A5101517160- Medical Imaging Techniques and Applications
- Radiation Dose and Imaging
- Advanced X-ray and CT Imaging
- Lung Cancer Diagnosis and Treatment
- Radiology practices and education
- Optical Coherence Tomography Applications
- Acute Ischemic Stroke Management
- Fungal Biology and Applications
- Glaucoma and retinal disorders
- Venous Thromboembolism Diagnosis and Management
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Traditional and Medicinal Uses of Annonaceae
- Antiplatelet Therapy and Cardiovascular Diseases
- Cancer Mechanisms and Therapy
- COVID-19 diagnosis using AI
- Synthesis and Biological Activity
- Advanced MRI Techniques and Applications
- Retinal Imaging and Analysis
- Advanced Neuroimaging Techniques and Applications
First Affiliated Hospital of Jinan University
2024
Nankai University
2024
Nanyang Normal University
2016-2022
Nanjing Medical University
2021
Southern Medical University
2016-2019
Dalian Maritime University
2015
To develop and evaluate deep learning models for the detection semiquantitative analysis of cardiomegaly, pneumothorax, pleural effusion on chest radiographs.In this retrospective study, were trained lesion or lung segmentation. The first dataset consisted 2838 radiographs from 2638 patients (obtained between November 2018 January 2020) containing findings positive that used in developing Mask region-based convolutional neural networks plus Point-based Rendering models. Separate each...
Low-dose computed tomography (LdCT) has been widely used in clinical applications including image-guided biopsy needle and lung screening. With the low radiation dose data acquiring during scans, image quality will degrade due to excessive quantum noise if there is no adequate treatment processing for reconstruction. For conventional low-dose CT reconstruction, much effort spend on preservation of edges while removing noise, not enough attention paid texture preserving. However, textures are...
Sparse-view CT has the advantages of accelerated data collection and reduced radiation dose, but missing arising from process causes serious streaking artifact noise in images reconstructed using traditional filtering back projection algorithm (FBP). To solve this problem, we propose a multi-scale wavelet residual network (MWResNet) to restore sparse-view images.The MWResNet was based on combination deep learning model MWCNN, combined with block enhance network's ability embed image features...
Segmentation of pulmonary nodules in computer- aided diagnosis systems is a challenging problem. Currently, method image segmentation using an active contour model already being widely applied several fields. This paper analyzed the difficulty nodules, focusing on and improved model. Then this compared advantages performance these models. At last some methods used to improve accuracy models were summarized.
In some clinical applications, prior normal-dose CT (NdCT) images are available, and the valuable textures structure features in them may be used to promote follow-up low-dose (LdCT) reconstruction. This study aims learn texture information from NdCT leverage it for LdCT image reconstruction preserve features. Specifically, proposed method first learns those patches with similar structures image, can clustered by searching context efficiently surroundings of current patch. Then utilizes...
In this study we present a novel contrast-medium anisotropy-aware TTV (Cute-TTV) model to reflect intrinsic sparsity configurations of cerebral perfusion Computed Tomography (PCT) object. We also propose PCT reconstruction scheme via the Cute-TTV improve performance reconstructions in weak radiation tasks (referred as CuteTTV-RECON). An efficient optimization algorithm is developed for CuteTTV-RECON. Preliminary simulation studies demonstrate that it can achieve significant improvements over...
The effectiveness of the standard bilateral filter is rather good in some cases for lots images. It could not only smooth images, but also preserve edges images simultaneously. However, shape coronary angiography performing complex, diameters blood vessels changing tremendously and image noise etc. greatly increased difficulty processing angiography. What's more, contrast ratio between vascular structure shown background generally low. Therefore, tends to blur indispensable develop an...