Shuwei Shen

Shuwei Shen

Auto-generated profile, based on publicly available information

Shuwei Shen

School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei Anhui China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 January 2022 in BME Frontiers
Verified
Journal Article
Open access
PDF file
SSShuwei Shen
Shuwei Shen
MXMengjuan Xu
Mengjuan Xu
FZFan Zhang
Fan Zhang
PSPengfei Shao
Pengfei Shao
HLHonghong Liu
Honghong Liu
RXRonald X. Xu
Ronald X. Xu
Objective and Impact Statement . There is a need to develop high-performance and low-cost data augmentation strategies for intelligent skin cancer screening devices that can be deployed in rural or underdeveloped communities. The proposed strategy can not only improve the classification performance of skin lesions but also highlight the potential regions of interest for clinicians’ attention. This strategy can also be implemented in a broad range of clinical disciplines for early screening and automatic diagnosis of many other diseases in low resource settings. Methods . We propose a high-performance data augmentation strategy of search space 10 1 , which can be combined with any model through a plug-and-play mode and search for the best argumentation method for a medical database with low resource cost. Results . With EfficientNets as a baseline, the best BACC of HAM10000 is 0.853, outperforming the other published models of “single-model and no-external-database” for ISIC 2018 Lesion Diagnosis Challenge (Task 3). The best average AUC performance on ISIC 2017 achieves 0.909 (±0.015), exceeding most of the ensembling models and those using external datasets. Performance on Derm7pt archives the best BACC of 0.735 (±0.018) ahead of all other related studies. Moreover, the model-based heatmaps generated by Grad-CAM++ verify the accurate selection of lesion features in model judgment, further proving the scientific rationality of model-based diagnosis. Conclusion . The proposed data augmentation strategy greatly reduces the computational cost for clinically intelligent diagnosis of skin lesions. It may also facilitate further research in low-cost, portable, and AI-based mobile devices for skin cancer screening and therapeutic guidance.

7 April 2022 in Neuroscience
Verified
Journal Article
Closed access
FZFan Zhang
Fan Zhang
BPBo Pan
Bo Pan
PSPengfei Shao
Pengfei Shao
PLPeng Liu
Peng Liu
SSShuwei Shen
Shuwei Shen
RXRonald X. Xu
Ronald X. Xu

8 September 2017 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SSShuwei Shen
Shuwei Shen
HWHaili Wang
Haili Wang
YXYue Xue
Yue Xue
LYLi Yuan
Li Yuan
XZXiming Zhou
Ximing Zhou
RXRonald X. Xu
Ronald X. Xu
Preoperative assessment of tissue anatomy and accurate surgical planning is crucial in conjoined twin separation surgery. We developed a new method that combines three-dimensional (3D) printing, assembling, and casting to produce anatomic models of high fidelity for surgical planning. The related anatomic features of the conjoined twins were captured by computed tomography (CT), classified as five organ groups, and reconstructed as five computer models. Among these organ groups, the skeleton was produced by fused deposition modeling (FDM) using acrylonitrile-butadiene-styrene. For the other four organ groups, shell molds were prepared by FDM and cast with silica gel to simulate soft tissues, with contrast enhancement pigments added to simulate different CT and visual contrasts. The produced models were assembled, positioned firmly within a 3D printed shell mold simulating the skin boundary, and cast with transparent silica gel. The produced phantom was subject to further CT scan in comparison with that of the patient data for fidelity evaluation. Further data analysis showed that the produced model reassembled the geometric features of the original CT data with an overall mean deviation of less than 2 mm, indicating the clinical potential to use this method for surgical planning in conjoined twin separation surgery.

18 March 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ZZZheng Zhang
Zheng Zhang
PYPeng Yao
Peng Yao
MCMingxiao Chen
Mingxiao Chen
LZLiang Zeng
Liang Zeng
PSPengfei Shao
Pengfei Shao
RXRonald X. Xu
Ronald X. Xu
Cervical abnormal cell detection plays a crucial role in the early screening of cervical cancer. In recent years, some deep learning-based methods have been proposed. However, these methods rely heavily on large amounts of annotated images, which are time-consuming and laborintensive to acquire, thus limiting the detection performance. In this paper, we present a novel Semi-supervised Cervical Abnormal Cell detector (SCAC), which effectively utilizes the abundant unlabeled data. We utilize Transformer as the backbone of SCAC to capture long-range dependencies to mimic the diagnostic process of pathologists. In addition, in SCAC, we design a Unified Strong and Weak Augment strategy (USWA) that unifies two data augmentation pipelines, implementing consistent regularization in semisupervised learning and enhancing the diversity of the training data. We also develop a Global Attention Feature Pyramid Network (GAFPN), which utilizes the attention mechanism to better extract multi-scale features from cervical cytology images. Notably, we have created an unlabeled cervical cytology image dataset, which can be leveraged by semi-supervised learning to enhance detection accuracy. To the best of our knowledge, this is the first publicly available large unlabeled cervical cytology image dataset. By combining this dataset with two publicly available annotated datasets, we demonstrate that SCAC outperforms other existing methods, achieving state-of-theart performance. Additionally, comprehensive ablation studies are conducted to validate the effectiveness of USWA and GAFPN. These promising results highlight the capability of SCAC to achieve high diagnostic accuracy and extensive clinical applications. The code and dataset are publicly available at https://github.com/Lewisonez/cc_detection .

23 September 2024 in Neural Networks
Verified
Journal Article
Closed access
YCYi Cheng
Yi Cheng
PYPeng Yao
Peng Yao
LXLiang Xu
Liang Xu
MCMingxiao Chen
Mingxiao Chen
PLPeng Liu
Peng Liu
RXRonald X. Xu
Ronald X. Xu

19 December 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
LXLiang Xu
Liang Xu
MCMingxiao Chen
Mingxiao Chen
YCYi Cheng
Yi Cheng
PSPengwu Song
Pengwu Song
PSPengfei Shao
Pengfei Shao
RXRonald X. Xu
Ronald X. Xu
The UNet architecture, based on convolutional neural networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this limitation by effectively capturing global feature correlations. However, the integration of the Transformer modules may result in the loss of local contextual information during the global feature fusion process. In this work, we propose a 2D medical image segmentation model called multi-scale cross perceptron attention network (MCPA). The MCPA consists of three main components: an encoder, a decoder, and a Cross Perceptron. The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales. The resulting multi-scale feature vectors are then spatially unfolded, concatenated, and fed through a Global Perceptron module to model global dependencies. Considering the high computational cost of using 3D neural network models, and the fact that many important clinical data can only be obtained in two dimensions, our MCPA focuses on 2D medical image segmentation. Furthermore, we introduce a progressive dual-branch structure (PDBS) to address the semantic segmentation of the image involving finer tissue structures. This structure gradually shifts the segmentation focus of MCPA network training from large-scale structural features to more sophisticated pixel-level features. We evaluate our proposed MCPA model on several publicly available medical image datasets from different tasks and devices, including the open large-scale dataset of CT (Synapse), MRI (ACDC), and widely used 2D medical imaging datasets captured by fundus camera (DRIVE, CHASE\(\_\)DB1, HRF), and OCTA (ROSE). The experimental results show that our MCPA model achieves state-of-the-art performance.