A5050486660- AI in cancer detection
- Cervical Cancer and HPV Research
- Advanced Measurement and Detection Methods
- Privacy-Preserving Technologies in Data
- Forecasting Techniques and Applications
- Cryptography and Data Security
- Simulation Techniques and Applications
- Image Processing Techniques and Applications
- Cancer, Lipids, and Metabolism
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Cleft Lip and Palate Research
- Parkinson's Disease Mechanisms and Treatments
- Renin-Angiotensin System Studies
- Bone health and treatments
- Nuclear Receptors and Signaling
- Generative Adversarial Networks and Image Synthesis
- Fault Detection and Control Systems
- Chromium effects and bioremediation
- 3D Shape Modeling and Analysis
- Privacy, Security, and Data Protection
- Hand Gesture Recognition Systems
- Sepsis Diagnosis and Treatment
- Computer Graphics and Visualization Techniques
- Mobile Crowdsensing and Crowdsourcing
Central South University
2018-2025
Hangzhou Hospital of Traditional Chinese Medicine
2025
Zhejiang Chinese Medical University
2025
Guangxi University of Chinese Medicine
2024
Nanjing Medical University
2024
University of Jinan
2022-2023
Inner Mongolia People's Hospital
2018-2023
Huaqiao University
2021-2022
Beijing University of Chemical Technology
2021
Ministry of Education of the People's Republic of China
2021
This study aimed to evaluate the biological role of geranylgeranyl diphosphate synthase (GGPPS) in progression lung adenocarcinoma. GGPPS expression was detected adenocarcinoma tissues by qRT-PCR, tissue microarray (TMA) and western blotting. The relationships between clinicopathological characteristics prognosis patients were assessed. down-regulated SPCA-1, PC9 A549 cells using siRNA up-regulated an adenoviral vector. roles cell proliferation, apoptosis, migration invasion determined MTT...
Capturing the three-dimensional (3D) shape of burden surface a blast furnace (BF) in real-time with high accuracy is crucial for improving gas flow distribution, optimizing coke operation, and stabilizing BF operation. However, it difficult to perform 3D measurement during ironmaking process because high-temperature, high-dust, lightless enclosed environment inside BF. To solve this problem, system developed study by combining an industrial endoscope virtual multi-head camera array...
Abstract Objective. Recent studies have shown that integrating inertial measurement unit (IMU) signals with surface electromyographic (sEMG) can greatly improve hand gesture recognition (HGR) performance in applications such as prosthetic control and rehabilitation training. However, current deep learning models for multimodal HGR encounter difficulties invasive modal fusion, complex feature extraction from heterogeneous signals, limited inter-subject model generalization. To address these...
In the modern chemical industry, only a small number of representative samples can be used to build soft models due practical factors. However, accuracy model built in this case is not sufficient meet demand. To overcome problem, novel virtual sample generation (VSG) method based on conditional generative adversarial networks (CGANs) with cycle structure (CS-CGAN) proposed augment data sets and enrich diversity. method, first, for obtaining inputs samples, Wasserstein GAN gradient penalty...
Objective. In order to better adapt clinical applications, this paper proposes a cross-validation decision-making fusion method of Vision Transformer and DenseNet161. Methods. The dataset is the most critical acetic acid image for diagnosis, SR areas are processed by specific method. Then, DenseNet161 models trained fivefold method, prediction results corresponding two fused different weights. Finally, five averaged obtain category with highest probability. Results. show that in reaches an...
Protein regulator of cytokinesis 1 (PRC1) has been reported to play important role in the pathogenesis various cancers. However, its colon cancer not studied. Here, we aimed investigate biological functions and potential mechanism PRC1 cancer.The expression level tissues cell lines was detected by quantitative real-time polymerase chain reaction (qRT-PCR), Western blotting, immunohistochemical (IHC) staining a tissue microarray (TMA). Furthermore, HCT116 SW480 were treated with short hairpin...
Abstract This study aims to determine the function of topotecan (TPT) in acute lung injury (ALI) induced by sepsis. The mouse sepsis model was constructed through cecal ligation and puncture (CLP). ALI score wet/dry (W/D) weight ratio were applied evaluate level injury. Hematoxylin–eosin staining used examine role TPT tissue a CLP‐induced model. Enzyme‐linked immunosorbent assay quantitative real‐time polymerase chain reaction detect concentrations inflammatory factors, such as interleukin‐6...
Objective. To explore an inpainting method that can balance texture details and visual observability to eliminate the specular reflection (SR) regions in colposcopic image, thus improving accuracy of clinical diagnosis for cervical cancer. Methods. (1) ensure smoothness, Gaussian Blur filling methods are applied global image. (2) Striving preserve anatomical image as much possible, exemplar-based is local blocks. (3) The images inpainted previous two steps integrated, so important...
We summarize some results from an extensive performance comparison of the procedures MSER-5 and N-Skart for handling simulation start-up problem. assume a fixed-length simulation-generated time series which point confidence-interval (CI) estimators steady-state mean are sought. uses data-truncation that minimizes half-length usual batch-means CI computed truncated data set. randomness test to determine beyond spaced batch means approximately independent each other simulation's initial...
In colposcopy-assisted diagnosis, the difference between different lesion grades of colposcopic images is small, and visual similarity high. Therefore, it a very challenging task to accurately diagnose cervical lesions through images. This paper proposes new risk assessment net in (RACNet). The RACNet mainly consists two parts. At first, location grade scales are detected multi-scale detection network. Then, these classified by designing multi-branch convolutional neural network (CNN)...
We summarize some results from an extensive performance comparison of the procedures MSER-5 and N-Skart for handling simulation start-up problem. assume a fixed-length simulation-generated time series which point confidence-interval (CI) estimators steady-state mean are sought. uses data-truncation that minimizes half-length usual batch-means CI computed truncated data set. randomness test to determine beyond spaced batch means approximately independent each other simulation's initial...
Abstract Accurate height and distribution of blast furnace burden is essential to improve coke-ore ratio, gas flow reduce CO 2 emission. However, conventional measure method by mechanical sounding rod can only or 3 fixed discontinues information. This article uses a light field imaging system estimate distribution. At first, the camera used obtain 4D image surface, position angle information utilized refocus focal stack images. Then depth surface obtained finding out refocused target based...
This paper aims to establish an intelligent diagnosis model of cervical cancer screening and solve the shortcomings physician traditional computer-aided methods in current. We propose a method based on transfer learning, which uses pre-trained MobileNetV2 classify colposcopic images. Firstly, data is augmented normalized, then ImageNet used realize classification lesions Finally, results are compared with those physicians. Experiments show that this can effectively diagnose CIN2+ accuracy...
Distributed crowdsourcing platforms technology has been widely used in existing applications based on network including Amazon, eBay and Alibaba. Apparently, current distributed method can response almost requests immediately when the system received prevent attacks from malicious users make whole with high robustness. However, privacy information attack hardly be prevented by servers may cause serious damage for individuals due to all contain platform structure. In this paper, we propose a...
In recent research, improving the performance and guaranteeing security of intelligent system is an essential issue for current system. High computation speed co-construction systems has been developed by researchers to enhance effectiveness However, disposing numbers data utilizing a safe method important challenge any focus on changing architecture modeling methods, which ignore mechanism may cause serious problems. this article, we propose novel can guarantee high Through smart contract...