A5043052005- Advanced Radiotherapy Techniques
- Radiation Therapy and Dosimetry
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Radiation Detection and Scintillator Technologies
- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Diagnosis and Treatment
- Nuclear Physics and Applications
- Radiation Dose and Imaging
- Medical Imaging and Analysis
- Advanced MRI Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- Dermatologic Treatments and Research
- Advanced Neural Network Applications
- Head and Neck Cancer Studies
- Ultrasound and Hyperthermia Applications
- Digital Radiography and Breast Imaging
- Management of metastatic bone disease
- Breast Cancer Treatment Studies
- Ultrasound Imaging and Elastography
- Medical Image Segmentation Techniques
- Photodynamic Therapy Research Studies
- Photoacoustic and Ultrasonic Imaging
- Prostate Cancer Treatment and Research
Emory University
2019-2025
Zhejiang Sci-Tech University
2025
Nanjing Medical University
2022-2024
Second Affiliated Hospital of Chongqing Medical University
2022-2024
Winship Cancer Institute
2024
Second Affiliated Hospital of Xi'an Jiaotong University
2017-2024
Cancer Institute (WIA)
2024
Oil and Gas Center
2023
Foshan University
2023
Changzhi Medical College
2023
Purpose The incorporation of cone‐beam computed tomography (CBCT) has allowed for enhanced image‐guided radiation therapy. While CBCT allows daily 3D imaging, images suffer from severe artifacts, limiting the clinical potential CBCT. In this work, a deep learning‐based method generating high quality corrected (CCBCT) is proposed. Methods proposed integrates residual block concept into cycle‐consistent adversarial network (cycle‐GAN) framework, called res‐cycle GAN, to learn mapping between...
Magnetic resonance imaging (MRI) has been widely used in combination with computed tomography (CT) radiation therapy because MRI improves the accuracy and reliability of target delineation due to its superior soft tissue contrast over CT.The MRI-only treatment process is currently an active field research since it could eliminate systematic MR-CT co-registration errors, reduce medical cost, avoid diagnostic exposure, simplify clinical workflow.The purpose this work validate application a...
In breast tomosynthesis there is a compromise between resolution, noise, and acquisition speed for given glandular dose. The purpose of the present work to develop simulation platform investigate potential imaging performance many possible system configurations. was used dependence image blur signal difference noise ratio (SDNR) several different Simulated projections slanted thin tungsten wire placed in object planes were modified according detector's modulation transfer function (MTF),...
The purpose of this work is to validate the application a deep learning-based method for pelvic synthetic CT (sCT) generation that can be used prostate proton beam therapy treatment planning. We propose integrate dense block minimization into 3D cycle-consistent generative adversarial networks (cycleGAN) framework effectively learn nonlinear mapping between MRI and pairs. A cohort 17 patients with co-registered MR pairs were test sCT by leave-one-out cross-validation. Image quality images,...
To evaluate spot-scanning proton arc therapy (SPArc) and multi-field robust optimized intensity modulated (RO-IMPT) in treating stage III non-small-cell lung cancer (NSCLC) patients.Two groups of IIIA or IIIB NSCLC patients (group 1: eight with tumor motion less than 5 mm; group 2: six equal to more mm) were re-planned SPArc RO-IMPT. Both plans generated using optimization achieve an optimal coverage 99% internal target volume (ITV) receiving 66 Gy (RBE) 33 fractions. The dosimetric results...
Abstract Proton therapy requires accurate dose calculation for treatment planning to ensure the conformal doses are precisely delivered targets. The conversion of CT numbers material properties is a significant source uncertainty calculation. aim this study develop physics-informed deep learning (PIDL) framework derive mass density and relative stopping power maps from dual-energy computed tomography (DECT) images. PIDL allows (DL) models be trained with physics loss function, which includes...
Abstract The advantage of proton therapy as compared to photon stems from the Bragg peak effect, which allows protons deposit most their energy directly at tumor while sparing healthy tissue. However, even with such benefits, does present certain challenges. biological effectiveness differences between and photons are not fully incorporated into clinical treatment planning processes. In current practice, relative (RBE) is set constant 1.1. Numerous studies have suggested that RBE can exhibit...
A three‐dimensional (3D) linear model for digital breast tomosynthesis (DBT) was developed to investigate the effects of different imaging system parameters on reconstructed image quality. In present work, experimental validation performed a prototype DBT equipped with an amorphous selenium (a‐Se) mammography detector and filtered backprojection (FBP) reconstruction methods. The can be operated in either full resolution pixel size or binning mode reduce acquisition time. Twenty‐five...
SummaryThis feasibility study shows that Spot-scanning Proton Arc therapy (SPArc) is able to significantly reduce the dose hippocampus and cochlea compared both Volumetric Modulated Photon Therapy (VMAT) robust optimized Intensity (ro-IMPT) plans in whole brain radiotherapy. Furthermore, SPArc not only improves plan robustness but could potentially deliver a treatment as efficient ro-IMPT when proton system's energy layer switch time less than 1 s.
Purpose Stereotactic radiosurgery (SRS) is widely used to obliterate arteriovenous malformations (AVMs). Its performance relies on the accuracy of delineating target AVM. Manual segmentation during a framed SRS procedure time consuming and subject inter‐ intraobserver variation. To address these drawbacks, we proposed deep learning‐based method automatically segment AVMs CT simulation image sets. Methods We developed using deeply supervised three‐dimensional (3D) V‐Net with compound loss...
Because the manual contouring process is labor-intensive and time-consuming, segmentation of organs-at-risk (OARs) a weak link in radiotherapy treatment planning process. Our goal was to develop synthetic MR (sMR)-aided dual pyramid network (DPN) for rapid accurate head neck multi-organ order expedite process.Forty-five patients' CT, MR, contours pairs were included as our training dataset. Nineteen OARs target organs be segmented. The proposed sMR-aided DPN method featured deep attention...
Organ-at-risk (OAR) delineation is a key step for cone-beam CT (CBCT) based adaptive radiotherapy planning that can be time-consuming, labor-intensive, and subject-to-variability process. We aim to develop fully automated approach aided by synthetic MRI rapid accurate CBCT multi-organ contouring in head-and-neck (HN) cancer patients. has superb soft-tissue contrasts, while offers bony-structure contrasts. Using the complementary information provided expected enable segmentation HN In our...
Abstract Magnetic Resonance Imaging (MRI) is increasingly being used in treatment planning due to its superior soft tissue contrast, which useful for tumor and delineation compared computed tomography (CT). However, MRI cannot directly provide mass density or relative stopping power (RSP) maps, are required calculating proton radiotherapy doses. Therefore, the integration of artificial intelligence (AI) into MRI-based estimate RSP from has generated significant interest. A deep learning (DL)...
Abstract Objective: This study aims to develop a digital twin (DT) framework achieve adaptive proton prostate stereotactic body radiation therapy (SBRT) with fast treatment plan selection and patient-specific clinical target volume (CTV) setup uncertainty. Prostate SBRT has emerged as leading option for external beam radiotherapy due its effectiveness reduced duration. However, interfractional anatomy variations can impact outcomes. seeks address these uncertainties using DT concept improve...
Abstract Purpose Deep learning‐based segmentation of organs‐at‐risk (OAR) is emerging to become mainstream in clinical practice because the superior performance over atlas and model‐based autocontouring methods. While several commercial deep autosegmentation solutions are now available, implementation these tools still at such a primitive stage that acceptance criteria underdeveloped due lack knowledge about systems’ tendencies failure modes. As starting point iterative process...
Time series anomaly detection is a significant challenge due to the inherent complexity and diversity of time data. Traditional methods for (TAD) often struggle effectively address intricate nature complex composite characteristics diverse anomalies. In this paper, we propose SCConv-Denoising Diffusion Probabilistic Model Anomaly Detection Based on TimesNet (SDADT), novel framework that integrates Spatial Channel Reconstruction Convolution (SCConv) module Denoising Models (DDPMs) these...
Purpose: In order to increase the accuracy and speed of catheter reconstruction in a high-dose-rate (HDR) prostate implant procedure, an automatic tracking system has been developed using electromagnetic (EM) device (trakSTAR, Ascension Technology, VT). The performance system, including noise level with various parameters conditions, were investigated. Methods: A direct current (dc) EM transmitter (midrange model) sensor diameter 1.3 mm (Model 130) used trakSTAR for position during HDR...
To introduce a novel, deep-learning method to generate synthetic computed tomography (SCT) scans for proton treatment planning and evaluate its efficacy.50 Patients with base of skull tumors were divided into 2 nonoverlapping training study cohorts. Computed magnetic resonance imaging pairs patients in the cohort used our novel 3-dimensional generative adversarial network (cycleGAN) algorithm. Upon completion phase, SCT predicted based on their images only. The obtained compared against...