Yang Kyun Park

Dr. Yang Kyun Park

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 April 2024 in Journal of Applied Clinical Medical Physics
Verified
Journal Article
Open access
EKEuidam Kim
Euidam Kim
YPYang Kyun Park
Yang Kyun Park
TZTianyu Zhao
Tianyu Zhao
ELEric Laugeman
Eric Laugeman
XZXiaodong Neo Zhao
Xiaodong Neo Zhao
HLHugh Lee
Hugh Lee
Purpose: The quality of on‐board imaging systems, including cone‐beam computed tomography (CBCT), plays a vital role in image‐guided radiation therapy (IGRT) and adaptive radiotherapy. Recently, there has been an upgrade of the CBCT systems fused in the O‐ring linear accelerators called HyperSight, featuring a high imaging performance. As the characterization of a new imaging system is essential, we evaluated the image quality of the HyperSight system by comparing it with Halcyon 3.0 CBCT and providing benchmark data for routine imaging quality assurance.Methods: The HyperSight features ultra‐fast scan time, a larger kilovoltage (kV) detector, a more substantial kV tube, and an advanced reconstruction algorithm. Imaging protocols in the two modes of operation, treatment mode with IGRT and the CBCT for planning (CBCTp) mode were evaluated and compared with Halcyon 3.0 CBCT. Image quality metrics, including spatial resolution, contrast resolution, uniformity, noise, computed tomography (CT) number linearity, and calibration error, were assessed using a Catphan and an electron density phantom and analyzed with TotalQA software.Results: HyperSight demonstrated substantial improvements in contrast‐to‐noise ratio and noise in both IGRT and CBCTp modes compared to Halcyon 3.0 CBCT. CT number calibration error of HyperSight CBCTp mode (1.06%) closely matches that of a full CT scanner (0.72%), making it suitable for adaptive planning. In addition, the advanced hardware of HyperSight, such as ultra‐fast scan time (5.9 s) or 2.5 times larger heat unit capacity, enhanced the clinical efficiency in our experience.Conclusions: HyperSight represented a significant advancement in CBCT imaging. With its image quality, CT number accuracy, and ultra‐fast scans, HyperSight has a potential to transform patient care and treatment outcomes. The enhanced scan speed and image quality of HyperSight are expected to significantly improve the quality and efficiency of treatment, particularly benefiting patients.


30 May 2024 in Physics in Medicine & Biology
Verified
Journal Article
Open access
YGYin Gao
Yin Gao
YPYang Kyun Park
Yang Kyun Park
XJXun Jia
Xun Jia
Objective. Automatic treatment planning of radiation therapy (RT) is desired to ensure plan quality, improve planning efficiency, and reduce human errors. We have proposed an Intelligent Automatic Treatment Planning framework with a virtual treatment planner (VTP), an artificial intelligence robot built using deep reinforcement learning, autonomously operating a treatment planning system (TPS). This study extends our previous successes in relatively simple prostate cancer RT planning to head-and-neck (H&N) cancer, a more challenging context even for human planners due to multiple prescription levels, proximity of targets to critical organs, and tight dosimetric constraints. Approach. We integrated VTP with a real clinical TPS to establish a fully automated planning workflow guided by VTP. This integration allowed direct model training and evaluation using the clinical TPS. We designed the VTP network structure to approach the decision-making process in RT planning in a hierarchical manner that mirrors human planners. The VTP network was trained via the Q-learning framework. To assess the effectiveness of VTP, we conducted a prospective evaluation in the 2023 Planning Challenge organized by the American Association of Medical Dosimetrists (AAMD). We extended our evaluation to include 20 clinical H&N cancer patients, comparing the plans generated by VTP against their clinical plans. Main results. In the prospective evaluation for the AAMD Planning Challenge, VTP achieved a plan score of 139.08 in the initial phase evaluating plan quality, and 15 min of planning time with the first place ranking in the adaptive phase competing for planning efficiency while meeting all plan quality requirements. For clinical cases, VTP-generated plans achieved an average VTP score of 125.33 ± 11.12 , which outperformed the corresponding clinical plans with an average score of 117.76 ± 13.56 . Significance. We successfully integrated VTP with the clinical TPS to achieve a fully automated treatment planning workflow. The compelling performance of VTP demonstrated its potential in automating H&N cancer RT planning.

4 November 2020 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
HLH Hc Lee
H Hc Lee
YPYang Kyun Park
Yang Kyun Park
XDX Duan
X Duan
XJX Jia
X Jia
SJS Jiang
S Jiang
MYM Yang
M Yang
Dual-energy computed tomography (DECT) has shown a great potential for lowering range uncertainties, which is necessary for truly leveraging the Bragg peak in proton therapy. However, analytical stopping-power-ratio (SPR) estimation methods have limitations in resolving the influence from the beam-hardening artifact, i.e. CT number variation of the same object scanned under different imaging conditions, such as different patient size and location in the field-of-view (FOV). We present a convolutional neural network (CNN)-based framework to estimate proton SPR that accounts for patient geometry variation and addresses CT number variation. The proposed framework was tested on both prostate and head-and-neck (HN) patient datasets. Simulated CT images were used in order to have a well-defined ground-truth SPR for evaluation. Two training scenarios were evaluated: training with patient CT images (ideal scenario) and training with computational phantoms (realistic scenario). For the training in ideal scenario, computational phantoms were created based on 120 kVp patient CT images using a custom-defined density and material translation curve. Then, 80 kVp and 150 kVp Sn DECT image pairs were obtained using ray-tracing simulation, and their corresponding SPR was calculated from the known density and elemental compositions. For the training in realistic scenario, computational phantoms were created based on the geometry of calibration phantoms. For both scenarios, evaluation was performed on the phantoms created from patient CT images. Compared to a conventional parametric model, U-net trained with computational phantoms (realistic scenario) reduced the SPR estimation uncertainty (95th percentile) of the prostate patient from 1.10% to 0.71%, and HN patient from 2.11% to 1.20%. With the U-net trained with patient images (ideal scenario) uncertainty values were 0.32% and 0.42% for prostate and HN patients, respectively. These results suggest that CNN has great potential to improve the accuracy of SPR estimation in proton therapy by incorporating individual patient geometry information.

11 November 2025 in Radiation
Verified
Journal Article
Open access
PDF file
BZBanghao Zhou
Banghao Zhou
LGLixiang Guo
Lixiang Guo
WLWeiguo Lu
Weiguo Lu
MRMahbubur Rahman
Mahbubur Rahman
RZRongxiao Zhang
Rongxiao Zhang
KWKen Kang-Hsin Wang
Ken Kang-Hsin Wang
Background: FLASH radiotherapy delivers ultra-high dose rates with normal tissue sparing, but mechanisms remain unclear. We present a streamlined workflow for establishing a LINAC-based electron FLASH (eFLASH) platform in low-resource settings without requiring vendor-proprietary hardware or software, or vendor-assisted modifications to broaden accessibility for FLASH studies. Methods: A LINAC was converted to eFLASH with pulse control and monitoring. Automatic frequency control (AFC) was optimized to stabilize dose per pulse (DPP). Beam data were measured with EBT-XD films, and a Monte Carlo (MC) model was commissioned for in vivo dose calculation. We demonstrated in vivo dosimetry in planning studies of mouse whole-brain and rat spinal cord (C1–T2) irradiation. We further assessed the impact of AFC optimization on the FLASH spinal cord study. Results: AFC optimization stabilized DPP at ~0.6 Gy/pulse, reducing large fluctuations under the default setting. MC agreed with measurements within 2% for PDDs and profiles. MC planning showed uniform whole-brain irradiation with 6 MeV FLASH, while the spinal cord study exhibited up to 10% dose fall-off within 1 cm along the cord, suggesting potential dose-volume effects confounding FLASH sparing. Following AFC optimization, 50% of the C1–T2 cord reached >133 Gy/s, a 23% increase versus default. Conclusions: We demonstrated a cost-effective eFLASH platform and verified its accuracy for preclinical studies, expanding the accessibility of FLASH research.

8 June 2026 in Machine Learning: Health
Verified
Journal Article
Open access
PDF file
AMAusten Matthew Maniscalco
Austen Matthew Maniscalco
YPYang Kyun Park
Yang Kyun Park
SDSean Joseph Domal
Sean Joseph Domal
MLMu-Han Lin
Mu-Han Lin
SHSanda Maria Harabagiu
Sanda Maria Harabagiu
DNDan Nguyen
Dan Nguyen
Autonomous radiotherapy planning via agentic orchestration using a multimodal TPS-integrated compound AI platform, Maniscalco, Austen Matthew, Park, Yang-Kyun, Domal, Sean J, Lin, Mu-Han, Harabagiu, Sanda Maria, Jiang, Steve B, Nguyen, Dan Autonomous radiotherapy planning via agentic orchestration using a multimodal TPS-integrated compound AI platform, Maniscalco, Austen Matthew, Park, Yang-Kyun, Domal, Sean J, Lin, Mu-Han, Harabagiu, Sanda Maria, Jiang, Steve B, Nguyen, Dan