Jin Sung Kim
Yonsei University
Imaging phantomQuality assuranceOpticsPhysicsRadiologyIterative reconstructionBeam (structure)Materials scienceMonte Carlo methodMedical physicsRadiation treatment planningTomotherapyProton therapyNuclear medicineComputer visionComputer scienceRadiation therapyProtonMedicineImage-guided radiation therapy
244Publications
15H-index
1,172Citations
Publications 232
Newest
#1Jaehee Chun (Yonsei University)H-Index: 1
#2Justin C. ParkH-Index: 11
Last. Steve B JiangH-Index: 65
view all 8 authors...
In this study, we propose a tailored DL framework for patient-specific performance that leverages the behavior of a model intentionally overfitted to a patient-specific training dataset augmented from the prior information available in an ART workflow - an approach we term Intentional Deep Overfit Learning (IDOL). Implementing the IDOL framework in any task in radiotherapy consists of two training stages: 1) training a generalized model with a diverse training dataset of N patients, just as in t...
#1Seung Yeun Chung (Yonsei University)H-Index: 5
#2Jee Suk Chang (Yonsei University)H-Index: 14
Last. Yong Bae Kim (Yonsei University)H-Index: 20
view all 9 authors...
BACKGROUND In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians' workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours...
Source
#1Su Chul Han (Yonsei University)
#2Jihun Kim (Yonsei University)H-Index: 5
Last. Jin Sung Kim (Yonsei University)H-Index: 15
view all 8 authors...
This study evaluates the changes occurring in the X-ray energy of a linear accelerator (LINAC) using a Daily QA3 detector system. This is accomplished by comparing the Daily QA3 results against those obtained using a water phantom. The X-energy levels of a LINAC were monitored over a duration of 1 month using the Daily QA3 system. Moreover, to account for the uncertainty, the reproducibility of the Daily QA3 ionization-chamber results was assessed by performing repeated measurements (12 per day)...
Source
#1Nalee Kim (Yonsei University)H-Index: 8
#2Jaehee Chun (Yonsei University)H-Index: 3
Last. Jin Sung Kim (Yonsei University)H-Index: 15
view all 6 authors...
This study investigated the feasibility of deep learning-based segmentation (DLS) and continual training for adaptive radiotherapy (RT) of head and neck (HN (ii) using data obtained from 60 identical patients with 20 unmatched patients in the test set (DLSu). Manually contoured OARs in adaptive planning CT for independent 20 patients were provided as test sets. Deformable image registration (DIR) was also performed. All 23 OARs were compared using quantitative measurements, and nine OARs were al...
Source
#1Min Cheol Han (Yonsei University)H-Index: 4
#2Kyung Hwan Chang (Yonsei University)H-Index: 3
Last. Jin Sung Kim (Yonsei University)H-Index: 15
view all 8 authors...
Abstract Purpose Existing phantom-less quality assurance (QA) platforms does not provide patient-specific QA for helical tomotherapy (HT). A new system, called TomoEQA, is presented to facilitate this using the leaf open time (LOT) of a binary multi-leaf collimator, as measured by an exit detector. Methods TomoEQA was designed to provide measurement-based LOTs based on detector data and to generate a new digital imaging and communication in medicine (DICOM) dataset that includes the measured LOT...
Source
#1Seo Hee Choi (Yonsei University)H-Index: 10
#2Jee Suk Chang (Yonsei University)H-Index: 14
Last. Yong Bae Kim (Yonsei University)H-Index: 20
view all 10 authors...
ABSTRACT Purpose To study the hypothyroidism risk following adjuvant radiotherapy (RT) and the association of different RT targets with hypothyroidism risk. Methods and Materials We studied 4,073 women treated with adjuvant RT for breast cancer in 2007–2016. The primary endpoint was hypothyroidism development following RT. Patients were divided and analyzed into 3 groups: “whole breast (WB)-alone” (n = 2,468), “regional node irradiation (RNI)-Lv.4” (n = 215, cranial border at the subclavian arte...
Source
#1Heejoo Ko (Catholic University of Korea)
#2Jee Suk Chang (Yonsei University)H-Index: 14
Last. Jin Sung Kim (Yonsei University)H-Index: 15
view all 11 authors...
Source
#2Jin Sung KimH-Index: 15
Last. Sohyun AhnH-Index: 3
view all 4 authors...
Source
#1Dong Wook Kim (Yonsei University)H-Index: 15
#2Jiwon Sung (Seoul National University Hospital)H-Index: 6
Last. Dong-Ho ShinH-Index: 32
view all 16 authors...
Source