A5013637462- Medical Image Segmentation Techniques
- Machine Fault Diagnosis Techniques
- Optical Coherence Tomography Applications
- Retinal Imaging and Analysis
- Gear and Bearing Dynamics Analysis
- Radiomics and Machine Learning in Medical Imaging
- Fault Detection and Control Systems
- AI in cancer detection
- Structural Health Monitoring Techniques
- Engineering Diagnostics and Reliability
- Cerebrovascular and Carotid Artery Diseases
- Photoacoustic and Ultrasonic Imaging
- MRI in cancer diagnosis
- Advanced machining processes and optimization
- Automated Road and Building Extraction
- Esophageal Cancer Research and Treatment
- COVID-19 diagnosis using AI
- Satellite Image Processing and Photogrammetry
- Remote Sensing and LiDAR Applications
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Image and Signal Denoising Methods
- Endometrial and Cervical Cancer Treatments
- Lung Cancer Diagnosis and Treatment
- Alcoholism and Thiamine Deficiency
Guangzhou Medical University
2024
Guangzhou First People's Hospital
2024
South China University of Technology
2024
Suzhou Vocational University
2024
Suzhou Institute of Biomedical Engineering and Technology
2018-2023
Chinese Academy of Sciences
2018-2023
Soochow University
2018
University of Science and Technology of China
2015-2016
State Key Laboratory of Remote Sensing Science
2014
VA Sepulveda Ambulatory Care Center
1988
Automatic segmentation is important for esophageal OCT image processing, which able to provide tissue characteristics such as shape and thickness disease diagnosis. Existing automatical methods based on deep convolutional networks may not generate accurate results due limited training set various layer shapes. This study proposed a novel adversarial network (ACN) segment images using trained by learning. The framework includes generator discriminator, both with U-Net alike fully...
Endoscopic optical coherence tomography (OCT) imaging offers a non-invasive way to detect esophageal lesions on the microscopic scale, which is of clinical potential in early diagnosis and treatment cancers. Recent studies focused applying deep learning-based methods OCT image analysis achieved promising results, require large data size. However, traditional augmentation techniques generate samples that are highly correlated sometimes far from reality, may not lead satisfied trained model....
Abstract Purpose To compare a deep learning model with radiomics in differentiating high-grade (LR-3, LR-4, LR-5) liver imaging reporting and data system (LI-RADS) tumors from low-grade (LR-1, LR-2) LI-RADS based on the contrast-enhanced magnetic resonance images. Methods Magnetic scans of 361 suspected hepatocellular carcinoma patients were retrospectively reviewed. Lesion volume segmentation was manually performed by two radiologists, resulting 426 lesions training set 83 test set. The...
Automatic segmentation of esophageal layers in OCT images is crucial for studying diseases and computer-assisted diagnosis. This work aims to improve the current techniques increase accuracy robustness image segmentation. A two-step edge-enhanced graph search (EEGS) framework proposed this study. Firstly, a preprocessing scheme applied suppress speckle noise remove disturbance structure. Secondly, formulated into layer boundaries are located by search. In process, we propose an weight matrix...
Pneumonia, a major infectious cause of morbidity and mortality among children worldwide, is typically diagnosed using low-dose pediatric chest X-ray [CXR (chest radiography)]. In CXR images, bone occlusion leads to risk missed diagnosis. Deep learning-based bone-suppression networks relying on training data have enabled considerable progress be achieved in suppression adult images; however, these poor generalizability images because the lack labeled (i.e., vs. soft-tissue images)....
Endoscopic optical coherence tomography (OCT) devices are capable of generating high-resolution images esophageal structures at high speed. To make the obtained data easy to interpret and reveal clinical significance, an automatic segmentation algorithm is needed. This work proposes a fast combining sparse Bayesian learning graph search (termed as SBGS) automatically identify six layer boundaries on OCT images. The SBGS first extracts features, including multi-scale gradients, averages Gabor...
Automatic segmentation of layered tissue is the key to esophageal optical coherence tomography (OCT) image processing. With advent deep learning techniques, frameworks based on a fully convolutional network are proved be effective in classifying pixels images. However, due speckle noise and unfavorable imaging conditions, relevant diagnosis not always easy identify. An approach address this problem extracting more powerful feature maps, which have similar expressions for same show...
Automatic segmentation of layered tissue is critical for optical coherence tomography (OCT) image analysis. The development deep learning techniques provides various solutions to this problem, while most existing methods suffer from topological errors such as outlier prediction and label disconnection. channel attention mechanism a powerful technique address these problems due its simplicity robustness. However, it relies on global average pooling (GAP), which only calculates the lowest...
Automatic segmentation is the crucial step for esophageal optical coherence tomography (OCT) image processing, which able to highlight diagnosis-related tissue layers and provide characteristics such as shape thickness disease diagnosis. This study proposes a dual-stage framework using specifically designed encoder-decoder network configuration accurate reliable layer segmentation, named U-shape convolutional (D-UCN). The proposed approach utilized one UCN locate target region, followed by...
Abstract Automatic segmentation of layered tissue is the key to optical coherence tomography (OCT) image analysis for esophagus. While deep learning technology offers promising solutions this problem, requirement large numbers annotated samples often poses a significant obstacle, as it both expensive and challenging obtain. With in mind, we introduced self‐supervised framework esophageal OCT images. In particular, proposed method employs masked autoencoder (MAE) training constructs network...
Thickness of the esophagus is an important diagnostic marker for many diseases. While labeling boundaries by manual to compute each layer's average thickness time-consuming and subjective. In this paper, we present a new fully automatic algorithm which includes Fast Marching Method (FMM) Fourth-Order Runge-Kutta method (RK4) identify five layers on optical coherence tomography (OCT) images. FMM used calculate weighted geodesic distance. particular, velocity function involved in combines...
Cohen, M. B.; Lake, R. R.; Graham, L. S.; Fitten, J.; O'Rear, Kling, A. Metter, E. Yamada, Bronca, G. A.; Gan, P.; Greenwell, K. L.; Sevrin, Author Information