A5043323603- Fetal and Pediatric Neurological Disorders
- Neonatal and fetal brain pathology
- Machine Learning in Bioinformatics
- Domain Adaptation and Few-Shot Learning
- Protein Structure and Dynamics
- RNA and protein synthesis mechanisms
- Advanced Neuroimaging Techniques and Applications
- Dental Radiography and Imaging
- Autopsy Techniques and Outcomes
- Enzyme Structure and Function
- Cleft Lip and Palate Research
- Effects and risks of endocrine disrupting chemicals
- Anesthesia and Neurotoxicity Research
- Radiomics and Machine Learning in Medical Imaging
- Glioma Diagnosis and Treatment
- Health, Environment, Cognitive Aging
- MRI in cancer diagnosis
- Thyroid and Parathyroid Surgery
- Head and Neck Cancer Studies
- Thyroid Cancer Diagnosis and Treatment
University of North Carolina at Chapel Hill
2023-2024
Hunan University
2020-2023
Zhejiang University of Technology
2018-2019
Ab initio protein tertiary structure prediction is one of the long-standing problems in structural bioinformatics. With help residue-residue contact and secondary information, accuracy ab can be enhanced. In this study, an improved differential evolution with information referred to as SCDE proposed for prediction. SCDE, two score models based on are proposed, selection strategies, namely, structure-based strategy contact-based strategy, designed guide conformation space search. A...
Recognition of thyroid glands and tissues the neck is vital for screening related diseases in ultrasound videos. This task subjective, challenging, dependent on experience sonographer current clinical practice. The purpose to develop a fully automated gland recognition framework assist doctors distinguishing boundaries different tissues. In this paper, we propose novel deep learning that consists feature extraction network, region proposal object detection head, spatial pyramid...
The prevalence of thyroid diseases has been increasing year by year. In this study, we established and validated a deep learning method (Cascade region-based convolutional neural network, R-CNN) based on ultrasound videos for automatic detection segmentation the gland its surrounding tissues in order to reduce workload radiologists improve diagnosis rate disease.Seventy-one patients with normal were included. 59 used as training dataset, data 12 validation addition, 9 patents testing...
Fetal Magnetic Resonance Imaging (MRI) is challenged by fetal movements and maternal breathing. Although fast MRI sequences allow artifact free acquisition of individual 2D slices, motion frequently occurs in the spatially adjacent slices. Motion correction for each slice thus critical reconstruction 3D brain MRI. In this paper, we propose a novel multi-task learning framework that adopts coarse-to-fine strategy to jointly learn pose estimation parameters tissue segmentation map...
Robust motion correction of fetal brain MRI slices is crucial for 3D volume reconstruction. However, conventional methods can only handle a limited range motion. Hence, deep learning model based on geometric constraints proposed in order to predict the arbitrary standard anatomical space, which consists global estimation network and relative network. In particular, used estimate between two adjacent slices, exploited as constraint. Then, sharing features networks make learn more unique...
De novo protein structure prediction can be treated as a conformational space optimization problem under the guidance of an energy function. However, it is challenge how to design accurate function which ensures low-energy conformations close native structures. Fortunately, recent studies have shown that accuracy de significantly improved by integrating residue-residue distance information. In this paper, two-stage feature-based algorithm (TDFO) for proposed within framework evolutionary...
Robust motion correction of fetal brain MRI slices is crucial for volume reconstruction. However, conventional methods can only handle a limited range motion. Hence, deep learning model based on prior geometric constraints proposed to predict the 2D slices. It consists global and relative estimation network. Sharing features between two networks make learn more unique feature representations correction. Moreover, we present control point-based approach simulate complex trajectories. The...
Motivation: The fetal brain MRI 3D volume is critical for development assessment. However, the inevitable motion during acquisition makes it challenging to reconstruct a high-quality from multiple stacks. Goal(s): Herein, we propose novel deep learning method automated reconstruction. Approach: Firstly, multi-scale feature fusion model proposed solve arbitrary correction. Secondly, an initial estimated by point spread function. Next, residual-based used improve quality of volume. Results:...
Protein structure prediction has been a long-standing problem for the past decades. In particular, loop region remains an obstacle in forming accurate protein tertiary because of its flexibility. this study, Rama torsion angle and secondary feature-guided differential evolution named RSDE is proposed to predict three-dimensional with exploitation on structure. RSDE, improved by following: loop-based cross operator, which interchanges configuration randomly selected between individuals,...