Yingying Zhang

Yingying Zhang

Auto-generated profile, based on publicly available information

Yingying Zhang

Hangzhou International Innovation Institute, Beihang University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
7 October 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YGYuxin Gong
Yuxin Gong
YZYingying Zhang
Yingying Zhang
HZHaogang Zhu
Haogang Zhu
JLJing Lv
Jing Lv
QCQian Cheng
Qian Cheng
Shuliang WangShuliang Wang
Shuliang Wang
Fetal congenital heart disease (FHD) is a common and serious congenital malformation in children. In Asia, FHD birth defect rates have reached as high as 9.3‰. For the early detection of birth defects and mortality, echocardiography remains the most effective method for screening fetal heart malformations. However, standard echocardiograms of the fetal heart, especially four-chamber view images, are difficult to obtain. In addition, the pathophysiological changes in fetal hearts during different pregnancy periods lead to ever-changing twodimensional fetal heart structures and hemodynamics, and it requires extensive professional knowledge to recognize and judge disease development. Thus, research on the automatic screening for FHD is necessary. In this paper, we proposed a new model named DGACNN that shows the best performance in recognizing FHD, achieving a rate of 85%. The motivation for this network is to deal with the problem that there are insufficient training datasets to train a robust model. There are many unlabeled video slices, but they are tough and time-consuming to annotate. Thus, how to use these unannotated video slices to improve the DGACNN capability for recognizing FHD, in terms of both recognition accuracy and robustness, is very meaningful for FHD screening. The architecture of DGACNN comprises two parts, that is, DANomaly and GACNN (Wgan-GP and CNN). DANomaly, similar to the ALOCC network, but incorporates cycle adversarial learning to train an end-to-end one-class classification (OCC) network that is more robust and has a higher accuracy than ALOCC in screening video slices. For the GACNN architecture, we use FCH(four chamber heart) video slices at around the endsystole, as screened by DANomaly, to train a WGAN-GP for the purpose of obtaining ideal low-level features that can robustly improve the FHD recognition accuracy. A few annotated video slices, as screened by DANomaly, can also be used for data augmentation so as to improve the FHD recognition further. The experiments show that the DGACNN outperforms other state-of-the-art networks by 1%–20% in recognizing FHD.A comparison experiment shows that the proposed network already outperforms the performance of expert cardiologists in recognizing FHD, reaching 84% in a test. Thus, the proposed architecture has high potential for helping cardiologists complete early FHD screenings.

1 November 2020 in Pattern Recognition
Verified
Journal Article
Open access
YZYingying Zhang
Yingying Zhang
YGYuxin Gong
Yuxin Gong
HZHaogang Zhu
Haogang Zhu
XBXiao Bai
Xiao Bai
WTWenzhong Tang
Wenzhong Tang

9 August 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Open access
YZYingying Zhang
Yingying Zhang
HZHaogang Zhu
Haogang Zhu
JCJian Cheng
Jian Cheng
JWJingyi Wang
Jingyi Wang
XGXiaoyan Gu
Xiaoyan Gu
HZHongjia Zhang
Hongjia Zhang
Fetal congenital heart disease (FCHD) is a common, serious birth defect affecting ∼1% of newborns annually. Fetal echocardiography is the most effective and important technique for prenatal FCHD diagnosis. The prerequisites for accurate ultrasound FCHD diagnosis are accurate view recognition and high-quality diagnostic view extraction. However, these manual clinical procedures have drawbacks such as, varying technical capabilities and inefficiency. Therefore, the automatic identification of high-quality multiview fetal heart scan images is highly desirable to improve prenatal diagnosis efficiency and accuracy of FCHD. Here, we present a framework for multiview fetal heart ultrasound image recognition and quality assessment that comprises two parts: a multiview classification and localization network (MCLN) and an improved contrastive learning network (ICLN). In the MCLN, a multihead enhanced self-attention mechanism is applied to construct the classification network and identify six accurate and interpretable views of the fetal heart. In the ICLN, anatomical structure standardization and image clarity are considered. With contrastive learning, the absolute loss, feature relative loss and predicted value relative loss are combined to achieve favorable quality assessment results. Experiments show that the MCLN outperforms other state-of-the-art networks by 1.52–13.61% when determining the F1 score in six standard view recognition tasks, and the ICLN is comparable to the performance of expert cardiologists in the quality assessment of fetal heart ultrasound images, reaching 97% on a test set within 2 points for the four-chamber view task. Thus, our architecture offers great potential in helping cardiologists improve quality control for fetal echocardiographic images in clinical practice.

25 June 2025 in iScience
Verified
Journal Article
Open access
HSHao Sheng
Hao Sheng
YZYingying Zhang
Yingying Zhang
RCRuixuan Cong
Ruixuan Cong
SWShuai Wang
Shuai Wang
DYDa Yang
Da Yang
WLWeifeng Lv
Weifeng Lv
5D hyperspectral light field (H-LF) integrates multi-angular and multi-spectral observation, offering a comprehensive opportunity to capture more detailed information from biological samples. In this article, we integrate hyperspectral light field microscopy imaging to analyze H&E-stained whole slide images (WSIs) of colorectal cancer (CRC). Specifically, we design a triple separable transformer encoder (HLFTST) that efficiently extracts features by decoupling the 5D H-LF data into lower-dimensional components and applying self-attention for global interaction. We also introduce a text encoder-decoder to align H-LF features with language, enabling automatic cell classification and pathology report generation through a three-stage training pipeline. Experiments show our method outperforms 2D, 3D, and 4D baselines, improving precision by up to 4.88% and F1 score by 4.21% across five CRC cell categories. Additionally, it generates meaningful pathology descriptions, highlighting its potential for enhancing diagnostics and supporting personalized treatment in broader biomedical settings.

3 October 2024
Verified
Book Chapter
Closed access
PDF file
MBMingkun Bao
Mingkun Bao
YWYan Wang
Yan Wang
XWXinlong Wei
Xinlong Wei
BJBosen Jia
Bosen Jia
XFXiaolin Fan
Xiaolin Fan
HZHaogang Zhu
Haogang Zhu

26 March 2025 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
XFXiaolin Fan
Xiaolin Fan
YWYan Wang
Yan Wang
YZYingying Zhang
Yingying Zhang
MBMingkun Bao
Mingkun Bao
BJBosen Jia
Bosen Jia
HZHaogang Zhu
Haogang Zhu
Automatic view positioning is crucial for cardiac computed tomography (CT) examinations, including disease diagnosis and surgical planning. However, it is highly challenging due to individual variability and large 3D search space. Existing work needs labor-intensive and time-consuming manual annotations to train view-specific models, which are limited to predicting only a fixed set of planes. However, in real clinical scenarios, the challenge of positioning semantic 2D slices with any orientation into varying coordinate space in arbitrary 3D volume remains unsolved. We thus introduce a novel framework, AVP-AP, the first to use Atlas Prompting for self-supervised Automatic View Positioning in the 3D CT volume. Specifically, this paper first proposes an atlas prompting method, which generates a 3D canonical atlas and trains a network to map slices into their corresponding positions in the atlas space via a self-supervised manner. Then, guided by atlas prompts corresponding to the given query images in a reference CT, we identify the coarse positions of slices in the target CT volume using rigid transformation between the 3D atlas and target CT volume, effectively reducing the search space. Finally, we refine the coarse positions by maximizing the similarity between the predicted slices and the query images in the feature space of a given foundation model. Our framework is flexible and efficient compared to other methods, outperforming other methods by 19.8% average structural similarity (SSIM) in arbitrary view positioning and achieving 9% SSIM in two-chamber view compared to four radiologists. Meanwhile, experiments on a public dataset validate our framework’s generalizability.