A5062593013- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- Radiation Therapy and Dosimetry
- Medical Imaging Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Advanced Fluorescence Microscopy Techniques
- Prostate Cancer Diagnosis and Treatment
- Near-Field Optical Microscopy
- Advances in Oncology and Radiotherapy
- Advanced Electron Microscopy Techniques and Applications
- Radiation Dose and Imaging
- AI in cancer detection
- Ion-surface interactions and analysis
- Digital Holography and Microscopy
- Radiation Detection and Scintillator Technologies
- Brain Tumor Detection and Classification
- X-ray Spectroscopy and Fluorescence Analysis
- Topic Modeling
- Advanced Data Processing Techniques
- Web Data Mining and Analysis
- Text and Document Classification Technologies
Duke Medical Center
2019-2025
Duke University
2019-2025
Sichuan University
2024
Duke University Hospital
2021
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...
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...
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 This article investigates the performance of a commercial BeO optically stimulated luminescent (OSL) dosimetry system (myOSLchip, RadPro GmbH International, Remscheid, Germany) through application commissioning framework for dosimeters as described in American Association Physicists Medicine Task Group 191 (AAPM TG191) report. Initial clinical experiences and dosimetric results are also presented. The following properties were characterized: linearity correction factors ranged from...
Abstract Objective
Head-and-neck (HN) simultaneous integrated boost (SIB) treatment planning using intensity modulated radiation therapy (IMRT) is particularly challenging due to the proximity organs-at-risk (OARs). Depending on specific clinical conditions, different parotid-sparing strategies are utilized preserve parotid function without compromising local tumor control. Clinically this typically done with attending’s directive or via trial-and-error comparison sparing tradeoffs....
Head and neck (HN) cancers pose a difficult problem in the planning of intensity-modulated radiation therapy (IMRT) treatment. The primary tumor can be large asymmetrical, multiple organs at risk (OARs) with varying dose-sparing goals lie close to target volume. Currently, there is no systematic way automating generation IMRT plans, manual options face quality long time challenges. In this article, we present reinforcement learning (RL) model for purposes providing automated treatment reduce...
Abstract Purpose:
To develop a deep reinforcement learning (DRL) agent to self-interact with the treatment planning system (TPS) automatically generate intensity modulated radiation therapy (IMRT) plans for head-and-neck (HN) cancer consistent organ-at-risk (OAR) sparing performance.
Methods:
With IRB approval, one hundred and twenty HN patients receiving IMRT were included. The DRL was trained 20 patients. During each inverse optimization process, intermediate...
Quantum entanglement serves as an essential resource across various fields, including quantum communication, computing, and precision measurement. microscope, one of the significant applications in measurement, could bring revolutionary advancements both signal-to-noise ratio (SNR) spatial resolution imaging. Here, we present a microscopy system that relies on fully fiber-integrated high-performance energy-time entangled light source operating within near-infrared II (NIR-II) window....
Artificial intelligence (AI) based treatment planning tools are being implemented in clinic. However, human interactions with such AI rarely analyzed. This study aims to comprehend planner's interaction the tool and incorporate analysis improve existing tool.
To describe the clinical commissioning of an in-house artificial intelligence (AI) treatment planning platform for head-and-neck (HN) Intensity Modulated Radiation Therapy (IMRT).
Purpose: To optimize collimator setting to improve dosimetric quality of pancreas volumetric modulated arc therapy plan for stereotactic body radiation therapy. Materials and Methods: Fifty-five cases in were retrospectively included this study with internal review board approval. Different from the routine practice initializing settings a template, proposed algorithm simultaneously optimizes angles jaw positions that are customized patient geometry. Specifically, includes 2 key steps: (1)...
Purpose.We have previously reported an artificial intelligence (AI) agent that automatically generates intensity-modulated radiation therapy (IMRT) plans via fluence map prediction, by-passing inverse planning. This AI achieved clinically comparable quality for prostate cases, but its performance on head-and-neck patients leaves room improvement. study aims to collect insights of the deep-learning-based (DL-based) prediction model by systematically analyzing errors.Methods.From modeling...
Objective. Deep learning (DL) models for fluence map prediction (FMP) have great potential to reduce treatment planning time in intensity-modulated radiation therapy (IMRT) by avoiding the lengthy inverse optimization process. This study aims improve rigor of input feature design a DL-FMP model examining how different designs features influence performance.Approach. included 231 head-and-neck patients. Three were investigated. The first (D1) assumed that information all critical structures...
In this paper,we report a novel measurement system based on the development of Fudan Scanning Proton Microscopy(SPM) facility.By using Si-PIN diode(Hamamatsu S1223-01) detector,scanning transmission ion microscopy(STIM) has been set up.It can provide density and structural images with high probing efficiency non-destruction by utilizing energy loss energy(MeV) focused ions penetrating through thin sample.STIM is able to map distribution organic elements which mostly compose biology...