A5089126739- Medical Imaging Techniques and Applications
- Advanced Image Processing Techniques
- Image and Signal Denoising Methods
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- Image Processing Techniques and Applications
- Opportunistic and Delay-Tolerant Networks
- Advanced X-ray and CT Imaging
- Mobile Ad Hoc Networks
- Energy Efficient Wireless Sensor Networks
- Advanced Neuroimaging Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Vision and Imaging
- Sparse and Compressive Sensing Techniques
- Advanced Radiotherapy Techniques
- Advanced Measurement and Detection Methods
- Caching and Content Delivery
- Generative Adversarial Networks and Image Synthesis
- COVID-19 diagnosis using AI
- AI in cancer detection
- Brain Tumor Detection and Classification
- Image and Video Stabilization
- Functional Brain Connectivity Studies
- Face and Expression Recognition
- Nuclear Physics and Applications
Chengdu University of Information Technology
2016-2025
Sichuan University
2015-2025
Chengdu University
2010-2024
Chinese Academy of Medical Sciences & Peking Union Medical College
2023
West China Hospital of Sichuan University
2019
Seattle University
2019
Southwest Jiaotong University
2013
Leshan Normal University
2013
PRG S&Tech (South Korea)
2011
McGill University
2009
Objective: To obtain high-quality positron emission tomography (PET) image with low-dose tracer injection, this study attempts to predict the standard-dose PET (S-PET) from both its (L-PET) counterpart and corresponding magnetic resonance imaging (MRI). Methods: It was achieved by patch-based sparse representation (SR), using training samples a complete set of MRI, L-PET S-PET modalities for dictionary construction. However, number is often limited. In practice, many generally have...
This paper discusses a novel conceptual formulation of the fractional-order variational framework for retinex, which is partial differential equation (FPDE) retinex multi-scale nonlocal contrast enhancement with texture preserving. The well-known shortcomings traditional integer-order computation-based contrast-enhancement algorithms, such as ringing artefacts and staircase effects, are still in great need special research attention. Fractional calculus has potentially received prominence...
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) are patch-based and ignore consistency of pixels overlapped patches. In addition, features learned by these always contain shifted versions same features. recent convolutional sparse coding (CSC) has developed to address this paper, inspired several successful applications CSC field signal processing, we...
Magnetic resonance (MR) images are usually limited by low spatial resolution, which leads to errors in post-processing procedures. Recently, learning-based super-resolution methods, such as sparse coding and convolution neural network, have achieved promising reconstruction results scene images. However, these methods remain insufficient for recovering detailed information from low-resolution MR due the size of training dataset.To investigate different edge responses using kernel sizes, this...
Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation . However, most existing SSL methods predict pixels in single image independently, ignoring relations among images and categories. In this paper, we propose two-stage Dual Contrastive Learning Network semi-supervised MoS, which utilizes global local contrastive strengthen classes. Concretely, Stage 1, develop similarity-guided explore...
Multi-source Domain Adaptation (MDA) aims to transfer knowledge from multiple labeled source domains an unlabeled target domain. Nevertheless, traditional methods primarily focus on achieving inter-domain alignment through sample-level constraints, such as Maximum Mean Discrepancy (MMD), neglecting three pivotal aspects: 1) the potential of data augmentation, 2) significance intra-domain alignment, and 3) design cluster-level constraints. In this paper, we introduce a novel hardness-driven...
Semi-supervised learning (SSL) has shown notable potential in relieving the heavy demand of dense prediction tasks on large-scale well-annotated datasets, especially for challenging multi-organ segmentation (MoS). However, prevailing class-imbalance problem MoS caused by substantial variations organ size exacerbates difficulty SSL network. To address this issue, paper, we propose an innovative semi-supervised network with BAlanced Subclass regularIzation and semantic-Conflict penalty...
The black hole attack is one of the security attacks that occur in mobile ad hoc networks (MANETs). In this article, routing issues and problem coordinated by multiple holes acting group MANET are addressed detail. Two authentication mechanisms, based on hash function, message code (MAC) pseudo random function (PRF), proposed to provide fast verification identification, identify cooperating with each other discover safe avoiding cooperative attack.
We propose an ontological Chinese legal consultation system (CLCS) based on characteristics by integrating statutes and judicial precedents to facilitate the retrieval of relevant judgments for general public. Ontology, emerging research topic in recent years, incorporates a hierarchical structure supports logical reasoning, which can reduce semantic ambiguities extract implied information. constructed ontology case using bottom-up method top-down method, respectively. Then, test precision...