A5045605868- Head and Neck Cancer Studies
- Cancer Diagnosis and Treatment
- Tracheal and airway disorders
- Cancer-related molecular mechanisms research
- Autonomous Vehicle Technology and Safety
- Advanced Neural Network Applications
- Domain Adaptation and Few-Shot Learning
- Lung Cancer Treatments and Mutations
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and LiDAR Applications
- Text and Document Classification Technologies
- Robotics and Sensor-Based Localization
- Reconstructive Surgery and Microvascular Techniques
- Visual Attention and Saliency Detection
- Multimodal Machine Learning Applications
- Cleft Lip and Palate Research
- RNA modifications and cancer
- Cancer-related gene regulation
- Radiomics and Machine Learning in Medical Imaging
- Cell death mechanisms and regulation
- Video Surveillance and Tracking Methods
- Olfactory and Sensory Function Studies
- Industrial Automation and Control Systems
- Gastric Cancer Management and Outcomes
- Lung Cancer Diagnosis and Treatment
Ningxia Medical University
2025
Suzhou University of Science and Technology
2021-2024
Shandong Provincial Hospital
2020-2024
Shandong First Medical University
2020-2024
Southeast University
2023
Karamay Central Hospital
2022
Qingdao University
2018-2021
Affiliated Hospital of Qingdao University
2018-2021
Second Hospital of Shandong University
2016-2020
Nanjing University of Science and Technology
2017-2019
Objective: To explore the quantitative value of T2mapping sequence in evaluating early glenohumeral joint cartilage injury. Methods: A total 92 patients with shoulder pain who underwent routine and scanning General Hospital Ningxia Medical University from March 2023 to 2024 were retrospectively collected as a case group. The classified into tendinitis group, partial tear group full according degree tendon Another 25 healthy subjects same age selected control Two physicians divided articular...
Abstract Support vector data description (SVDD) has been effectively used in many anomaly detection problems. As equipped with kernel functions, its training complexity grows exponentially the increase of data, which makes it less practical for large-scale dataset. In this paper, we proposed a boundary samples extraction SVDD(BSE-SVDD) method based on reduction, aiming data. Firstly, BSE mechanism is established basis demonstrating that spatial position sample related to corresponding...
Abstract Long noncoding RNAs (lncRNAs) have been identified as potential prognostic tools and therapeutic biomarkers for a variety of human cancers. However, the functional roles underlying mechanisms key lncRNAs affecting laryngeal squamous cell carcinomas (LSCCs) are largely unknown. Here, we adopted novel subpathway strategy based on lncRNA-mRNA profiles from Cancer Genome Atlas (TCGA) database lncRNA deleted in lymphocytic leukemia 2 (DLEU2) an oncogene pathogenesis LSCCs. We found that...
Road Detection is a basic task in automated driving field, which 3D lidar data commonly used recently. In this paper, we propose to rearrange into new organized form construct direct spatial relationship among point cloud, and put forward features for real-time road detection tasks. Our model works based on two prerequisites: (1) regions are always flatter than non-road regions. (2) Light travels straight lines uniform medium. Based prerequisite 1, difference-between-lines feature, while...
Earphones have become a popular voice input and interaction device. However, airborne speech is susceptible to ambient noise, making it necessary improve the quality intelligibility of on earphones in noisy conditions. As dual-microphone structure (i.e., outer in-ear microphones) has been widely adopted (especially ANC earphones), we design EarSpeech which exploits acoustic sensory as complementary modality enable enhancement. The key idea that less sensitive noise exhibits correlation with...
The Lifelong Multi-Label (LML) image recognition builds an online class-incremental classifier in a sequential multilabel data stream. However, training on the with different Partial Labels may result more serious Catastrophic Forgetting old classes. To solve problem, study proposes Augmented Graph Convolutional Network (AGCN)to build Correlation Matrix (ACM) across partial-label tasks and sustain catastrophic forgetting. First, ACM, intra-task relations derive from hard label statistics,...
Recently, plenty of millimeter-wave image concealed object detection models have achieved superior performance on benchmark datasets. The success these heavily depends a large amount fully annotated data. However, noisy-label data often exist in large-scale dataset, which deteriorate the models. In this article, we delve into training detector with label noise, where recognize divergent types noisy annotations. To tackle multitype noise problem, propose unified framework, including two...
Multi-Label Continual Learning (MLCL) is a framework designed for class-incremental multi-label image recognition. However, MLCL faces two critical challenges: the construction of label relationships on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">past-missing and future-missing partial labels</i> training data, problem xmlns:xlink="http://www.w3.org/1999/xlink">catastrophic forgetting</i> , which leads to poor generalization. To address...
For coronal shear fractures of humeral capitellum, the lateral approach is most commonly used surgical approach. However, exposure range anterior aspect distal humerus inadequate. The anterolateral has also been adopted to overcome this disadvantage. seems anatomically complex due risk iatrogenic injury radial nerve. So far, optimal for treatment capitellar remains inconclusive. purpose study prospectively review and compare early clinical radiographic outcomes treated with open reduction...
Due to the intraarticular and complex nature of coronal shear fracture humeral capitellum its rarity, it has been difficult formulate a universally accepted method surgical management. The purpose this study is retrospectively evaluate clinical outcomes 15 patients with isolated fractures treated by Herbert screw fixation through anterolateral approach, address safety tips for procedure. This retrospective included without posterior involvement, which were classified according Dubberley...
Laryngeal cancer is one of the most common fatal cancers among head and neck carcinomas, whose mechanism, however, remains unclear. The proneural basic-helix-loop-helix protein achaete-scute complex homologue-1, a member basic helix-loop-helix family, plays very important role in many cancers. This study aims to explore clinical value mechanism homologue-1 laryngeal cancer. Methods including Cell Counting Kit-8, flow cytometry, Transwell invasion assays, scratch assay were adopted further...
Paris saponin has shown great therapeutic value in cancer therapy. We used isolated II (PSII), an active component of saponin, and demonstrated its antitumor effect on human head neck squamous cell carcinoma lines. Additionally, we investigated mechanisms action vivo by establishing a xenograft mouse model. The results showed that PSII had presented strong anticancer effects both hypopharyngeal malignant tumor lines (FaDu) laryngeal (Tu212 Tu686). In addition, successfully cultured the stem...
To determine the expression of gene programmed cell death 5 (PDCD5) and its protein PDCD5 in laryngeal squamous carcinoma to analyse possible correlations with clinicopathological parameters.PDCD5 mRNA was assessed using reverse transcription-polymerase chain reaction studied Western blot analysis immunohistochemistry morphologically normal para-carcinoma tissue.A total 41 29 tissue specimens were examined. Expression both significantly reduced compared tissue. correlated clinical stage...
In this paper, a bottom-up and data-driven model is introduced to detect co-salient objects from an image pair. Inspired by the biologically-plausible across-scale architecture, we propose multi-layer fusion algorithm extract conspicuous parts input image. At each layer, two existing saliency models are first combined obtain initial map, which simultaneously codes for color names based surrounded cue background measure boundary connectivity. Then global with respect invoked refine fuse...
Head and neck squamous cell carcinomas (HNSCC) are still one of the most common malignant tumors in China, with a high metastasis rate poor prognosis. The tumor immune microenvironment can affect occurrence, development prognosis tumors, but underlying mechanism is unclear. In this study, we tried to describe correlation between recurrence HNSCC (TME). expression data [estimate level stromal infiltration, (ESTIMATE)] algorithm was used identify estimate highly correlated cells, prognostic...