A5018774370- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- AI in cancer detection
- Image and Signal Denoising Methods
- Radiation Dose and Imaging
- Advanced Image Processing Techniques
- Brain Tumor Detection and Classification
- Cardiac Imaging and Diagnostics
- Medical Imaging and Analysis
- Advanced Radiotherapy Techniques
- Image Processing Techniques and Applications
- Cell Image Analysis Techniques
- MRI in cancer diagnosis
- CCD and CMOS Imaging Sensors
- Bioinformatics and Genomic Networks
- Advanced SAR Imaging Techniques
- Nuclear Physics and Applications
- Plasmonic and Surface Plasmon Research
- Metabolomics and Mass Spectrometry Studies
- Radiopharmaceutical Chemistry and Applications
- Lung Cancer Diagnosis and Treatment
- Photonic and Optical Devices
Shenzhen Institutes of Advanced Technology
2020-2025
Chinese Academy of Sciences
2020-2025
Wuhan National Laboratory for Optoelectronics
2020-2021
Huazhong University of Science and Technology
2020-2021
China Academy of Chinese Medical Sciences
2020
Ministry of Education of the People's Republic of China
2020
To suppress noise and artifacts caused by the reduced radiation exposure in low-dose computed tomography, several deep learning (DL)-based image restoration methods have been proposed over past few years. Many of these popular DL-based adopt an encoder–decoder framework, for instance, residual convolutional neural network. However, this framework may suffer from information loss continual downsampling operations. In article, cascaded networks (DCRNs) are to optimize First, cross up-...
Dose reduction in computed tomography (CT) has gained considerable attention clinical applications because it decreases radiation risks. However, a lower dose generates noise low-dose (LDCT) images. Previous deep learning (DL)-based works have investigated ways to improve diagnostic performance address this ill-posed problem. most of them disregard the anatomical differences among different human body sites constructing mapping function between LDCT images and their high-resolution...
Myocardial blood flow (MBF) provides important diagnostic information for myocardial ischemia. However, dynamic computed tomography perfusion (CTP) needed MBF involves multiple exposures, leading to high radiation doses. This study investigated synthesizing from simulated static CTP explore dose reduction potential, bypassing the traditional input function. The included 253 subjects with intermediate-to-high pretest probabilities of obstructive coronary artery disease (CAD). was...
Nasopharyngeal carcinoma (NPC) is a malignant tumor primarily treated by radiotherapy. Accurate delineation of the target essential for improving effectiveness However, segmentation performance current models unsatisfactory due to poor boundaries, large-scale volume variation, and labor-intensive nature manual In this paper, MMCA-Net, novel network NPC using PET/CT images that incorporates an innovative multimodal cross attention transformer (MCA-Transformer) modified U-Net architecture,...
Brain structure segmentation is of great value in diagnosing brain disorders, allowing radiologists to quickly acquire regions interest and assist subsequent analyses, diagnoses treatment. Current methods are usually applied magnetic resonance (MR) images, which provide higher soft tissue contrast better spatial resolution. However, fewer conducted on a positron emission tomography/magnetic imaging (PET/MRI) system that combines functional structural information improve analysis accuracy.In...
Accurate segmentation of lung nodules is crucial for the early diagnosis and treatment cancer in clinical practice. However, similarity between surrounding tissues has made their a longstanding challenge.
The novel coronavirus (COVID-19) pneumonia has become a serious health challenge in countries worldwide. Many radiological findings have shown that X-ray and CT imaging scans are an effective solution to assess disease severity during the early stage of COVID-19. artificial intelligence (AI)-assisted diagnosis works rapidly been proposed focus on solving this classification problem determine whether patient is infected with Most these designed networks applied single image perform...
Abstract Many deep learning methods have been proposed to improve the quality of low‐dose PET images (LPET), which usually construct end‐to‐end networks with certain radiation dose inputs. However, these approaches omitted noise disparity in images, may differ among manufacturers or populations. Therefore, we tend exploit differences achieve adaptive restoration. We a 3D level‐guided restoration network for LPET including (1) level‐aware subnetwork and (2) subnetwork. The first aims predict...
Many deep learning (DL)-based image restoration methods for low-dose CT (LDCT) problems directly employ the end-to-end networks on training data without considering dose differences. However, radiation difference has a great impact ultimate results, and lower doses increase difficulty of restoration. Moreover, there is increasing demand to design estimate acceptable scanning patients in clinical practice, necessitating dose-aware embedded with adaptive estimation. In this paper, we consider...
This paper presents an approach to the improvement of range ambiguity resolution performance by making use extended Chinese Remainder Theorem (CRT), which is valid for moduli non-mutually prime. A CRT algorithm possessing computational simplicity and feasibility proposed alleviate over-sensitive error that inherent in classical caused noisy data. Some results from theoretical analysis Monte Carlo simulation show that, under some condition weaker than usual. probability correct greater...
Abstract Objective. Nuclei segmentation is crucial for pathologists to accurately classify and grade cancer. However, this process faces significant challenges, such as the complex background structures in pathological images, high-density distribution of nuclei, cell adhesion. Approach. In paper, we present an interactive nuclei framework that increases precision segmentation. Our incorporates expert monitoring gather much prior information possible segment nucleus images through limited...
The short frames of low-count positron emission tomography (PET) images generally cause high levels statistical noise. Thus, improving the quality by using image postprocessing algorithms to achieve better clinical diagnoses has attracted widespread attention in medical imaging community. Most existing deep learning-based PET enhancement methods have achieved satisfying results, however, few them focus on denoising with magnetic resonance (MR) modality as guidance. prior context features...