Manman Zhu

Manman Zhu

Auto-generated profile, based on publicly available information

Manman Zhu

School of Biomedical Engineering, Southern Medical University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 March 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
MMMingqiang Meng
Mingqiang Meng
YWYongbo Wang
Yongbo Wang
MZManman Zhu
Manman Zhu
XTXi Tao
Xi Tao
ZMZerui Mao
Zerui Mao
JMJianhua Ma
Jianhua Ma
Deep learning (DL) algorithms have achieved unprecedented success in low-dose CT (LDCT) imaging and are expected to be a new generation of CT reconstruction technology. However, most DL-based denoising models often lack the ability to generalize to unseen dose data. And they only learn the posterior distribution of latent normal-dose CT (NDCT) images conditioned on observed LDCT images in the traditional maximum a posteriori (MAP) framework, while ignoring the noise generation process of LDCT images. Moreover, most simulation tools for LDCT typically operate on proprietary projection data, which is generally not accessible without an established collaboration with CT manufacturers. To alleviate these issues, in this work, we propose a dose-agnostic dual-task transfer network, termed DDT-Net, for simultaneous LDCT denoising and simulation. Concretely, the dual-task learning module is constructed to integrate the LDCT denoising and simulation tasks into a unified optimization framework by learning the joint distribution of LDCT and NDCT data. We approximate the joint distribution of continuous dose level data by training DDT-Net with discrete dose data, which can be generalized to denoising and simulation of unseen dose data. In particular, the mixed-dose training strategy adopted by DDT-Net can promote the denoising performance of lower-dose data. The paired dataset simulated by DDT-Net can be used for data augmentation to further restore the tissue texture of LDCT images. Experimental results on synthetic data and clinical data show that the proposed DDT-Net outperforms competing methods in terms of denoising and generalization performance at unseen dose data, and it also provides a simulation tool that can quickly simulate realistic LDCT images at arbitrary dose levels.

16 March 2020
Verified
Conference Paper
Closed access
PDF file
DLDanyang Li
Danyang Li
SLSui Li
Sui Li
MZManman Zhu
Manman Zhu
QGQi Gao
Qi Gao
ZBZhaoying Bian
Zhaoying Bian
JMJianhua Ma
Jianhua Ma
Deep learning (DL) networks show a great potential in computed tomography (CT) imaging field. Most of them are supervised DL network greatly based on their capability and the amount of CT training data (i.e., low-dose CT measurements/high-quality ones). However, collection of large-scale CT datasets are time-consuming and expensive. In addition, the training and testing CT datasets used for supervised DL network are highly desired similarities in CT scan protocol (i.e., similar anatomical structure, and same kVp setting). These two issues are particularly critical in spectral CT imaging. In this work, to address the issues, we presents an unsupervised data fidelity enhancement network (USENet) to produce high-quality spectral CT images. Specifically, the presented USENet consists of two parts, i.e., supervised network and unsupervised network. In the supervised network, the spectral CT image pairs at 140 kVp (low-dose CT images/high-dose ones) are used for network training. It should be noted that there is a great difference of CT value between spectral CT images at 140 kVp and 80 kVp, and the supervised network trained with CT images at 140 kVp cannot be directly used for CT image reconstruction at 80 kVp. Then unsupervised network enrolls physical model and the spectral CT measurements at 80 kVp for fine-tuning the supervised network, which is the major contribution of the presented USENet method. Finally, accurate spectral CT reconstructions are achieved for the sparse-view and low-dose cases, which fully demonstrate the effectiveness of the presented USENet method.

16 March 2020
Verified
Conference Paper
Closed access
PDF file
LWLei Wang
Lei Wang
QGQi Gao
Qi Gao
MMMingQiang Meng
MingQiang Meng
SLSui Li
Sui Li
MZManman Zhu
Manman Zhu
JMJianhua Ma
Jianhua Ma
Fully supervised deep learning (DL) methods have been widely used in low-dose CT (LDCT) imaging field and can usually achieve high accuracy results. These methods require a large labeled training set which consists of pairs of LDCT images as well as their corresponding high-dose CT (HDCT) ones. They successfully learn intermediate concept of features describing important components in CT images, such as noise distribution, and structure details, which is important to capture dependencies from LDCT image to HDCT ones. However, it should be noted that it is quite time-consuming and costly to obtain such a large of labeled CT images especially the HDCT images are limited in clinics. In comparison, lots of unlabeled LDCT images are usually easily accessible and massive critical information latent in the unlabeled LDCT can be leveraged to further boost restoration performance. Therefore, in this work, we present a semi-supervised noise distribution learning network to suppress noise-induced artifacts in the LDCT images. For simplicity, the presented network in termed as "SNDL-Net". The presented SNDL-Net consists of two sub-networks, i.e., supervised network, and unsupervised network. In the supervised network, the LDCT/HDCT image pairs are used for network training. And the unsupervised network considers the complex noise distribution in the LDCT images, and model the noise with a Gaussian mixture framework, then learns the proper gradient of LDCT images in a purely unsupervised manner. Similar with the supervised network training, the gradient information in a large of unlabeled LDCT images can be used for unsupervised network training. Moreover, to learn the noise distribution accurately, the discrepancy between the learned noise distribution in the supervised network and learned noise distribution in the unsupervised network can be modeled by a Kullback-Leibler (KL) divergence. Experiments on the Mayo clinic dataset verify the method is effective in low-dose CT image restoration with only a small amount of labeled data compared to previous supervised deep learning methods.

16 March 2020
Verified
Conference Paper
Closed access
PDF file
SLSui Li
Sui Li
LYLisha Yao
Lisha Yao
MZManman Zhu
Manman Zhu
DLDanyang Li
Danyang Li
QGQi Gao
Qi Gao
JMJianhua Ma
Jianhua Ma
Deep learning-based algorithms have been widely used in the low-dose CT imaging field, and have achieved promising results. However, most of these algorithms only consider the information of the desired CT image itself, ignoring the external information that can help improve the imaging performance. Therefore, in this study, we present a convolutional neural network for low-dose CT reconstruction with non-local texture learning (NTL-CNN) approach. Specifically, different from the traditional network in CT imaging, the presented NTL- CNN approach takes into consideration the non-local features within the adjacent slices in 3D CT images. Then, both low-dose target CT images and the non-local features feed into the residual network to produce desired high-quality CT images. Real patient datasets are used to evaluate the performance of the presented NTL-CNN. The corresponding experiment results demonstrate that the presented NTL-CNN approach can obtain better CT images compared with the competing approaches, in terms of noise-induced artifacts reduction and structure details preservation.

7 April 2023
Verified
Conference Paper
Closed access
PDF file
MZManman Zhu
Manman Zhu
CWChen Wang
Chen Wang
ZWZidan Wang
Zidan Wang
MMMingQiang Meng
MingQiang Meng
YWYongbo Wang
Yongbo Wang
JMJianhua Ma
Jianhua Ma
High-attenuation artifacts in digital breast tomosynthesis (DBT) imaging will potentially obscure some lesions in breast, which may result in increasing false-negative rate. Many image domain and projection domain based methods have been developed to reduce the high-attenuation artifacts. However, the high-attenuation artifacts have not been effectively removed, since these existing methods have not exactly addressed the inherent DBT imaging constraint of sparse-view low-dose scanning in a limited angular range. Recently, view-by-view backprojection tensor (VVBP-Tensor) domain is presented as the intermediary domain between projection domain and image domain, which may be beneficial to DBT image reconstruction. Moreover, high-attenuation artifacts are relative to the imaging geometry, and it is reasonable to hypothesize that the diffusion pattern of artifacts in VVBP-Tensor domain are similar for the same DBT imaging system. Therefore, we proposed a VVBP-Tensor based deep learning framework for high-attenuation artifact reduction in DBT imaging (shorten as VTDL-DBT), which learns the artifact diffusion pattern in VVBP-Tensor domain and remove these artifacts in a data-driven manner. The proposed method can be considered as the implicitly weighted filtered backprojection (wFBP) algorithm, which replaces the explicit weighted summing with the learnable deep neural network model. In addition, a pipeline of generating paired training data is also presented for DBT high-attenuation artifact removal task, which utilizes digital anthropomorphic breast phantoms and the Monte Carlo simulation algorithm. Both qualitative and quantitative results demonstrate that the presented VTDL-DBT method has a superior DBT imaging performance on the simulated DBT dataset, in terms of high-attenuation artifact reduction and structural texture preservation.

26 December 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
MZManman Zhu
Manman Zhu
ZWZidan Wang
Zidan Wang
CWChen Wang
Chen Wang
CZCuidie Zeng
Cuidie Zeng
DZDong Zeng
Dong Zeng
YWYongbo Wang
Yongbo Wang
High-attenuation (HA) artifacts may lead to obscured subtle lesions and lesion over-estimation in digital breast tomosynthesis (DBT) imaging. High-attenuation artifact suppression (HAAS) is vital for widespread DBT applications in clinic. The conventional HAAS methods usually rely on the segmentation accuracy of HA objects and manual weighting schemes, without considering the geometry information in DBT reconstruction. And the global weighted strategy designed for HA artifacts may decrease the resolution in low-contrast soft-tissue regions. Moreover, the view-by-view backprojection tensor (VVBP-Tensor) domain has recently developed as a new intermediary domain that contains the lossless information in projection domain and the structural details in image domain. Therefore, we propose a VOI-Based VVBP-Tensor Network (VBVT-Net) for HAAS task in DBT imaging, which learns a local implicit weighted strategy based on the analytical FDK reconstruction mechanism. Specifically, the VBVT-Net method incorporates a volume of interest (VOI) recognition sub-network and a HAAS sub-network. The VOI recognition sub-network automatically extracts all 4D VVBP-Tensor patches containing HA artifacts. The HAAS sub-network reduces HA artifacts in these 4D VVBP-Tensor patches by leveraging the ray-trace backprojection features and extra neighborhood information. All results on four datasets demonstrate that the proposed VBVT-Net method could accurately detect HA regions, effectively reduce HA artifacts and simultaneously preserve structures in soft-tissue background regions. The proposed VBVT-Net method has a good interpretability as a general variant of the weighted FDK algorithm, which is potential to be applied in the next generation DBT prototype system in the future.