract the feature representations of DW images along input directions, and then these features and the difference between the any querying diffusion direction and the input directions are input into a IRR module to derive the implicit representation and DW image along this query direction. Finally, based on the principle of dMRI, an adaptive weighting method is used to refine the DW image quality. During testing, given any diffusion directions, we can simply infer the corresponding DW images along these directions, accordingly, SARDI‐nn can realize arbitrary scale angular super resolution. To test the effectiveness of the proposed method, we compare it with several existing methods in terms of peak signal to noise ratio (PSNR), structural similarity index measure (SSIM), and root mean square error (RMSE) of DW image and microstructure metrics derived from diffusion kurtosis imaging (DKI) and neurite orientation dispersion and density imaging (NODDI) models at different upsampling scales on Human Connectome Project (HCP) and several in‐house datasets. Results: The comparison results demonstrate that our method achieves almost the best performance at all scales, with SSIM of reconstructed DW images improved by 10.04% at the upscale of 3 and 5.9% at the upscale of 15. Regarding the microstructures derived from DKI and NODDI models, when the upscale is not larger than 6, our method outperforms the best supervised learning method. In addition, the test results on external datasets show the well generality of our method. Conclusions: SARDI‐nn is currently the only method that can reconstruct high‐angular resolution DW images with any upscales, which allows the variation of both input diffusion direction number and upscales, therefore, it can be easily extended to any unseen test datasets, not requiring to retrain the model. SARDI‐nn provides a promising means for exploring the tissue microstructures from DW images along few diffusion gradient directions.
- 20 February 2025
- Published by Wiley in Medical Physics
- Vol. 52 (5) , 2976-2998
Self‐supervised arbitrary‐scale super‐angular resolution diffusion MRI reconstruction
Background: Diffusion magnetic resonance imaging (dMRI) is currently the unique noninvasive imaging technique to investigate the microstructure of in vivo tissues. To fully explore the complex tissue microstructure at sub‐voxel scale, diffusion weighted (DW) images along many diffusion gradient directions are usually acquired, this is undoubtedly time consuming and inhibits their clinical applications. How to estimate the tissue microstructure only from DW images acquired with few diffusion directions remains a challenge. Purpose: To address this challenge, we propose a self‐supervised arbitrary scale super‐angular resolution diffusion MRI reconstruction network (SARDI‐nn), which can generate DW images along any directions from few acquisitions, allowing to overcome the limits of diffusion direction number on exploring the tissue microstructure. Methods: SARDI‐nn is mainly composed of a diffusion direction‐specific DW image feature extraction (DWFE) module and a physics‐driven implicit expression and reconstruction (IRR) module. During training, dual downsampling operations are implemented. The first downsampling is used to produce the low‐angular resolution (LAR) DW images; the second downsampling is for constructing input and learning target of SARDI‐nn. The input LAR DW images pass through a DWFE module (composed of several residual blocks) to extract the feature representations of DW images along input directions, and then these features and the difference between the any querying diffusion direction and the input directions are input into a IRR module to derive the implicit representation and DW image along this query direction. Finally, based on the principle of dMRI, an adaptive weighting method is used to refine the DW image quality. During testing, given any diffusion directions, we can simply infer the corresponding DW images along these directions, accordingly, SARDI‐nn can realize arbitrary scale angular super resolution. To test the effectiveness of the proposed method, we compare it with several existing methods in terms of peak signal to noise ratio (PSNR), structural similarity index measure (SSIM), and root mean square error (RMSE) of DW image and microstructure metrics derived from diffusion kurtosis imaging (DKI) and neurite orientation dispersion and density imaging (NODDI) models at different upsampling scales on Human Connectome Project (HCP) and several in‐house datasets. Results: The comparison results demonstrate that our method achieves almost the best performance at all scales, with SSIM of reconstructed DW images improved by 10.04% at the upscale of 3 and 5.9% at the upscale of 15. Regarding the microstructures derived from DKI and NODDI models, when the upscale is not larger than 6, our method outperforms the best supervised learning method. In addition, the test results on external datasets show the well generality of our method. Conclusions: SARDI‐nn is currently the only method that can reconstruct high‐angular resolution DW images with any upscales, which allows the variation of both input diffusion direction number and upscales, therefore, it can be easily extended to any unseen test datasets, not requiring to retrain the model. SARDI‐nn provides a promising means for exploring the tissue microstructures from DW images along few diffusion gradient directions.
- 30 December 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 101, 103435
Cooperative multi-task learning and interpretable image biomarkers for glioma grading and molecular subtyping
- 30 December 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 101, 103435
Cooperative multi-task learning and interpretable image biomarkers for glioma grading and molecular subtyping
- Open Access
GESH-Net: Graph-Enhanced Spherical Harmonic Convolutional Networks for Cortical Surface Registration
Currently, cortical surface registration techniques based on classical methods have been well developed. However, a key issue with classical methods is that for each pair of images to be registered, it is necessary to search for the optimal transformation in the deformation space according to a specific optimization algorithm until the similarity measure function converges, which cannot meet the requirements of real-time and high-precision in medical image registration. Researching cortical surface registration based on deep learning models has become a new direction. But so far, there are still only a few studies on cortical surface image registration based on deep learning. Moreover, although deep learning methods theoretically have stronger representation capabilities, surpassing the most advanced classical methods in registration accuracy and distortion control remains a challenge. Therefore, to address this challenge, this paper constructs a deep learning model to study the technology of cortical surface image registration. The specific work is as follows: (1) An unsupervised cortical surface registration network based on a multi-scale cascaded structure is designed, and a convolution method based on spherical harmonic transformation is introduced to register cortical surface data. This solves the problem of scale-inflexibility of spherical feature transformation and optimizes the multi-scale registration process. (2)By integrating the attention mechanism, a graph-enhenced module is introduced into the registration network, using the graph attention module to help the network learn global features of cortical surface data, enhancing the learning ability of the network. The results show that the graph attention module effectively enhances the network's ability to extract global features, and its registration results have significant advantages over other methods.
Open AccessGESH-Net: Graph-Enhanced Spherical Harmonic Convolutional Networks for Cortical Surface Registration
Currently, cortical surface registration techniques based on classical methods have been well developed. However, a key issue with classical methods is that for each pair of images to be registered, it is necessary to search for the optimal transformation in the deformation space according to a specific optimization algorithm until the similarity measure function converges, which cannot meet the requirements of real-time and high-precision in medical image registration. Researching cortical surface registration based on deep learning models has become a new direction. But so far, there are still only a few studies on cortical surface image registration based on deep learning. Moreover, although deep learning methods theoretically have stronger representation capabilities, surpassing the most advanced classical methods in registration accuracy and distortion control remains a challenge. Therefore, to address this challenge, this paper constructs a deep learning model to study the technology of cortical surface image registration. The specific work is as follows: (1) An unsupervised cortical surface registration network based on a multi-scale cascaded structure is designed, and a convolution method based on spherical harmonic transformation is introduced to register cortical surface data. This solves the problem of scale-inflexibility of spherical feature transformation and optimizes the multi-scale registration process. (2)By integrating the attention mechanism, a graph-enhenced module is introduced into the registration network, using the graph attention module to help the network learn global features of cortical surface data, enhancing the learning ability of the network. The results show that the graph attention module effectively enhances the network's ability to extract global features, and its registration results have significant advantages over other methods.
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5459-5472
Progressive Dual Priori Network for Generalized Breast Tumor Segmentation
To promote the generalization ability of breast tumor segmentation models, as well as to improve the segmentation performance for breast tumors with smaller size, low-contrast and irregular shape, we propose a progressive dual priori network (PDPNet) to segment breast tumors from dynamic enhanced magnetic resonance images (DCE-MRI) acquired at different centers. The PDPNet first cropped tumor regions with a coarse-segmentation based localization module, then the breast tumor mask was progressively refined by using the weak semantic priori and cross-scale correlation prior knowledge. To validate the effectiveness of PDPNet, we compared it with several state-of-the-art methods on multi-center datasets. The results showed that, comparing against the suboptimal method, the DSC and HD95 of PDPNet were improved at least by 5.13% and 7.58% respectively on multi-center test sets. In addition, through ablations, we demonstrated that the proposed localization module can decrease the influence of normal tissues and therefore improve the generalization ability of the model. The weak semantic priors allow focusing on tumor regions to avoid missing small tumors and low-contrast tumors. The cross-scale correlation priors are beneficial for promoting the shape-aware ability for irregular tumors. Thus integrating them in a unified framework improved the multi-center breast tumor segmentation performance. The source code and open data can be accessed at https://github.com/wangli100209/PDPNet .
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5459-5472
Progressive Dual Priori Network for Generalized Breast Tumor Segmentation
To promote the generalization ability of breast tumor segmentation models, as well as to improve the segmentation performance for breast tumors with smaller size, low-contrast and irregular shape, we propose a progressive dual priori network (PDPNet) to segment breast tumors from dynamic enhanced magnetic resonance images (DCE-MRI) acquired at different centers. The PDPNet first cropped tumor regions with a coarse-segmentation based localization module, then the breast tumor mask was progressively refined by using the weak semantic priori and cross-scale correlation prior knowledge. To validate the effectiveness of PDPNet, we compared it with several state-of-the-art methods on multi-center datasets. The results showed that, comparing against the suboptimal method, the DSC and HD95 of PDPNet were improved at least by 5.13% and 7.58% respectively on multi-center test sets. In addition, through ablations, we demonstrated that the proposed localization module can decrease the influence of normal tissues and therefore improve the generalization ability of the model. The weak semantic priors allow focusing on tumor regions to avoid missing small tumors and low-contrast tumors. The cross-scale correlation priors are beneficial for promoting the shape-aware ability for irregular tumors. Thus integrating them in a unified framework improved the multi-center breast tumor segmentation performance. The source code and open data can be accessed at https://github.com/wangli100209/PDPNet .
- 1 June 2024
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 96
Adaptive spatial and frequency experts fusion network for medical image fusion
- 1 June 2024
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 96
Adaptive spatial and frequency experts fusion network for medical image fusion