A5025285538- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Radiotherapy Techniques
- Advanced X-ray and CT Imaging
- Sparse and Compressive Sensing Techniques
- Radiomics and Machine Learning in Medical Imaging
- Seismic Imaging and Inversion Techniques
- Medical Imaging and Analysis
- Spine and Intervertebral Disc Pathology
- Brain Tumor Detection and Classification
- Remote Sensing and LiDAR Applications
- Image and Signal Denoising Methods
- Spinal Fractures and Fixation Techniques
- Remote Sensing in Agriculture
- Photoacoustic and Ultrasonic Imaging
- Smart Agriculture and AI
- Neurological Disease Mechanisms and Treatments
University of Science and Technology of China
2023-2025
Anhui University
2019
Rice lodging severely affects harvest yield. Traditional evaluation methods and manual on-site measurement are found to be time-consuming, labor-intensive, cost-intensive. In this study, a new method for rice assessment based on deep learning UNet (U-shaped Network) architecture was proposed. The UAV (unmanned aerial vehicle) equipped with high-resolution digital camera three-band multispectral synchronously used collect lodged non-lodged images at an altitude of 100 m. After splicing...
During interventional procedures, clinicians require immediate imaging feedback. The requirement can be fulfilled by the online reconstruction of dynamic magnetic resonance (dMRI), where current frame is reconstructed using only previous data. Unfortunately, existing algorithms fall short in terms quality and time delay, failing to meet demands modern treatments. Addressing this issue, we introduce a more effective efficient algorithm. To expedite process, our approach employs concept...
The co-registration between an optical tracker and Magnetic Resonance Imaging (MRI) space is indispensable step for MRI-guided surgery. In this study, with a focus on RGB cameras as the tracker, we introduce innovative scheme tracker-to-MRI integration. Firstly, design cube-shaped registration model that equipped ArUco marker its exterior camera detection houses four water blobs inside MRI calibration. Secondly, employ line scan pulse sequence localization reconstruction of blobs. Lastly,...
Magnetic Resonance Imaging (MRI) is a crucial medical imaging technique, but MR images are often corrupted by noise. To address this issue, the higher-order singular value decomposition (HOSVD) denoising method one of mainstream approaches to remove noise in images. Notably, Iterative Low-Rank HOSVD (ILR-HOSVD) algorithm has demonstrated its supremacy terms peak signal-to-noise ratio (PSNR). However, ILR-HOSVD overlooks potential impact orthogonal bases under high conditions. Moreover,...
Intensity inhomogeneity remains a pivotal challenge that hampers the diagnostic efficacy of Magnetic Resonance Imaging (MRI). Traditional reference scan methods, while effective in correcting intensity inhomogeneity, often inadvertently introduce noise into images, thus degrading Signal-to-Noise Ratio (SNR). In this study, we an innovative modified methodology. Initially, posit sensitivity map utilized for correction exhibits spatial consistency within Region Interest (ROI). Subsequently,...
Brain atrophy is one of the most common features neurodegenerative diseases and particularly critical in early diagnosis conditions like Alzheimer's multiple sclerosis. Automated segmentation quantification are highly desirable brain evaluation but existing methods require high-quality MRI scans with isotropic resolution. However practice, clinicians usually choose to reduce number slices save time, because their anisotropic resolution, morphometric analysis cannot be implemented. Here we...
Introduction Fine-tuning (FT) is a generally adopted transfer learning method for deep learning-based magnetic resonance imaging (MRI) reconstruction. In this approach, the reconstruction model initialized with pre-trained weights derived from source domain ample data and subsequently updated limited target domain. However, direct full-weight update strategy can pose risk of "catastrophic forgetting" overfitting, hindering its effectiveness. The goal study to develop zero-weight preserve...
Deep learning (DL)-based methods substantially enhance the speed of magnetic resonance imaging (MRI). Recently, transformer network architectures have been increasingly applied to image reconstruction owing their exceptional ability model long-range dependencies. However, directly employing a for MRI results in considerable computational burden because complexity is proportional square spatial resolution. To alleviate this limitation, study aims design computationally efficient with improved...
Channel attention mechanisms have been proven to effectively enhance network performance in various visual tasks, including the Magnetic Resonance Imaging (MRI) reconstruction task. typically involve channel dimensionality reduction and cross-channel interaction operations achieve complexity generate more effective weights of channels. However, may negatively impact MRI since it was found that there is no discernible correlation between adjacent channels low information value some feature...