A5079154390- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- Domain Adaptation and Few-Shot Learning
- Medical Imaging and Analysis
- Multimodal Machine Learning Applications
- AI in cancer detection
- Retinal Imaging and Analysis
- Epoxy Resin Curing Processes
- Synthesis and properties of polymers
- AI in Service Interactions
- Cancer-related molecular mechanisms research
- Renal cell carcinoma treatment
- Cervical Cancer and HPV Research
- Speech and dialogue systems
- Medical Imaging Techniques and Applications
- Renal and Vascular Pathologies
- Head and Neck Cancer Studies
- Visual Attention and Saliency Detection
- Brain Tumor Detection and Classification
- Adsorption and biosorption for pollutant removal
- Advanced X-ray and CT Imaging
- Polymer composites and self-healing
- Chromium effects and bioremediation
- Language Acquisition and Education
Northwestern Polytechnical University
2022-2025
Fujian Agriculture and Forestry University
2024
Fudan University
2022-2023
South China Normal University
2020-2022
Beijing University of Chemical Technology
2019-2022
Yale University
2022
Shanghai University of Traditional Chinese Medicine
2020
Xiamen University
2009-2016
Segmentation of retinal vessels on fundus images plays a critical role in the diagnosis micro-vascular and ophthalmological diseases. Although being extensively studied, this task remains challenging due to many factors including highly variable vessel width poor vessel-background contrast. In paper, we propose multiscale feature interaction network (MFI-Net) for segmentation, which is U-shaped convolutional neural equipped with pyramid squeeze-and-excitation (PSE) module, coarse-to-fine...
Self-supervised learning (SSL) has long had great success in advancing the field of annotation-efficient learning. However, when applied to CT volume segmentation, most SSL methods suffer from two limitations, including rarely using information acquired by different imaging modalities and providing supervision only bottleneck encoder layer. To address both we design a pretext task align each 3D corresponding 2D generated X-ray image extend self-distillation deep self-distillation. Thus,...
The interactions of microbes with metal ions form an important basis for our study biotechnological applications. Despite the recent progress in studying some properties Au(III) adsorption and reduction by Bacillus megatherium D01 biomass, there is still a need additional data on molecular mechanisms biosorbents responsible their to have further insight make better exposition.The biosorption mechanism onto resting cell biomass level has been studied here. infrared (IR) spectroscopy that...
Large class sizes significantly limit EFL (English as a foreign language) learners' speaking opportunities in class, and it is also quite difficult for them to have regular language partner if they want practice English after class. Microsoft Xiaoying, chatbot available on smart phones, offers learners virtual conduct conversational with engage learning anytime anywhere. This study evaluates 50 accuracy, errors, improvements oral tasks during 28 days of training employing this chatbot, which...
Cross-domain joint segmentation of optic disc and cup on fundus images is essential, yet challenging, for effective glaucoma screening. Although many unsupervised domain adaptation (UDA) methods have been proposed, these can hardly achieve complete alignment, leading to suboptimal performance. In this paper, we propose a triple-level alignment (TriLA) model address issue by aligning the source target domains at input level, feature output level simultaneously. At learnable Fourier (LFDA)...
Universal segmentation models offer significant potential in addressing a wide range of tasks by effectively leveraging discrete annotations. As the scope and modalities expands, it becomes increasingly important to generate strategically position task- modal-specific priors within universal model. However, existing often overlook correlations between different priors, optimal placement frequency these remain underexplored. In this paper, we introduce MedUniSeg, prompt-driven model designed...
Platinum nanomaterial is one of the significant noble metal catalysts, and interaction platinum with microbe key factors in influencing size distribution nanoparticles on microbial biomass. Some properties Pt(IV) adsorption reduction by resting cells Bacillus megatherium D01 biomass have once been investigated, still mechanism active biosorption remains to be seen requires further elucidating. A insight into onto D02 a molecular level has obtained. The image scanning electron microscopy...
Radiation therapy is a primary and effective NasoPharyngeal Carcinoma (NPC) treatment strategy. The precise delineation of Gross Tumor Volumes (GTVs) Organs-At-Risk (OARs) crucial in radiation treatment, directly impacting patient prognosis. Previously, the GTVs OARs was performed by experienced oncologists. Recently, deep learning has achieved promising results many medical image segmentation tasks. However, for NPC segmentation, few public datasets are available model development...
This study aims to investigate the association between CD4+ T cell count and combined antiretroviral therapy (cART) with prevalence of anal human papillomavirus (HPV) infection among HIV-positive male cohort in China.A survey was conducted men from a HIV Taizhou, China 2016 2019. A face-to-face questionnaire interview administered, an anal-canal swab collected for HPV genotyping.A total 766 were recruited. The lower those increased than decreased or unchanged (46.5 vs. 56.6%, p = 0.033)...
Bisphenol A dicyanate (BADCy) resin microparticles were prepared by precipitation polymerization synthesis and homogeneously dispersed in a BADCy prepolymer matrix to prepare self-reinforced composites. The active functional groups of the characterized Fourier transform infrared (FT-IR) spectroscopy. results an FT-IR curve showed that had triazine ring group also reactive -OCN, which can initiate reaction with matrix. structure was scanning electron microscopy (SEM) transmission (TEM). From...
This article reports on a teaching experiment that uses speech visualization technology to facilitate EFL (English as foreign language) learners’ ability of imitating and reading aloud (IRA). Traditional practice “listen repeat” used in pronunciation intonation training often only hazily illustrates some salient features, such pitch intensity, etc., making it difficult for learners accurately differentiate the features capture subtlety target language . As transforms aural information into...
<title>Abstract</title> The high-dimensional linear separability of the classic support vector machine is achieved through kernel method, which maps data to a space. However, method involves estimating multiple parameters, reduces model's computational efficiency. To address this, some related works use quantum estimation replace thus reducing load associated with parameter in machines. Despite these improvements, machines face challenge establishing correlations between different points...
Scribble-based weakly supervised segmentation techniques offer comparable performance to fully methods while significantly reducing annotation costs, making them an appealing alternative. Existing often rely on auxiliary tasks enforce semantic consistency and use hard pseudo labels for supervision. However, these overlook the unique requirements of models trained with sparse annotations. Since model must predict pixel-wise maps limited annotations, ability handle varying levels richness is...
Distribution shifts widely exist in medical images acquired from different centers, hindering the deployment of semantic segmentation models trained on data one center (source domain) to another (target domain). While unsupervised domain adaptation (UDA) has shown significant promise mitigating these shifts, it poses privacy risks due sharing between centers. To facilitate while preserving privacy, source-free (SFDA) and test-time (TTA) have emerged as effective paradigms, relying solely...