A5024753869- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Neural Networks and Applications
- Infrastructure Maintenance and Monitoring
- Asphalt Pavement Performance Evaluation
- Simulation and Modeling Applications
- AI in cancer detection
- Brain Tumor Detection and Classification
- Machine Learning and Algorithms
- Machine Learning and Data Classification
- Adversarial Robustness in Machine Learning
- Geotechnical Engineering and Underground Structures
- Advanced Sensor and Control Systems
- Image Retrieval and Classification Techniques
- Fault Detection and Control Systems
- Lung Cancer Diagnosis and Treatment
- Remote Sensing and LiDAR Applications
- Advanced Image and Video Retrieval Techniques
- Advanced Algorithms and Applications
- Advanced machining processes and optimization
- Cell Image Analysis Techniques
- BRCA gene mutations in cancer
- Advanced Image Processing Techniques
- Piezoelectric Actuators and Control
Sichuan University
2020-2024
King's College London
2023-2024
Changsha University of Science and Technology
2021-2024
University of Leicester
2019-2023
Northeastern University
2021-2023
Lanzhou Jiaotong University
2019-2021
Ruijin Hospital
2008-2021
Shanghai Jiao Tong University
2019-2021
China Railway Group (China)
2014
Wuhan University
2013
Integrating artificial intelligence with food category recognition has been a field of interest for research the past few decades. It is potentially one next steps in revolutionizing human interaction food. The modern advent big data and development data-oriented fields like deep learning have provided advancements recognition. With increasing computational power ever-larger datasets, approach's potential yet to be realized. This survey provides an overview methods that can applied various...
Aim: Alzheimer's disease is a neurodegenerative that causes 60–70% of all cases dementia. This study to provide novel method can identify AD more accurately. Methods: We first propose VGG-inspired network (VIN) as the backbone and investigate use attention mechanisms. proposed an Disease VGG-Inspired Attention Network (ADVIAN), where we integrate convolutional block modules on VIN backbone. Also, 18-way data augmentation avoid overfitting. Ten runs 10-fold cross-validation are carried out...
The COVID-19 coronavirus has spread rapidly around the world and caused global panic. Chest CT images play a major role in confirming positive patients. computer aided diagnosis of from based on artificial intelligence have been developed deployed some hospitals. But environmental influences movement lung will affect image quality, causing parenchyma pneumonia area unclear images. Therefore, performance COVID-19's diagnostic algorithm is reduced. If chest are reconstructed, accuracy may be...
Novel coronavirus pneumonia (NCP) has become a global pandemic disease, and computed tomography-based (CT) image analysis recognition are one of the important tools for clinical diagnosis. In order to assist medical personnel achieve an efficient fast diagnosis patients with new pneumonia, this paper proposes assisted algorithm based on ensemble deep learning. The method combines Stacked Generalization learning VGG16 form cascade classifier, information constituting classifier comes from...
Alzheimer’s and related diseases are significant health issues of this era. The interdisciplinary use deep learning in field has shown great promise gathered considerable interest. This paper surveys literature to disease, mild cognitive impairment, from 2010 early 2023. We identify the major types unsupervised, supervised, semi-supervised methods developed for various tasks field, including most recent developments, such as application recurrent neural networks, graph-neural generative...
Inspired by the biological evolution, this paper proposes an evolutionary synthesis mechanism to automatically evolve DenseNet towards high sparsity and efficiency for medical image classification. Unlike traditional automatic design methods, generates a sparser offspring in each generation based on its previous trained ancestor. Concretely, we use synaptic model mimic evolution asexual reproduction. Each generation's knowledge is passed down descendant, environmental constraint limits size...
Aim . This study proposes a new artificial intelligence model based on cardiovascular computed tomography for more efficient and precise recognition of Tetralogy Fallot (TOF). Methods Our is structurally optimized stochastic pooling convolutional neural network (SOSPCNN), which combines pooling, structural optimization, network. In addition, multiple‐way data augmentation used to overcome overfitting. Grad‐CAM employed provide explainability the proposed SOSPCNN model. Meanwhile, both...
Abstract Counting high‐density objects quickly and accurately is a popular area of research. Crowd counting has significant social economic value major focus in artificial intelligence. Despite many advancements this field, them are not widely known, especially terms research data. The authors proposed three‐tier standardised dataset taxonomy (TSDT). Taxonomy divides datasets into small‐scale, large‐scale hyper‐scale, according to different application scenarios. This theory can help...
This letter presents a method of seamline determination based on segmentation for orthoimage mosaicking in an urban area. Image is used to achieve regions objects. First, preferred through which seamlines are inclined be passed determined by spans segmented regions. Second, pixel-level optimization carried out using Dijkstra's algorithm differential cost find the optimized seamline. The experimental results digital aerial orthoimages area prove that new promising mosaicking.
The area Voronoi diagrams with overlap (AVDO) method was recently presented and has been used to generate a seamline network for the mosaicking of orthoimages. shows considerable potential advantages seamless mosaics covering large geographic region. In this paper, is further improved, refinement approach based on AVDO presented. improvements include detection valid regions orthoimages, more general algorithm generation bisectors, combining bottleneck model Dijkstra's algorithm. Finally,...
Few-shot and one-shot learning have been the subject of active intensive research in recent years, with mounting evidence pointing to successful implementation exploitation few-shot algorithms practice. Classical statistical theories do not fully explain why few- or is at all possible since traditional generalisation bounds normally require large training testing samples be meaningful. This sharply contrasts numerous examples one- systems applications. In this work we present mathematical...
Working memory (WM) - one of the brain ability that maintains information can evaluate function brain. Activities related to sustention, inhibition and disinhibition have gathered significant attention for basic neurocognitive architecture. Although researchers proposed some models attempt explain entire procedure WM, little evidence proof describe it, more particularly, regions structures maintenance, require investigation. We used phase lock coherence general partial directed construct...
Abstract Image mosaicking is a process during which multiple orthoimages are combined into single seamless composite orthoimage. One of the most difficult steps in automatic seamline determination. This paper presents novel algorithm that selects seamlines based on marker-based watershed segmentation. A representative extracted at object level and pixel as follows. First, segmentation performed to obtain objects. To avoid over-segmentation, regional adaptive proposed. Second, difference...
To explore the characteristics of breast ductal carcinoma in situ (DCIS) on real-time grayscale contrast-enhanced ultrasound (CEUS) imaging and diagnostic value CEUS DCIS.A total 127 histopathologically confirmed DCIS lesions 124 fibroadenomas (FAs; controls) were subjected to conventional CEUS. Next, findings FA lesions, including morphologic features quantitative parameters, analyzed.Binary logistic regression was used identify independent risk factors from detected by Contrast-enhanced...