A5057573049- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Medical Image Segmentation Techniques
- EEG and Brain-Computer Interfaces
- Advanced Neural Network Applications
- Face and Expression Recognition
- Blind Source Separation Techniques
- Machine Learning and ELM
- Advanced Computing and Algorithms
- Image and Signal Denoising Methods
- Image Enhancement Techniques
- COVID-19 diagnosis using AI
- Advanced X-ray and CT Imaging
- AI in cancer detection
- Advanced Image Fusion Techniques
- Advanced Clustering Algorithms Research
- Medical Imaging Techniques and Applications
- Neural Networks and Applications
- Video Surveillance and Tracking Methods
- RNA modifications and cancer
- Image Retrieval and Classification Techniques
- Advanced Algorithms and Applications
- IoT and Edge/Fog Computing
- Cancer-related molecular mechanisms research
- Colorectal Cancer Surgical Treatments
Soochow University
2017-2025
Changshu No.1 People's Hospital
2014-2024
University of Malaya
2022-2024
Beijing Academy of Artificial Intelligence
2024
Changshu Institute of Technology
2009-2022
China University of Mining and Technology
2018-2021
Xuzhou Medical College
2020
Jiangnan University
2019
Florida Atlantic University
2019
Due to the space inconsistency between benchmark image and segmentation result in many existing semantic algorithms for abdominal CT images, an improved model based on basic framework of DeepLab-v3 is proposed, Pix2pix network introduced as generation adversarial model. Our proposed realizes combining deep feature with multi-scale feature. In order improve generalization ability training accuracy model, this paper proposes a combination traditional multi-classification cross-entropy loss...
The prediction for Multivariate Time Series (MTS) explores the interrelationships among variables at historical moments, extracts their relevant characteristics, and is widely used in finance, weather, complex industries other fields. Furthermore, it important to construct a digital twin system. However, existing methods do not take full advantage of potential properties variables, which results poor predicted accuracy. In this paper, we propose Adaptive Fused Spatial-Temporal Graph...
With the development of sensors, more and multimodal data are accumulated, especially in biomedical bioinformatics fields. Therefore, analysis becomes very important urgent. In this study, we combine multi-kernel learning transfer learning, propose a feature-level multi-modality fusion model with insufficient training samples. To be specific, firstly extend kernel Ridge regression to its version under lp-norm constraint explore complementary patterns contained data. Then use marginal...
Alzheimer's disease (AD) is an illness that involves a gradual and irreversible degeneration of the brain. It crucial to establish precise diagnosis AD early on in order enable prompt therapies prevent further deterioration. Researchers are currently focusing increasing attention investigating potential machine learning techniques simplify automated using neuroimaging. The present study involved comparison models for detection through utilization 2D image slices obtained from magnetic...
Background Maintaining machines effectively continues to be a challenge for industrial organisations, which frequently employ reactive or premeditated methods. Recent research has begun shift its attention towards the application of Predictive Maintenance (PdM) and Digital Twins (DT) principles in order improve maintenance processes. PdM technologies have capacity significantly profitability, safety, sustainability various industries. Significantly, precise equipment estimation, enabled by...
The clustering algorithm play s a very important role in the applications of medical analysis, it can effective analysis log disease. It accurately analyze characteristics various diseases, thus providing accurate basis for doctor's diagnosis. In this paper, we will cluster algorithm--Fuzzy C-Means Algorithm (FCM). traditional FCM is liable to trap into problem local optimum. We propose an improved based on smooth technology. consider sample points different positions have effects and number...
Vigilance or sustained attention is an important aspect for people who engaged in long time demanding tasks such as monotonous monitoring and driving. detection has been topic the field of brain-computer interface (BCI) research. However, study limited due to low SNR (Signal-Noise Ratio) nature EEG. Common spatial pattern (CSP) a one most effective algorithms feature extraction method BCI area. The CSP seeks optimal projection direction (spatial filter) by maximizing variance class...
Cerebral microbleed (CMB) is a serious public health concern. It associated with dementia, which can be detected brain magnetic resonance image (MRI). CMBs often appear as tiny round dots on MRIs, and they spotted anywhere over brain. Therefore, manual inspection tedious lengthy, the results are short in reproducible. In this paper, novel automatic CMB diagnosis method was proposed based deep learning optimization algorithms, used MRI input output non-CMB. Firstly, sliding window processing...
Background and objective Accurately predicting the extent of lung tumor infiltration is crucial for improving patient survival cure rates. This study aims to evaluate application value an improved CT index combined with serum biomarkers, obtained through artificial intelligence recognition system analyzing features pulmonary nodules, in early prediction cancer using machine learning models. Patients methods A retrospective analysis was conducted on clinical data 803 patients hospitalized...
Spontaneous intracerebral hemorrhage (SICH) is the second most common cause of cerebrovascular disease after ischemic stroke, with high mortality and disability rates, imposing a significant economic burden on families society. This retrospective study aimed to develop evaluate an interpretable machine learning model predict functional outcomes 3 months SICH. A analysis was conducted clinical data from 380 patients SICH who were hospitalized at three different centers between June 2020 2023....
Magnetic resonance (MR) images have distinctive advantages in radiation treatment (RT) planning due to their superior, anatomic and functional information compared with computed tomography (CT). For the RT dose calculation, MR cannot be directly used because of lack electron density information. To address this issue, we propose generate pseudo-CT (pCT) terms multiple matching Dixon support MR-only RT, particularly challenging body section abdomen. end, design dedicated multichannel residual...