Yunpeng Liu

Dr. Yunpeng Liu


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
22 October 2022 in Cancers
Verified
Journal Article
Open access
PDF file
YLYunpeng Liu
Yunpeng Liu
HWHaoran Wang
Haoran Wang
KSKaiwen Song
Kaiwen Song
MSMingYang Sun
MingYang Sun
彦邵彦斌 邵
彦斌 邵
Tianyu ZhangTianyu Zhang
Tianyu Zhang
Lung cancer is one of the most common malignant tumors in human beings. It is highly fatal, as its early symptoms are not obvious. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the final diagnosis of many diseases. Therefore, pathology diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far outpace the number of pathologists, especially for the treatment of lung cancer in less developed countries. To address this problem, we propose a plug-and-play visual activation function (AF), CroReLU, based on a priori knowledge of pathology, which makes it possible to use deep learning models for precision medicine. To the best of our knowledge, this work is the first to optimize deep learning models for pathology image diagnosis from the perspective of AFs. By adopting a unique crossover window design for the activation layer of the neural network, CroReLU is equipped with the ability to model spatial information and capture histological morphological features of lung cancer such as papillary, micropapillary, and tubular alveoli. To test the effectiveness of this design, 776 lung cancer pathology images were collected as experimental data. When CroReLU was inserted into the SeNet network (SeNet_CroReLU), the diagnostic accuracy reached 98.33%, which was significantly better than that of common neural network models at this stage. The generalization ability of the proposed method was validated on the LC25000 dataset with completely different data distribution and recognition tasks in the face of practical clinical needs. The experimental results show that CroReLU has the ability to recognize inter- and intra-class differences in cancer pathology images, and that the recognition accuracy exceeds the extant research work on the complex design of network layers.

10 October 2022 in Aging
Verified
Journal Article
Open access
PDF file
YJYan Jiao
Yan Jiao
JWJunyuan Wei
Junyuan Wei
ZLZhibin Li
Zhibin Li
JZJintao Zhou
Jintao Zhou
YLYunpeng Liu
Yunpeng Liu
Background: Lung cancer is the most frequent cancer globally with a high number of cancer-related deaths. The 4-and-a-half LIM domain protein 2 (FHL2) is an oncogenic gene, which promotes the proliferation, invasion, and metastasis of cancer cells. In this study, we aimed to demonstrate that lung cancer patients with high FHL2 expression have worse overall survival (OS) and relapse-free survival (RFS). Methods: TCGA was used to study FHL2 mRNA expression. Nomograms were used to predict the relationship between FHL2 expression levels and survival. The qRT-PCR was used to detect the FHL2 expression in lung cancer cells. In vitro experiments including CCK-8 assay, wound healing, and Transwell assay were performed. Results: This study comprised RNA-Seq gene expression data and clinical features for 1018 lung cancer patients. FHL2 was found to be overexpressed in lung cancer tissues. FHL2 demonstrated moderate diagnostic ability for lung cancer (AUC = 0.857). Kaplan–Meier curves and Cox regression analysis revealed the higher FHL2 expression with the poorer OS and RFS (P < 0.001). The nomogram results indicated that FHL2 could be used to predict the survival of lung cancer patients. GSEA analysis results show that high expression of FHL2 is related to glycolysis and unfolded protein reflection. FHL2 was highly expressed in lung cancer cells and related to their proliferation, migration, and invasion ability. Conclusions: The high expression level of FHL2 in lung cancer can be used as an independent predictor of prognosis in clinical practice.

1 September 2022 in Current Oncology
Verified
Journal Article
Open access
PDF file
HSHuanlan Sa
Huanlan Sa
YXYinghui Xu
Yinghui Xu
XMXiaobo Ma
Xiaobo Ma
XWXu Wang
Xu Wang
CSChao Sun
Chao Sun
KMKewei Ma
Kewei Ma
Carcinoma ex pleomorphic adenoma (Ca ex PA) is a rare malignant tumor that arises from a primary or recurrent benign pleomorphic adenoma (PA). Ca ex PA has an aggressive behavior and poor prognosis. To date, there are no standardized therapeutic methods. Herein, we reported a case of a 57-year-old Chinese female with Ca ex PA of the submandibular gland. After surgery, cervical lymph nodes recurred, and multiple distant metastases were detected. During the treatment, she received multiple chemotherapies and radiotherapy but suffered from multidrug resistance and repeated disease progression. Hence, PD-1 inhibitor (sintilimab), in combination with anlotinib, was administered, which resulted in better control of pulmonary metastases compared to the other treatment regimens. This provided an alternative treatment option for Ca ex PA of the submandibular gland patients with failed multiple therapies.