A5028311940- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Digital Imaging for Blood Diseases
- Advanced Neural Network Applications
- Medical Image Segmentation Techniques
- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Retinal Imaging and Analysis
- Advanced Image Processing Techniques
- Brain Tumor Detection and Classification
- Image Processing Techniques and Applications
- Cancer Immunotherapy and Biomarkers
- Domain Adaptation and Few-Shot Learning
- Medical Imaging and Analysis
- Cell Image Analysis Techniques
- Retinal and Optic Conditions
- Remote-Sensing Image Classification
- Video Surveillance and Tracking Methods
- COVID-19 diagnosis using AI
- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Lung Cancer Diagnosis and Treatment
- Cerebrovascular and Carotid Artery Diseases
- Human Pose and Action Recognition
- Gene expression and cancer classification
Guilin University of Electronic Technology
2013-2025
Guangdong Academy of Medical Sciences
2020-2024
Guangdong Provincial People's Hospital
2020-2024
Southern Medical University
2023-2024
Key Laboratory of Guangdong Province
2022-2023
Guilin University
2013-2023
Dalian Maritime University
2023
Beijing University of Posts and Telecommunications
2016-2021
Underwater images typically suffer from various quality degradation issues due to the scattering and absorption of light, but these degraded-quality underwater are unbeneficial for analysis applications. To effectively solve issues, an image enhancement method via weighted wavelet visual perception fusion is introduced, called WWPF. Concretely, we first present attenuation-map-guided color correction strategy correct distortion image. Subsequently, employ maximum information entropy...
Vessel segmentation is critical for disease diagnosis and surgical planning. Recently, the vessel method based on deep learning has achieved outstanding performance. However, remains challenging due to thin vessels with low contrast that easily lose spatial information in traditional U-shaped network. To alleviate this problem, we propose a novel straightforward full-resolution network (FR-UNet) expands horizontally vertically through multiresolution convolution interactive mechanism while...
Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain diagnosis, cancer management and research purposes. With the great success of ten-year BraTS challenges as well advances CNN Transformer algorithms, a lot outstanding BTS models have been proposed to tackle difficulties different technical aspects. However, existing studies hardly consider how fuse multi-modality images reasonable manner. In this paper, we leverage clinical knowledge radiologists diagnose...
Ultrasonography is an important routine examination for breast cancer diagnosis, due to its non-invasive, radiation-free and low-cost properties. However, the diagnostic accuracy of still limited inherent limitations. Then, a precise diagnose using ultrasound (BUS) image would be significant useful. Many learning-based computer-aided methods have been proposed achieve diagnosis/lesion classification. most them require pre-define region interest (ROI) then classify lesion inside ROI....
In order to solve the problem of image degradation in foggy weather, a single defogging method based on multi-scale retinex with color restoration (MSRCR) multi-channel convolution (MC) is proposed. The whole process mainly consists four key parts: estimation illumination components, guided filter operation, reconstruction fog-free images, and white balance operation. First, Gaussian kernels are employed extract precise features estimate component. After that, MSRCR applied enhance global...
Underwater images suffer from color cast and low visibility caused by the medium scattering absorption, which will reduce use of valuable information image. In this paper, we propose a novel method includes four stages pixel intensity center regionalization, global equalization histogram, local histogram multi-scale fusion. Additionally, uses regionalization strategy to perform centralization image on overall Global is employed correct according characteristics each channel. Local...
Images captured underwater usually suffer from color distortion, detail blurring, low contrast, and a bluish or greenish tone due to light scattering absorption in the medium, which turn visibility is adversely affected by these factors seriously. Over last decades, various image restoration enhancement methods have been developed many researchers improve quality (visibility highlight richer details) of images. This paper introduces overview state-of-the-art techniques classifies approaches...
Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the giga-pixel whole slide images extremely expensive and time-consuming. In this paper, we use only patch-level classification to achieve tissue histopathology images, finally reducing annotation efforts. We propose two-step model including phases. phase, CAM-based generate...
Traditional digital image processing methods extract disease features manually, which have low efficiency and recognition accuracy. To solve this problem, In paper, we propose a convolutional neural network architecture FL-EfficientNet (Focal loss EfficientNet), is used for multi-category identification of plant images. Firstly, through the Neural Architecture Search technology, width, depth, resolution are adaptively adjusted according to group composite coefficients, improve balance...
Background Current prognostic and predictive biomarkers for lung adenocarcinoma (LUAD) predominantly rely on unimodal approaches, limiting their characterization ability. There is an urgent need a comprehensive accurate biomarker to guide individualized adjuvant therapy decisions. Methods In this retrospective study, data from patients with resectable LUAD (stage I–III) were collected two hospitals publicly available dataset, forming training dataset (n=223), validation (n=95), testing...
Histopathological tissue classification is a simpler way to achieve semantic segmentation for the whole slide images, which can alleviate requirement of pixel-level dense annotations. Existing works mostly leverage popular CNN backbones in computer vision histopathological classification. In this paper, we propose super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), any well-trained backbone improve performance without re-training burden. For each patch,...