A5072774321- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Lung Cancer Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- Radiation Therapy and Dosimetry
- Radiation Dose and Imaging
- Prostate Cancer Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- MicroRNA in disease regulation
- Ga2O3 and related materials
- Cancer-related molecular mechanisms research
- Statistical Methods in Clinical Trials
- Radiation Detection and Scintillator Technologies
- Brain Metastases and Treatment
- Radiation Effects in Electronics
- Anomaly Detection Techniques and Applications
- Evaluation and Optimization Models
- Artificial Intelligence in Healthcare and Education
- Gas Sensing Nanomaterials and Sensors
- Head and Neck Cancer Studies
- Nuclear Physics and Applications
- Circular RNAs in diseases
- ZnO doping and properties
Emory University
2021-2025
Inner Mongolia University
2024
Icahn School of Medicine at Mount Sinai
2024
Hubei University of Technology
2022-2023
Nanjing University
1999-2023
Collaborative Innovation Center of Advanced Microstructures
2023
Duke Medical Center
2018-2022
Newcastle University
2022
Northeast Normal University
2022
Emory Healthcare
2022
The purpose of this work was to develop a deep learning (DL) based algorithm, Automatic intensity-modulated radiotherapy (IMRT) Planning via Static Field Fluence Prediction (AIP-SFFP), for automated prostate IMRT planning with real-time efficiency. following method adopted: AIP-SFFP generates plan through predictions fluence maps using patient anatomy. No inverse is required. centered on custom-built neural network map prediction. Predictions are imported commercial treatment-planning system...
Evidences have shown that the RAS signalling pathway plays an important role in colorectal cancer (CRC). Moreover, RAS-GTPase-activating proteins (RASGAPs) as terminators are associated with tumourigenicity and tumour progression. In this study, we used bioinformatics analysis to predict study miRNAs could target p21 GTPase-activating protein 1 (RASA1), member of RASGAPs.The levels RASA1 miR-223 were analysed by real-time PCR, western blotting or situ immunofluorescence analyses. The...
Purpose: Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a difficult and time-consuming task. In this study, we aim to develop novel deep learning framework generate clinical-quality plans by direct prediction of fluence maps from patient anatomy using convolutional neural networks (CNNs). Materials Methods: Our proposed utilizes two CNNs predict intensity modulated deliverable plans: 1) Field dose CNN predicts field distributions in the region-of-interest...
This study aims to develop a novel Cycle-guided Denoising Diffusion Probability Model (CG-DDPM) for cross-modality MRI synthesis. The CG-DDPM deploys two DDPMs that condition each other generate synthetic images from different pulse sequences. exchange random latent noise in the reverse processes, which helps regularize both and matching modalities. improves image-to-image translation ac-curacy. We evaluated quantitatively using mean absolute error (MAE), multi-scale structural similarity...
Purpose: To develop an Artificial Intelligence (AI) agent for fully-automated rapid head and neck (H&N) IMRT plan generation without time-consuming inverse planning.$$$$ Methods: This AI was trained using a conditional Generative Adversarial Network architecture. The generator, PyraNet, is novel Deep Learning network that implements 28 classic ResNet blocks in pyramid-like concatenations. discriminator customized 4-layer DenseNet. first generates 2D projections at 9 template beam angles from...
Abstract G-quadruplex (G4) DNA and G4 resolvase are involved in a variety of biological processes. To understand the function structures their resolvases spermatogenesis, we investigated distribution mouse testis identified alterations during spermatogenesis. Meanwhile, studied RNA helicase associated with AU-rich element (RHAU), resolvase, spermatogenesis germ-cell-specific knockout model. The results showed that ablation RHAU germ cells caused increase thus resulted decrease spermatogonial...
Knowledge-based planning (KBP) utilizes experienced planners' knowledge embedded in prior plans to estimate optimal achievable dose volume histogram (DVH) of new cases. In the regression-based KBP framework, previously planned patients' anatomical features and DVHs are extracted, is summarized as regression coefficients that transform organ-at-risk DVH predictions. our study, we find different settings, methods work better. To improve robustness models, propose an ensemble method combines...
Purpose: To develop a deep learning-based AI agent, DDD-PIOP (Dose-Distribution-Driven PET Image Outcome Prediction), for predicting 18FDG-PET image outcomes of oropharyngeal cancer in response to intensity-modulated radiation therapy (IMRT). Methods: uses pre-radiotherapy 18FDG-PET/CT images and the planned spatial dose distribution as input, it predicts IMRT delivery. This agent centralizes customized convolutional neural network (CNN) learning approach, incorporates few designs enhance...
In this work, a solar-blind UV metal-semiconductor Schottky photodiode array is constructed by using metalorganic chemical vapor deposition grown ε-Ga2O3 thin film, possessing high-performance and self-powered characteristics, toward dual-mode (self-powered biased modes) binary light communication. For the unit, responsivity, specific detectivity, external quantum efficiency are 30.8 A/W/6.3 × 10-2 A/W, 1.51 104%/30.9%, 1.28 1014/5.4 1012 Jones for (-10 V)/self-powered operation. The rise...
As a simple and convenient technology to fabricate micron-to-nanoscale fibers with controllable structure, electrostatic spinning has produced fiber films many natural advantages, including large specific surface area high porosity. Maize zein, as major storage protein in corn, showed hydrophobicity been successfully applied promising carrier for encapsulation controlled release the pharmaceutical food areas. Proteins exhibit different physical chemical properties at pH values, it is worth...
Abstract In mammals, spermatogonial stem cells (SSCs) arise from early germ called gonocytes, which are derived primordial during embryogenesis and remain quiescent until birth. After birth, these migrate the center of testicular cord, through Sertoli cells, toward basement membrane to form SSC pool establish niche architecture. However, molecular mechanisms underlying cell migration establishment largely unknown. Here, we show that actin disassembly factor interacting protein 1 (AIP1) is...
Objective.Current segmentation practice for thoracic cancer RT considers the whole heart as a single organ despite increased risks of cardiac toxicities from irradiation specific substructures. Segmenting up to 15 different substructures can be very time-intensive process, especially due their volume sizes and anatomical variations amongst patients. In this work, new deep learning (DL)-based mutual enhancing strategy is introduced accurate automatic segmentation, smaller such coronary...
Abstract Purpose To investigate bolus design and VMAT optimization settings for total scalp irradiation. Methods Three silicone designs (flat, hat, custom) from .decimal were evaluated adherence to five anthropomorphic head phantoms. Flat was cut a sheet. Generic hat resembles an elongated swim cap while custom is manufactured by injecting into 3D printed mold. Bolus placement time recorded. Air gaps between quantified on CT images. The dosimetric effect of air target coverage in treatment...
The purpose of this study is to develop an accurate and reliable dose volume histogram (DVH) prediction method for external beam radiation therapy plans with multiple planning target volumes (PTVs).We present a novel DVH workflow, including new features modeling methodology, that makes better use PTVs: (a) We propose generalized feature characterize the geometric relationship organ-at-risk (OARs) respect two or more PTVs different prescribed levels; (b) incorporate data augmentation improve...
Treatment planning for pancreatic cancer stereotactic body radiation therapy (SBRT) is very challenging owing to vast spatial variations and close proximity of many organs-at-risk. Recently, deep learning (DL) based methods have been applied in dose prediction tasks various treatment sites with the aim relieving challenges. However, its effectiveness on SBRT yet be fully explored due limited investigations literature. This study aims further current knowledge DL-based by implementing...