Ying Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ying Wang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Boyu Zhang
University of Idaho
1 shared publication - Bryar Shareef
Department of Computer Science, University of Idaho, Idaho Falls, ID 83402, USA
1 shared publication Chenjun Jiang
School of Electrical Engineering, Yanshan University, Qinhuangdao, China
1 shared publicationChong Liu
School of Electrical Engineering, Yanshan University, Qinhuangdao, China
1 shared publication- Chunping Ning
Department of Ultrasound, Medical College of Qingdao University, Qingdao 266003, China
1 shared publication - Congjing An
Department of Breast and Thyroid Surgery, the Second Hospital of Hebei Medical University, Xinhua District, Shijiazhuang, China
1 shared publication
Latest Publications
- 17 September 2026
- Published by Elsevier in Ultrasound in Medicine & Biology
- Vol. 52 (12) , 2739-2745
Macrocalcification features in solid hypoechoic thyroid nodules
- 17 September 2026
- Published by Elsevier in Ultrasound in Medicine & Biology
- Vol. 52 (12) , 2739-2745
Macrocalcification features in solid hypoechoic thyroid nodules
- 10 March 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (6) , 3773-3788
A Thyroid Nodule Ultrasound Image Grading Model Integrating Medical Prior Knowledge
In recent years, there has been increasing research on computer-aided diagnosis (CAD) using deep learning and image processing techniques. Still, most studies have focused on the benign-malignant classification of nodules. In this study, we propose an integrated architecture for grading thyroid nodules based on the Chinese Thyroid Imaging Reporting and Data System (C-TIRADS). The method combines traditional handcrafted features with deep features in the extraction process. In the preprocessing stage, a pseudo-artifact removal algorithm based on the fast marching method (FMM) is employed, followed by a hybrid median filtering for noise reduction. Contrast-limited adaptive histogram equalization is used for contrast enhancement to restore and enhance the information in ultrasound images. In the feature extraction stage, the improved ShuffleNetV2 network with multi-head self-attention mechanism is selected, and its extracted features are fused with medical prior knowledge features. Finally, a multi-class classification task is performed using the eXtreme Gradient Boosting (XGBoost) classifier. The dataset used in this study consists of 922 original images, including 149 examples belonging to class 2, 140 examples to class 3, 156 examples to class 4A, 114 examples to class 4B, 123 examples to class 4C, and 240 examples to class 5. The model is trained for 2000 epochs. The accuracy, precision, recall, F1 score, and AUC value of the proposed method are 97.17%, 97.65%, 97.17%, 0.9834, and 0.9855, respectively. The results demonstrate that the fusion of medical prior knowledge based on C-TIRADS and deep features from convolutional neural networks can effectively improve the overall performance of thyroid nodule diagnosis, providing a new feasible solution for developing clinical CAD systems for thyroid nodule ultrasound diagnosis.
- 10 March 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (6) , 3773-3788
A Thyroid Nodule Ultrasound Image Grading Model Integrating Medical Prior Knowledge
In recent years, there has been increasing research on computer-aided diagnosis (CAD) using deep learning and image processing techniques. Still, most studies have focused on the benign-malignant classification of nodules. In this study, we propose an integrated architecture for grading thyroid nodules based on the Chinese Thyroid Imaging Reporting and Data System (C-TIRADS). The method combines traditional handcrafted features with deep features in the extraction process. In the preprocessing stage, a pseudo-artifact removal algorithm based on the fast marching method (FMM) is employed, followed by a hybrid median filtering for noise reduction. Contrast-limited adaptive histogram equalization is used for contrast enhancement to restore and enhance the information in ultrasound images. In the feature extraction stage, the improved ShuffleNetV2 network with multi-head self-attention mechanism is selected, and its extracted features are fused with medical prior knowledge features. Finally, a multi-class classification task is performed using the eXtreme Gradient Boosting (XGBoost) classifier. The dataset used in this study consists of 922 original images, including 149 examples belonging to class 2, 140 examples to class 3, 156 examples to class 4A, 114 examples to class 4B, 123 examples to class 4C, and 240 examples to class 5. The model is trained for 2000 epochs. The accuracy, precision, recall, F1 score, and AUC value of the proposed method are 97.17%, 97.65%, 97.17%, 0.9834, and 0.9855, respectively. The results demonstrate that the fusion of medical prior knowledge based on C-TIRADS and deep features from convolutional neural networks can effectively improve the overall performance of thyroid nodule diagnosis, providing a new feasible solution for developing clinical CAD systems for thyroid nodule ultrasound diagnosis.
- Open Access
- 12 May 2022
- Published by Springer Nature in Cancer Cell International
- Vol. 22 (1) , 1-13
LINC00662 enhances cell progression and stemness in breast cancer by MiR-144-3p/SOX2 axis
Background: Breast cancer (BC) is one of the most prevalent malignancies among women globally. Emerging evidence indicates that long non-coding RNAs (lncRNAs) are associated with BC carcinogenesis. In the current study, we explored the mechanism by which LINC00662 regulates BC. Methods: Quantitative real-time PCR (qRT-PCR) assessed RNA expressions while western blot for protein levels. Kaplan Meier analysis evaluated overall survival (OS). Cytoplasmic/nuclear fractionation, RNA binding protein immunoprecipitation (RIP) and luciferase reporter assays probed into the underlying molecular mechanism of LINC00662 in BC. Xenograft model was established to explore the influence of LINC00662 on BC progression in vivo. R square graphs were utilized to represent RNA relationships. Results: LINC00662 is overtly overexpressed in BC tissues and cell lines. LINC00662 knockdown hampers cell proliferation, migration, invasion and stemness. LINC00662 expression is negatively correlated with OS of BC patients. LINC00662 up-regulates SOX2 expression by competitively binding to miR-144-3p, thereby modulating BC cell progression. Xenograft experiments verified that LINC00662 promotes BC tumor growth and cell stemness in vivo. Conclusion: LINC00662 enhances cell proliferation, migration, invasion and stemness in BC by targeting miR-144-3p/SOX2 axis. The findings in the present study suggested that LINC00662 could be a potential therapeutic target for BC treatment. Graphical
- 12 May 2022
- Published by Springer Nature in Cancer Cell International
- Vol. 22 (1) , 1-13
Open AccessLINC00662 enhances cell progression and stemness in breast cancer by MiR-144-3p/SOX2 axis
Background: Breast cancer (BC) is one of the most prevalent malignancies among women globally. Emerging evidence indicates that long non-coding RNAs (lncRNAs) are associated with BC carcinogenesis. In the current study, we explored the mechanism by which LINC00662 regulates BC. Methods: Quantitative real-time PCR (qRT-PCR) assessed RNA expressions while western blot for protein levels. Kaplan Meier analysis evaluated overall survival (OS). Cytoplasmic/nuclear fractionation, RNA binding protein immunoprecipitation (RIP) and luciferase reporter assays probed into the underlying molecular mechanism of LINC00662 in BC. Xenograft model was established to explore the influence of LINC00662 on BC progression in vivo. R square graphs were utilized to represent RNA relationships. Results: LINC00662 is overtly overexpressed in BC tissues and cell lines. LINC00662 knockdown hampers cell proliferation, migration, invasion and stemness. LINC00662 expression is negatively correlated with OS of BC patients. LINC00662 up-regulates SOX2 expression by competitively binding to miR-144-3p, thereby modulating BC cell progression. Xenograft experiments verified that LINC00662 promotes BC tumor growth and cell stemness in vivo. Conclusion: LINC00662 enhances cell proliferation, migration, invasion and stemness in BC by targeting miR-144-3p/SOX2 axis. The findings in the present study suggested that LINC00662 could be a potential therapeutic target for BC treatment. Graphical
- Top Cited PapersOpen Access
- 14 April 2022
- Published by MDPI AG in Healthcare
- Vol. 10 (4) , 729
BUSIS: A Benchmark for Breast Ultrasound Image Segmentation
Breast ultrasound (BUS) image segmentation is challenging and critical for BUS computer-aided diagnosis (CAD) systems. Many BUS segmentation approaches have been studied in the last two decades, but the performances of most approaches have been assessed using relatively small private datasets with different quantitative metrics, which results in a discrepancy in performance comparison. Therefore, there is a pressing need for building a benchmark to compare existing methods using a public dataset objectively, to determine the performance of the best breast tumor segmentation algorithm available today, and to investigate what segmentation strategies are valuable in clinical practice and theoretical study. In this work, a benchmark for B-mode breast ultrasound image segmentation is presented. In the benchmark, (1) we collected 562 breast ultrasound images and proposed standardized procedures to obtain accurate annotations using four radiologists; (2) we extensively compared the performance of 16 state-of-the-art segmentation methods and demonstrated that most deep learning-based approaches achieved high dice similarity coefficient values (DSC ≥ 0.90) and outperformed conventional approaches; (3) we proposed the losses-based approach to evaluate the sensitivity of semi-automatic segmentation to user interactions; and (4) the successful segmentation strategies and possible future improvements were discussed in details.
- 14 April 2022
- Published by MDPI AG in Healthcare
- Vol. 10 (4) , 729
Top Cited PapersOpen AccessBUSIS: A Benchmark for Breast Ultrasound Image Segmentation
Breast ultrasound (BUS) image segmentation is challenging and critical for BUS computer-aided diagnosis (CAD) systems. Many BUS segmentation approaches have been studied in the last two decades, but the performances of most approaches have been assessed using relatively small private datasets with different quantitative metrics, which results in a discrepancy in performance comparison. Therefore, there is a pressing need for building a benchmark to compare existing methods using a public dataset objectively, to determine the performance of the best breast tumor segmentation algorithm available today, and to investigate what segmentation strategies are valuable in clinical practice and theoretical study. In this work, a benchmark for B-mode breast ultrasound image segmentation is presented. In the benchmark, (1) we collected 562 breast ultrasound images and proposed standardized procedures to obtain accurate annotations using four radiologists; (2) we extensively compared the performance of 16 state-of-the-art segmentation methods and demonstrated that most deep learning-based approaches achieved high dice similarity coefficient values (DSC ≥ 0.90) and outperformed conventional approaches; (3) we proposed the losses-based approach to evaluate the sensitivity of semi-automatic segmentation to user interactions; and (4) the successful segmentation strategies and possible future improvements were discussed in details.