A5101669571- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced Image Processing Techniques
- Advanced X-ray Imaging Techniques
- Image Processing Techniques and Applications
- AI in cancer detection
- Image and Signal Denoising Methods
- Advanced X-ray and CT Imaging
- Advanced Radiotherapy Techniques
- Brain Tumor Detection and Classification
- Air Quality and Health Impacts
- Advanced Neural Network Applications
- Face and Expression Recognition
- Genomics and Chromatin Dynamics
- Forensic Anthropology and Bioarchaeology Studies
- Colorectal Cancer Screening and Detection
- Obesity, Physical Activity, Diet
- Radiation Dose and Imaging
- Domain Adaptation and Few-Shot Learning
- Algorithms and Data Compression
- Cancer Genomics and Diagnostics
- Autopsy Techniques and Outcomes
- Ultrasound in Clinical Applications
- Advanced Vision and Imaging
- Advanced Text Analysis Techniques
Vision Medicals (China)
2022-2024
Medical Technologies (Czechia)
2023-2024
Children's Hospital of Zhejiang University
2023
Anhui Medical University
2022-2023
Beijing Institute of Technology
2008-2016
The global burden of digestive diseases has been rising in the last 30 years. rates and trends incidence, deaths, disability-adjusted life-years (DALYs) for need to be investigated.We extracted data on overall by cause between 1990-2019 from Global Burden Diseases 2019 website, including absolute number corresponding age-standardized incidence (ASIR), deaths (ASDR), DALYs (ASDALYs).Globally, incident cases, increased 74.44, 37.85, 23.46%, respectively, compared with that 1990, an increasing...
ABSTRACT The general framework of super resolution in computed tomography (CT) system is introduced. Two data acquisition ways before or after the reconstruction respectively are described. Three models including sinogram model, in‐plane model and z‐ axis addressed to adapt CT system. improved iterative back projection algorithm used this work. Experimental results based on simulated data, GE performance phantom scanned by LightSpeed VCT system, one patient volunteer TOSHIBA Aquilion a...
Accurate delineation of tumor targets is crucial for stereotactic body radiation therapy (SBRT) non-small cell lung cancer (NSCLC). This study aims to develop a deep learning-based segmentation approach accurately and efficiently delineate NSCLC using diagnostic PET-CT SBRT planning CT (pCT).The PET was registered pCT the transform matrix from registering pCT. We proposed 3D-UNet-based method segment on dual-modality PET-pCT images. network contained squeeze-and-excitation Residual blocks in...
Abstract MRI and CT images have been routinely used in clinical practice for treatment planning of the head‐and‐neck (HAN) radiotherapy. Delineating organs‐at‐risk (OAR) is an essential step radiotherapy, however, it time‐consuming prone to inter‐observer variation. The existing automatic segmentation approaches are either limited by image registration or lack global spatial awareness, thus under‐performed when dealing with complex anatomies. Herein, we propose a full‐scale attention network...
In 2020, our center established a Tanner-Whitehouse 3 (TW3) artificial intelligence (AI) system using convolutional neural network (CNN), which was built upon 9059 radiographs. However, the system, study is based, lacked gold standard for comparison and had not undergone thorough evaluation in different working environments.
Abstract Objective. Whole slide images (WSIs) play a crucial role in histopathological analysis. The extremely high resolution of WSIs makes it laborious to obtain fine-grade annotations. Hence, classifying with only slide-level labels is often cast as multiple instance learning (MIL) problem where WSI regarded bag and tiled into patches that are instances. purpose this study develop novel MIL method for histopathology Approach. We propose iterative (IMIL) classification representations...
Radiation therapy is the primary treatment for recurrent nasopharyngeal carcinoma. However, it may induce necrosis of nasopharynx, leading to severe complications such as bleeding and headache. Therefore, forecasting nasopharynx initiating timely clinical intervention has important implications reducing caused by re-irradiation. This research informs decision-making making predictions on re-irradiation carcinoma using deep learning multi-modal information fusion between multi-sequence...
Background Pneumoconiosis is the most important occupational disease all over world, with high prevalence and mortality. At present, monitoring of workers exposed to dust diagnosis pneumoconiosis rely on manual interpretation chest radiographs, which subjective low efficiency. With development artificial intelligence technology, a more objective efficient computer aided system for can be realized. Therefore, present study reported novel deep learning (DL) (AI) detecting in digital frontal...
Glioblastoma (GBM) and brain metastases (BMs) are the two most common malignant tumors in adults. Magnetic resonance imaging (MRI) is a commonly used method for screening evaluating prognosis of tumors, but specificity sensitivity conventional MRI sequences differential diagnosis GBM BMs limited. In recent years, deep neural network has shown great potential realization diagnostic classification establishment clinical decision support system. This study aims to apply radiomics features...
An approach for improving the z-axis resolution of MRI using super (SR) technology in post processing step is proposed. The 2D multi-slice often anisotropic, z-resolution lower than plane resolution. And isotropic necessary certain diagnostic while truly image hardly obtained. In this case an efficiency post-processing to obtain demand image. method, imaging volume acquired multiple times with small spatial shifts z-axis. We use algorithm which introduces Papoulis-Gerchberg extrapolation...
An approach for improving the z-axis resolution of spiral CT using super (SR) technology in post processing step is proposed this work. As has ability to produce over-lapped slice images without scanning, sub-slice thickness shifts require neither change hardware nor any additional radiation dose. The thinner obtained by combining those slices and applying SR algorithm. It secure convenient be used clinical cases. We use an algorithm which introduces Papoulis-Gerchberg extrapolation within...
The algorithm of touching string segmentation is concerned in the work. We proposed an example based algorithm. supervised learning was used on labelled examples and Markov Random Field has been applied on. belief propagation minimization method to select candidate patches compatibility neighbour patches. output MRF after iterative forms a probability map. cut position extracted from experiment shows that effective.
Ring artifacts often appear in cone-beam computed tomography (CBCT) images due to the inconsistent response of detector pixels. How remove ring without impairing image quality is still a hard problem. This article proposes novel method from CBCT images. First, reconstructed transformed Cartesian coordinates into polar coordinates, such that are as stripe easier be removed. Second, minimization model based on smoothing introduced smooth major edges reserved while eliminated special...
In this paper, we proposed a novel approach to image completion for overlapping chromosomes. our system, only given missing regions, the task can be performed automatically without human intervention. We address problem of chromosomes in context discrete global optimization problem. order reconstruct original chromosome as faithfully possible, objective cost function is defined under constraint conditions band patterns image, and corresponds energy Markov random fields. For efficiently...