A5106526188- AI in cancer detection
- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Face and Expression Recognition
- Remote-Sensing Image Classification
- Advanced Chemical Sensor Technologies
- Advanced Neural Network Applications
- Brain Metastases and Treatment
- Remote Sensing and Land Use
- Security and Verification in Computing
- Machine Learning in Healthcare
- DNA and Biological Computing
- Speech and Audio Processing
- Emotion and Mood Recognition
- Advanced Memory and Neural Computing
- Digital and Cyber Forensics
- Music and Audio Processing
- Glioma Diagnosis and Treatment
- Advanced Malware Detection Techniques
- Advanced Radiotherapy Techniques
- Anomaly Detection Techniques and Applications
- Acoustic Wave Phenomena Research
- Medical Imaging and Analysis
- Dental Radiography and Imaging
North Minzu University
2024-2025
State Ethnic Affairs Commission
2024
Harvard University
2024
Shandong Tumor Hospital
2021-2023
Shandong First Medical University
2021-2023
Guangdong Polytechnic Normal University
2023
Shandong University
2023
Beijing Institute of Technology
2022
Jiangsu University
2010
Background In medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce need for human annotation and advance disease classification. Among established techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) has demonstrated efficacy in improving across various modalities, such as X-rays CT. However, there remains a demand improved contrast enhancement methods considering heterogeneity datasets contrasts...
General target detection with deep learning has made tremendous strides in the past few years. However, small sometimes is associated insufficient sample size and difficulty extracting complete feature information. For safety during autonomous driving, remote signs pedestrians need to be detected from driving scenes photographed by car cameras. In early period of a medical lesion, because area great significance detect masses tumors for accurate diagnosis treatment. To deal these problems,...
Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However, there are some problems that the features different sizes and directions not sufficient when extracting in lung X-ray images.A classification model multi-scale directional feature enhancement MSD-Net proposed this paper.The main innovations as follows: Firstly, Multi-scale Residual Feature Extraction Module (MRFEM) designed to effectively extract features.The MRFEM uses dilated convolutions with...
The objective of this study is to analyse the diffusion rule contrast media in multi-phase delayed enhanced magnetic resonance (MR) T1 images using radiomics and construct an automatic classification segmentation model brain metastases (BM) based on support vector machine (SVM) Dpn-UNet. A total 189 BM patients with 1047 were enrolled. Contrast-enhanced MR obtained at 1, 3, 5, 10, 18, 20 min following medium injection. tumour target volume was delineated, features extracted analysed. models...
Background Deep-learning-based semantic segmentation algorithms, in combination with image preprocessing techniques, can reduce the need for human annotation and advance disease classification. Among established CLAHE has demonstrated efficacy enhancing segmentations algorithms across various modalities. Method This study proposes a novel technique, ps-KDE, to investigate its impact on deep learning segment major organs posterior-anterior chest X-rays. Ps-KDE augments contrast by...
In recent years, subspace clustering has become increasingly popular and achieved great success in band selection (BS) of hyperspectral imagery. However, current approaches are mostly insufficient capturing the fine spatial structure spectral correlation image. Therefore, this article proposes a sample latent feature-associated low-rank model (SLFLRSC) tailored for BS. First, utilizes entropy rate segmentation to capture rich information Meanwhile, Laplacian eigenmaps is employed extract key...
Facial expressions can properly express inner emotions. The differences between also make feature extraction the most important part of expression recognition. Among all deep learning network models, residual put forward by Kaiming He et al. dose better in training. Therefore, on base network, this paper will replace convolution block Pyramid Convolution. At same time, attention module is introduced to redistribute weight parameters channel and spatial dimensions, normalization operation...
Eliminating the negative effects of background environmental noise is an interesting and challenging task in audio processing. In recent years, denoising technology based on neural networks (NN) has achieved good performance. particular, structure convolutional encoder decoder been proven to achieve enhancement effects. On this basis, paper proposes a residual unet combined with attention mechanism. Effectively reduce impact gradient disappearance network training, improve semantic gap...