Xuqing Zeng

Xuqing Zeng

Auto-generated profile, based on publicly available information

Xuqing Zeng

Key Laboratory of Integrated Circuits and Microsystems (Guangxi Normal University) , Education Department of Guangxi Zhuang Autonomous Region , Guilin , China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 January 2025 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
HSHaixing Song
Haixing Song
XZXuqing Zeng
Xuqing Zeng
GLGuanglian Li
Guanglian Li
RWRongqing Wu
Rongqing Wu
SLSimin Liu
Simin Liu
FHFuyun He
Fuyun He
Three‐dimensional (3D) segmentation of neurons is a crucial step in the digital reconstruction of neurons and serves as an important foundation for brain science research. In neuron segmentation, the U‐Net and its variants have showed promising results. However, due to their primary focus on learning spatial domain features, these methods overlook the abundant global information in the frequency domain. Furthermore, issues such as insufficient processing of contextual features by skip connections and redundant features resulting from simple channel concatenation in the decoder lead to limitations in accurately segmenting neuronal fiber structures. To address these problems, we propose an encoder–decoder segmentation network integrating frequency domain and spatial domain to enhance neuron reconstruction. To simplify the segmentation task, we first divide the neuron images into neuronal cubes. Then, we design 3D FregSNet, which leverages both frequency and spatial domain features to segment the target neurons within these cubes. Then, we introduce a multiscale attention fusion module (MAFM) that utilizes spatial and channel position information to enhance contextual feature representation. In addition, a feature selection module (FSM) is incorporated to adaptively select discriminative features from both the encoder and decoder, increasing the weight on critical neuron locations and significantly improving segmentation performance. Finally, the segmented nerve fiber cubes were assembled into complete neurons and digitally reconstructed using available neuron tracking algorithms. In experiments, we evaluated 3D FregSNet on two challenging 3D neuron image datasets (the BigNeuron dataset and the CWMBS dataset). Compared to other advanced segmentation methods, 3D FregSNet demonstrates more accurate extraction of target neurons in noisy and weakly visible neuronal fiber images, effectively improving the performance of 3D neuron segmentation and reconstruction.

1 January 2026 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
XZXuqing Zeng
Xuqing Zeng
JHJieyuan Hu
Jieyuan Hu
GLGuanglian Li
Guanglian Li
RWRongqing Wu
Rongqing Wu
HSHaixing Song
Haixing Song
FHFuyun He
Fuyun He
The challenge of locating target regions owing to the absence of spatial position information in image‐level labels is resolved by using class activation maps (CAMs) for building localization. However, due to the intrinsic difference between classification and segmentation tasks, CAM is only able to focus on salient regions and often ignores subsignificant regions. This leads to incomplete internal regions and unclear boundaries of buildings extracted using weakly supervised models. Therefore, we propose an effective weakly supervised building extraction method, FRENet, to solve the above problems. So as to preserve building’s edge information, we employ dual‐flow edge compensation module to extract various frequency components of the structure and add an auxiliary branch to provide additional guidance. Moreover, we design a feature sensing module to relocate the building area, which further guides the model to generate more complete CAM. To evaluate the effectiveness of FRENet, we conducted experiments on the Postdam and Vaihingen datasets, comparing it with seven mainstream weakly supervised models. FRENet outperforms AEFT by 2.93% and 4.47%, respectively, on the Postdam dataset, outperforming the competing approaches in terms of F1 score and mIoU. On the Vaihingen dataset, the F1 score and mIoU of FRENet reached 89.91% and 81.75%, respectively, which were 1.19% and 1.94% higher than the second‐best ACGC. To further explore the source of this improvement, we visualized and analyzed frequency components of feature maps along with CAMs. The results provide insights into the feature learning advantages of FRENet and empirically validate the effectiveness of its design.

21 June 2024
Verified
Conference Paper
Open access
JHJieyuan Hu
Jieyuan Hu
XZXuqing Zeng
Xuqing Zeng
QBQiuyi Bai
Qiuyi Bai
TXTang Xiaohu
Tang Xiaohu
In the neuron morphological reconstruction aspect, denoting the type of node was a challenge by defining the radius of reconstructed nodes. In our research, we adapted deep learning methods to this task. The foreground pixel and background pixel of neuron images have a large imbalance in numbers, so that the model was hard to extract the features of neuron images, as a result, missing the neuron cell body during segmentation. In order to resolve this problem, we introduced the self-supervision signal on the top-level feature map by knowledge distillation using a variational autoencoder, except for changing the segmentation loss function. In order to resolve the flaw of hollows in neuron cell bodies, we introduce the attention fuse module on the skip connection from the segmentation encoder and upsampling layer of the segmentation decoder. Compared with the original model, the accuracy and Dice coefficient of the model in this paper are improved by 2% and 15%, respectively. As far as the two metrics of IOU and Dice coefficient are concerned, our method basically achieves the same level as the SwimUNet model, and there is no edge squaring in the segmentation results.