최장환(崔場煥) 조교수

휴먼기계바이오공학부/바이오정보학협동과정/시스템헬스융합전공[대학원]

최장환 프로필 사진
⌨ Medical AI Lab : http://bioe.ewha.ac.kr/
⌨ Intelligent Medical & Vision Research Group: https://imvrgroup.wixsite.com/imvrg

최장환 교수는 기계학습/인공지능 기반 Computer vision, Bio-informatics 관련 연구에 특화된 Medical AI Lab의 PI를 맡고 있다. 현재 Medical AI Lab은 BK21플러스, 기초연구실(BRL), 범부처의료기기지원사업 등 다양한 정부 사업을 통해 연구비를 지원받고 있으며, 다양한 국내외 유수의 산학연 협력연구 기관들과 함께 메디컬 빅데이터를 활용한 AI 기반 의료기기 개발 관련 융복합 연구를 활발히 수행하고 있다. Stanford University (미국, Palo Alto)에서 “다자유도 Robotics 기술 기반 Weight-bearing C-arm CT 개발”에 관한 연구 주제로 박사학위를 취득했다. 그 후, Stanford 의과대학 박사후과정 (Postdoctoral Research Fellow) 중에는 세계 최초로 임상에 적용 가능한 Weight-bearing CT 시스템을 성공적으로 개발하면서, 정형학외과 분야에서 가장 권위 있는 국제 학회인 Orthopaedic Research Society에서 젊은연구자상 (New Investigator Recognition Award)을 수상하였다.
  • 연구협력관 357호
  • 02-3277-6945
  • 면담 가능시간
    • 이메일 후 스케쥴
  • 연구관심분야
    • 인공지능/기계학습, 컴퓨터 비전, 바이오인포메틱스, 딥러닝 기반 바이오/의료영상처리, 헬스케어 의료기기
[]
[]
[{itemId=000000160498, userId=****153867, userName=최장환, title=A learning-based material decomposition pipeline for multi-energy x-ray imaging, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=MEDICAL PHYSICS, citationdate=2019, citationoissueno=v.46 no.2, citationpages=689-703, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000160498, publicYn=Y}, {itemId=000000162279, userId=****153867, userName=최장환, title=Automated stitching of microscope images of fluorescence in cells with minimal overlap, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=Micron, citationgenre=Journal, citationdate=2019, citationoissueno=v.126, citationpages=102718, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000162279, publicYn=Y}, {itemId=000000149954, userId=****153867, userName=최장환, title=Assessment of a photon-counting detector for a dual-energy C-arm angiographic system, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=Medical Physics, citationdate=2017, citationoissueno=v.44 no.11, citationpages=5938-5948, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000149954, publicYn=Y}, {itemId=000000145629, userId=****153867, userName=최장환, title=Fully automated nipple detection in digital breast tomosynthesis, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=Computer Methods and Programs in Biomedicine, citationgenre=Journal, citationdate=2017, citationoissueno=v.143, citationpages=113-120, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000145629, publicYn=Y}, {itemId=000000162147, userId=****153867, userName=최장환, title=Scatter correction using a primary modulator on a clinical angiography C-arm CT system, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=MEDICAL PHYSICS, citationgenre=Journal, citationdate=2017, citationoissueno=v.44 no.9, citationpages=E125-E137, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000162147, publicYn=Y}, {itemId=000000162070, userId=****153867, userName=최장환, title=Interventional dual-energy imaging-Feasibility of rapid kV-switching on a C-arm CT system, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=MEDICAL PHYSICS, citationgenre=Journal, citationdate=2016, citationoissueno=v.43 no.10, citationpages=5537-5546, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000162070, publicYn=Y}, {itemId=000000162022, userId=****153867, userName=최장환, title=Marker-free motion correction in weight-bearing cone-beam CT of the knee joint, indexed=SCIE;SCOPUS, subtype=Article, citationtitle=MEDICAL PHYSICS, citationgenre=Journal, citationdate=2016, citationoissueno=v.43 no.3, citationpages=1235-1248, uritype=고유URL, urientity=http://www.dcollection.net/handler/ewha/000000162022, publicYn=Y}]
[{seq=15386710131, userId=153867, achvDiv=101, achvNo=31, div=01, achvDivNm=학술지논문, achvNm=The effect of patellofemoral pain syndrome on patellofemoral joint kinematics under upright weight-bearing conditions, representDt=20200901, representYear=2020, publishOrgan=Public Library of Science, representNation=미국, journalNm=PLOS ONE, vol=0, edition=0, startPg=0, endPg=0, issnNo=1932-6203, langDiv=ENG, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCIE, indexed=SCIE, createDt=2020-09-27 01:09:30.0, entryDt=2020-09-27 01:12:55.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710118, userId=153867, achvDiv=101, achvNo=18, div=01, achvDivNm=학술지논문, achvNm=A learning-based material decomposition pipeline for multi-energy x-ray imaging, representDt=20190201, representYear=2019, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=46, edition=2, startPg=689, endPg=703, issnNo=0094-2405, langDiv=ENG, abstCntn=PurposeBenefiting from multi-energy x-ray imaging technology, material decomposition facilitates the characterization of different materials in x-ray imaging. However, the performance of material decomposition is limited by the accuracy of the decomposition model. Due to the presence of nonideal effects in x-ray imaging systems, it is difficult to explicitly build the imaging system models for material decomposition. As an alternative, this paper explores the feasibility of using machine learning approaches for material decomposition tasks. MethodsIn this work, we propose a learning-based pipeline to perform material decomposition. In this pipeline, the step of feature extraction is implemented to integrate more informative features, such as neighboring information, to facilitate material decomposition tasks, and the step of hold-out validation with continuous interleaved sampling is employed to perform model evaluation and selection. We demonstrate the material decomposition capability of our proposed pipeline with promising machine learning algorithms in both simulation and experimentation, the algorithms of which are artificial neural network (ANN), Random Tree, REPTree and Random Forest. The performance was quantitatively evaluated using a simulated XCAT phantom and an anthropomorphic torso phantom. In order to evaluate the proposed method, two measurement-based material decomposition methods were used as the reference methods for comparison studies. In addition, deep le, studyField=공학 전자/정보통신공학 마이크로프로세서/컴퓨터 인공지능, isiDiv=SCI, indexed=SCI, createDt=2019-03-04 23:53:35.0, entryDt=2019-12-23 16:17:49.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710121, userId=153867, achvDiv=101, achvNo=21, div=01, achvDivNm=학술지논문, achvNm=Automated stitching of microscope images of fluorescence in cells with minimal overlap, representDt=20191101, representYear=2019, publishOrgan=Pergamon Press Ltd., representNation=영국, journalNm=MICRON, vol=126, edition=0, startPg=102718, endPg=102718, issnNo=0968-4328, langDiv=ENG, abstCntn=The morphology of tumor cells is highly related to their phenotype and activity. To verify the drug response of a brain tumor patient, fluorescence microscope images of drug-treated patient-derived cells in each well are analyzed. Due to the limitation of the field of view (FOV), a large number of small FOVs are acquired to compose one complete microscope well. Here, we propose an automated method for accurately stitching tile-scanned fluorescence microscope images, even with noise and a narrow overlapping region between adjacent fields. The proposed method is based on intensity-based normalized cross-correlation (NCC) and a triangular method-based threshold. The proposed method's quantitative accuracy and the sensitivity of the input was compared to other existing stitching tools, MIST and FijiIS, setting manually stitched images as the ground truth. The test images were 20 samples of 3 x 3 grid images in three versions of the fluorescence channel. The distance between the location of each field and number of cells was determined for different input field overlap ranges (1%, 3%, 5%, and 10%), while the actual value was about 1.15%. The proposed method had a distance error of 1.5 pixels at an input overlap of 1%, showing the lowest minimum error at all channels. Regarding the difference in cell numbers, although the number of overlapping cells was always small because of the narrow overlapping range, the proposed method was able to generate the resultant image with the smalle, studyField=공학 전자/정보통신공학 영상시스템, isiDiv=SCI, indexed=SCI, createDt=2019-09-06 20:11:25.0, entryDt=2019-12-23 16:15:55.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710120, userId=153867, achvDiv=101, achvNo=20, div=01, achvDivNm=학술지논문, achvNm=의료영상 기반 암 예후 예측 AI 기술 최신동향, representDt=20190401, representYear=2019, publishOrgan=한국통신학회, representNation=대한민국, journalNm=정보와 통신, vol=36, edition=4, startPg=10, endPg=18, issnNo=12264725, langDiv=KOR, abstCntn=라디오믹스(radiomics)는 의료영상으로부터 정보를 추출하여 환자의 예후예측을 진단하는 학문으로서 개인별 맞춤 의료를 제 공하기 위한 정밀 진료와 함께 대두되었다. 본고에서는 라디오 믹스의 대표적인 전통적 방식인 handcrafted radiomics와 딥 러닝을 이용한 deep learning-based radiomics 와 함께 이를 활용한 폐암 환자의 생존과 재발 예측 연구의 최신 동향에 대해 알아본다. , studyField=공학, createDt=2019-07-21 01:19:00.0, entryDt=2020-06-22 16:19:22.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710116, userId=153867, achvDiv=101, achvNo=16, div=01, achvDivNm=학술지논문, achvNm=A Method for Generating Synthetic Mammograms using Information from Digital Breast Tomosynthesis (DBT) Images, representDt=20180601, representYear=2018, publishOrgan=Springer Verlag, representNation=독일, journalNm=INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, vol=13, edition=1, startPg=165, endPg=166, issnNo=1861-6410, langDiv=ENG, studyField=의약학 방사선과학 진단방사선 방사선기술, isiDiv=SCIE, indexed=SCIE, createDt=2018-07-04 17:15:50.0, entryDt=2018-12-11 13:18:42.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710112, userId=153867, achvDiv=101, achvNo=12, div=01, achvDivNm=학술지논문, achvNm=Assessment of a photon-counting detector for a dual-energy C-arm angiographic system, representDt=20171101, representYear=2017, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=44, edition=11, startPg=5938, endPg=5948, issnNo=0094-2405, langDiv=ENG, abstCntn=PurposeThis article presents the implementation and assessment of photon-counting dual-energy x-ray detector technology for angiographic C-arm systems in interventional radiology. MethodsA photon-counting detector was successfully integrated into a clinical C-arm CT system. Detector performance was assessed using image uniformity metrics in both 2D projections and 3D cone-beam computed tomography (CBCT) images. Uniform exposure fields were acquired to analyze projection images and scans of a homogeneous cylinder phantom were taken to analyze 3D reconstructions. Image uniformity was assessed over a broad range of imaging parameters. ResultsDetector calibration greatly improved image uniformity, reducing image variation from 8.8% to 0.5% in an ideal scenario, but image uniformity degraded when imaging parameters varied strongly from values set at calibration: the tube voltage, low-high energy threshhold, and tube current had the greatest impact. Material discrimination and dynamic angiography capabilities were successfully demonstrated in separate phantom and invivo experiments. ConclusionThe uniformity results identified major factors degrading image quality. The quantitative results will guide selection of calibration points to mitigate the loss of uniformity. The unique combination of dual-energy and fluoroscopy imaging capabilities with a flat-panel photon-counting detector may enable new applications in interventional radiology., studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-11-16 13:00:15.0, entryDt=2018-01-29 09:45:58.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710111, userId=153867, achvDiv=101, achvNo=11, div=01, achvDivNm=학술지논문, achvNm=Comparison of Different Approaches for Measuring Tibial Cartilage Thickness, representDt=20170701, representYear=2017, publishOrgan=Informationsmanagement in der Biotechnologie e.V. (IMBio e.V.), representNation=독일, journalNm=JOURNAL OF INTEGRATIVE BIOINFORMATICS, vol=14, edition=2, startPg=1, endPg=10, issnNo=1613-4516, langDiv=ENG, abstCntn=Osteoarthritis is a degenerative disease affecting bones and cartilage especially in the human knee. In this context, cartilage thickness is an indicator for knee cartilage health. Thickness measurements are performed on medical images acquired in-vivo. Currently, there is no standard method agreed upon that defines a distance measure in articular cartilage. In this work, we present a comparison of different methods commonly used in literature. These methods are based on nearest neighbors, surface normal vectors, local thickness and potential field lines. All approaches were applied to manual segmentations of tibia and lateral and medial tibial cartilage performed by experienced raters. The underlying data were contrast agent-enhanced cone-beam C-arm CT reconstructions of one healthy subject's knee. The subject was scanned three times, once in supine position and two times in a standing weight-bearing position. A comparison of the resulting thickness maps shows similar distributions and high correlation coefficients between the approaches above 0.90. The nearest neighbor method results on average in the lowest cartilage thickness values, while the local thickness approach assigns the highest values. We showed that the different methods agree in their thickness distribution. The results will be used for a future evaluation of cartilage change under weight-bearing conditions., studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCOPUS, indexed=SCOPUS, createDt=2017-08-11 01:41:15.0, entryDt=2019-07-02 13:57:10.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671011, userId=153867, achvDiv=101, achvNo=1, div=01, achvDivNm=학술지논문, achvNm=Fully automated nipple detection in digital breast tomosynthesis, representDt=20170501, representYear=2017, publishOrgan=Elsevier BV, representNation=아일랜드, journalNm=COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, vol=143, edition=0, startPg=113, endPg=120, issnNo=0169-2607, langDiv=ENG, abstCntn=Background and objective: We propose a nipple detection algorithm for use with digital breast tomosynthesis (DBT) images. DBT images have been developed to overcome the weaknesses of 2D mammograms for denser breasts by providing 3D breast images. The nipple location acts as an invaluable landmark in DBT images for aligning the right and left breasts and describing the relative location of any existing lesions. Methods: Nipples may be visible or invisible in a breast image, and therefore a nipple detection method must be able to detect the nipples for both cases. The detection method for visible nipples based on their shape is simple and highly efficient. However, it is difficult to detect invisible nipples because they do not have a prominent shape. Fibroglandular tissue in a breast is anatomically connected with the nipple. Thus, the nipple location can be detected by analyzing the location of such tissue. In this paper, we propose a method for detecting the location of both visible and invisible nipples using fibroglandular tissue and changes in the breast area. Results: Our algorithm was applied to 138 DBT images, and its nipple detection accuracy was evaluated based on the mean Euclidean distance. The results indicate that our proposed method achieves a mean Euclidean distance of 3.10 +/- 2.58 mm. Conclusions: The nipple location can be a very important piece of information in the process of a DBT image registration. This paper presents a method for the automatic nippl, studyField=의약학 임상병리학 검사정보학 영상처리학, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 14:23:07.0, entryDt=2017-11-16 14:31:54.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710113, userId=153867, achvDiv=101, achvNo=13, div=01, achvDivNm=학술지논문, achvNm=Scatter correction using a primary modulator on a clinical angiography C-arm CT system, representDt=20170901, representYear=2017, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=44, edition=9, startPg=125, endPg=137, issnNo=0094-2405, langDiv=ENG, abstCntn=Purpose: Cone beam computed tomography (CBCT) suffers from a large amount of scatter, resulting in severe scatter artifacts in the reconstructions. Recently, a new scatter correction approach, called improved primary modulator scatter estimation (iPMSE), was introduced. That approach utilizes a primary modulator that is inserted between the X-ray source and the object. This modulation enables estimation of the scatter in the projection domain by optimizing an objective function with respect to the scatter estimate. Up to now the approach has not been implemented on a clinical angiography C-arm CT system. Methods: In our work, the iPMSE method is transferred to a clinical C-arm CBCT. Additional processing steps are added in order to compensate for the C-arm scanner motion and the automatic X-ray tube current modulation. These challenges were overcome by establishing a reference modulator database and a block-matching algorithm. Experiments with phantom and experimental in vivo data were performed to evaluate the method. Results: We show that scatter correction using primary modulation is possible on a clinical C-arm CBCT. Scatter artifacts in the reconstructions are reduced with the newly extended method. Compared to a scan with a narrow collimation, our approach showed superior results with an improvement of the contrast and the contrast-to-noise ratio for the phantom experiments. In vivo data are evaluated by comparing the results with a scan with a narrow collimation and , studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-09-13 22:05:13.0, entryDt=2018-01-29 09:43:56.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671019, userId=153867, achvDiv=101, achvNo=9, div=01, achvDivNm=학술지논문, achvNm=Interventional dual-energy imaging-Feasibility of rapid kV-switching on a C-arm CT system, representDt=20161001, representYear=2016, publishOrgan=AMER ASSOC PHYSICISTS MEDICINE AMER INST PHYSICS, representNation=미국, journalNm=MEDICAL PHYSICS, vol=43, edition=10, startPg=5537, endPg=5546, issnNo=0094-2405, langDiv=ENG, abstCntn=Purpose: In the last years, dual-energy CT imaging has shown clinical value, thanks to its ability to differentiate materials based on their atomic number and to exploit different properties of images acquired at two different energies. C-arm CT systems are used to guide procedures in the interventional suite. Until now, there are no commercially available systems that employ dual-energy material decomposition. This paper explores the feasibility of implementing a fast kV-switching technique on a clinically available angiographic system for acquiring dual-energy C-arm CT images. Methods: As an initial proof of concept, a fast kV-switching approach was implemented on an angiographic C-arm system and the peak tube voltage during 3D rotational scans was measured. The tube voltage measurements during fast kV-switching scans were compared to corresponding measurements on kV-constant scans. Additionally, to prove stability of the requested exposure parameters, the accuracy of the delivered tube current and pulse width were also recorded and compared. In a first phantom experiment, the voxel intensity values of the individual tube voltage components of the fast kV-switching scans were compared to their corresponding kV-constant scans. The same phantom was used for a simple material decomposition between different iodine concentrations and pure water using a fast kV-switching protocol of 81 and 125 kV. In the last experiment, the same kV-switching protocol as in the phantom scan w, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 23:19:10.0, entryDt=2017-08-11 15:02:16.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=15386710110, userId=153867, achvDiv=101, achvNo=10, div=01, achvDivNm=학술지논문, achvNm=Kinect-based correction of overexposure artifacts in knee imaging with C-Arm CT systems, representDt=20160101, representYear=2016, publishOrgan=Hindawi Publishing Corporation 410 Park Avenue, 15th Floor, 287 pmb New York NY 10022, representNation=이집트, journalNm=International Journal of Biomedical Imaging, vol=2016, edition=1, startPg=1, endPg=15, issnNo=1687-4188, langDiv=ENG, abstCntn=Objective. To demonstrate a novel approach of compensating overexposure artifacts in CT scans of the knees without attaching any supporting appliances to the patient. C-Arm CT systems offer the opportunity to perform weight-bearing knee scans on standing patients to diagnose diseases like osteoarthritis. However, one serious issue is overexposure of the detector in regions close to the patella, which can not be tackled with common techniques. Methods. A Kinect camera is used to algorithmically remove overexposure artifacts close to the knee surface. Overexposed near-surface knee regions are corrected by extrapolating the absorption values from more reliable projection data. To achieve this, we develop a cross-calibration procedure to transform surface points from the Kinect to CT voxel coordinates. Results. Artifacts at both knee phantoms are reduced significantly in the reconstructed data and a major part of the truncated regions is restored. Conclusion. The results emphasize the feasibility of the proposed approach. The accuracy of the cross-calibration procedure can be increased to further improve correction results. Significance. The correction method can be extended to a multi-Kinect setup for use in real-world scenarios. Using depth cameras does not require prior scans and offers the possibility of a temporally synchronized correction of overexposure artifacts. To achieve this, we develop a cross-calibration procedure to transform surface points from the Kinect to CT vo, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCOPUS, indexed=SCOPUS, createDt=2017-03-10 23:34:01.0, entryDt=2017-08-11 15:02:05.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671012, userId=153867, achvDiv=101, achvNo=2, div=01, achvDivNm=학술지논문, achvNm=Marker-free motion correction in weight-bearing cone-beam CT of the knee joint, representDt=20160301, representYear=2016, publishOrgan=AMER ASSOC PHYSICISTS MEDICINE AMER INST PHYSICS, representNation=미국, journalNm=MEDICAL PHYSICS, vol=43, edition=3, startPg=1235, endPg=1248, issnNo=0094-2405, langDiv=ENG, abstCntn=Purpose: To allow for a purely image-based motion estimation and compensation in weight-bearing cone-beam computed tomography of the knee joint. Methods: Weight-bearing imaging of the knee joint in a standing position poses additional requirements for the image reconstruction algorithm. In contrast to supine scans, patient motion needs to be estimated and compensated. The authors propose a method that is based on 2D/3D registration of left and right femur and tibia segmented from a prior, motion-free reconstruction acquired in supine position. Each segmented bone is first roughly aligned to the motion-corrupted reconstruction of a scan in standing or squatting position. Subsequently, a rigid 2D/3D registration is performed for each bone to each of K projection images, estimating 6x4xK motion parameters. The motion of individual bones is combined into global motion fields using thin-plate-spline extrapolation. These can be incorporated into a motion-compensated reconstruction in the backprojection step. The authors performed visual and quantitative comparisons between a state-of-the-art marker-based (MB) method and two variants of the proposed method using gradient correlation (GC) and normalized gradient information (NGI) as similarity measure for the 2D/3D registration. Results: The authors evaluated their method on four acquisitions under different squatting positions of the same patient. All methods showed substantial improvement in image quality compared to the unco, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 15:40:43.0, entryDt=2017-08-11 15:03:39.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671017, userId=153867, achvDiv=101, achvNo=7, div=01, achvDivNm=학술지논문, achvNm=Dynamic detector offsets for field of view extension in C-arm computed tomography with application to weight-bearing imaging, representDt=20150501, representYear=2015, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=42, edition=5, startPg=2718, endPg=2729, issnNo=0094-2405, langDiv=ENG, abstCntn=Purpose: In C-arm computed tomography (CT), the field of view (FOV) is often not sufficient to acquire certain anatomical structures, e.g., a full hip or thorax. Proposed methods to extend the FOV use a fixed detector displacement and a 360 degrees scan range to double the radius of the FOV. These trajectories are designed for circular FOVs. However, there are cases in which the required FOV is not circular but rather an ellipsoid. Methods: In this work, the authors show that in fan-beam CT, the use of a dynamically adjusting detector offset can reduce the required scan range when using a noncircular FOV. Furthermore, the authors present an analytic solution to determine the minimal required scan ranges for elliptic FOVs given a certain detector size and an algorithmic approach for arbitrary FOVs. Results: The authors show that the proposed method can result in a substantial reduction of the required scan range. Initial reconstructions of data sets acquired with our new minimal trajectory yielded image quality comparable to reconstructions of data acquired using a fixed detector offset and a full 360 degrees rotation. Conclusions: Our results show a promising reduction of the necessary scan range especially for ellipsoidal objects that extend the FOV. In noncircular FOVs, there exists a set of solutions that allow a trade-off between detector size and scan range. (C) 2015 American Association of Physicists in Medicine., studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 23:08:34.0, entryDt=2020-03-11 10:02:03.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671013, userId=153867, achvDiv=101, achvNo=3, div=01, achvDivNm=학술지논문, achvNm=Practical dose point-based methods to characterize dose distribution in a stationary elliptical body phantom for a cone-beam C-arm CT system, representDt=20150801, representYear=2015, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=42, edition=8, startPg=4920, endPg=4932, issnNo=0094-2405, langDiv=ENG, abstCntn=Purpose: To propose new dose point measurement-based metrics to characterize the dose distributions and the mean dose from a single partial rotation of an automatic exposure control-enabled, C-arm-based, wide cone angle computed tomography system over a stationary, large, body-shaped phantom. Methods: A small 0.6 cm(3) ion chamber (IC) was used to measure the radiation dose in an elliptical body-shaped phantom made of tissue-equivalent material. The IC was placed at 23 well-distributed holes in the central and peripheral regions of the phantom and dose was recorded for six acquisition protocols with different combinations of minimum kVp (109 and 125 kVp) and z-collimator aperture (full: 22.2 cm; medium: 14.0 cm; small: 8.4 cm). Monte Carlo (MC) simulations were carried out to generate complete 2D dose distributions in the central plane (z = 0). The MC model was validated at the 23 dose points against IC experimental data. The planar dose distributions were then estimated using subsets of the point dose measurements using two proposed methods: (1) the proximity-based weighting method (method 1) and (2) the dose point surface fitting method (method 2). Twenty-eight different dose point distributions with six different point number cases (4, 5, 6, 7, 14, and 23 dose points) were evaluated to determine the optimal number of dose points and their placement in the phantom. The performances of the methods were determined by comparing their results with those of the validated MC sim, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 18:19:06.0, entryDt=2020-03-11 10:10:51.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671015, userId=153867, achvDiv=101, achvNo=5, div=01, achvDivNm=학술지논문, achvNm=Fiducial marker-based correction for involuntary motion in weight-bearing C-arm CT scanning of knees. II. Experiment, representDt=20140601, representYear=2014, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=41, edition=6, startPg=061902-1, endPg=061902-16, issnNo=0094-2405, langDiv=ENG, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 22:53:27.0, entryDt=2017-08-11 15:03:16.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671018, userId=153867, achvDiv=101, achvNo=8, div=01, achvDivNm=학술지논문, achvNm=CONRAD—A software framework for cone-beam imaging in radiology, representDt=20131101, representYear=2013, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=40, edition=11, startPg=111914-1, endPg=111914-8, issnNo=0094-2405, langDiv=ENG, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 23:12:33.0, entryDt=2017-08-11 15:02:35.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}, {seq=1538671016, userId=153867, achvDiv=101, achvNo=6, div=01, achvDivNm=학술지논문, achvNm=Fiducial marker-based correction for involuntary motion in weight-bearing C-arm CT scanning of knees. Part I. Numerical model-based optimization, representDt=20130901, representYear=2013, publishOrgan=American Association of Physicists in Medicine, representNation=미국, journalNm=MEDICAL PHYSICS, vol=40, edition=9, startPg=091905-1, endPg=091905-12, issnNo=0094-2405, langDiv=ENG, studyField=공학 의공학 생체역학 의용영상처리, isiDiv=SCI, indexed=SCI, createDt=2017-03-10 23:03:04.0, entryDt=2017-08-11 15:02:59.0, pfhomeYn=Y, viewYn=Y, cateNm=학술지논문, cateEnNm=Publications in academic journals}]
연구실적
  • A learning-based material decomposition pipeline for multi-energy x-ray imaging MEDICAL PHYSICS, 2019, v.46 no.2, 689-703
    SCIE Scopus dColl.
  • Automated stitching of microscope images of fluorescence in cells with minimal overlap Micron, 2019, v.126, 102718
    SCIE Scopus dColl.
  • Assessment of a photon-counting detector for a dual-energy C-arm angiographic system Medical Physics, 2017, v.44 no.11, 5938-5948
    SCIE Scopus dColl.
  • Fully automated nipple detection in digital breast tomosynthesis Computer Methods and Programs in Biomedicine, 2017, v.143, 113-120
    SCIE Scopus dColl.
  • Scatter correction using a primary modulator on a clinical angiography C-arm CT system MEDICAL PHYSICS, 2017, v.44 no.9, E125-E137
    SCIE Scopus dColl.
  • Interventional dual-energy imaging-Feasibility of rapid kV-switching on a C-arm CT system MEDICAL PHYSICS, 2016, v.43 no.10, 5537-5546
    SCIE Scopus dColl.
  • Marker-free motion correction in weight-bearing cone-beam CT of the knee joint MEDICAL PHYSICS, 2016, v.43 no.3, 1235-1248
    SCIE Scopus dColl.
  • [학술지논문] The effect of patellofemoral pain syndrome on patellofemoral joint kinematics under upright weight-bearing conditions PLOS ONE, 2020, v.0 no.0 , 0-0
    SCIE
  • [학술지논문] A learning-based material decomposition pipeline for multi-energy x-ray imaging MEDICAL PHYSICS, 2019, v.46 no.2 , 689-703
    SCI
  • [학술지논문] Automated stitching of microscope images of fluorescence in cells with minimal overlap MICRON, 2019, v.126 no.0 , 102718-102718
    SCI
  • [학술지논문] 의료영상 기반 암 예후 예측 AI 기술 최신동향 정보와 통신, 2019, v.36 no.4 , 10-18
  • [학술지논문] A Method for Generating Synthetic Mammograms using Information from Digital Breast Tomosynthesis (DBT) Images INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2018, v.13 no.1 , 165-166
    SCIE
  • [학술지논문] Assessment of a photon-counting detector for a dual-energy C-arm angiographic system MEDICAL PHYSICS, 2017, v.44 no.11 , 5938-5948
    SCI
  • [학술지논문] Comparison of Different Approaches for Measuring Tibial Cartilage Thickness JOURNAL OF INTEGRATIVE BIOINFORMATICS, 2017, v.14 no.2 , 1-10
    Scopus
  • [학술지논문] Fully automated nipple detection in digital breast tomosynthesis COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2017, v.143 no.0 , 113-120
    SCI
  • [학술지논문] Scatter correction using a primary modulator on a clinical angiography C-arm CT system MEDICAL PHYSICS, 2017, v.44 no.9 , 125-137
    SCI
  • [학술지논문] Interventional dual-energy imaging-Feasibility of rapid kV-switching on a C-arm CT system MEDICAL PHYSICS, 2016, v.43 no.10 , 5537-5546
    SCI
  • [학술지논문] Kinect-based correction of overexposure artifacts in knee imaging with C-Arm CT systems International Journal of Biomedical Imaging, 2016, v.2016 no.1 , 1-15
    Scopus
  • [학술지논문] Marker-free motion correction in weight-bearing cone-beam CT of the knee joint MEDICAL PHYSICS, 2016, v.43 no.3 , 1235-1248
    SCI
  • [학술지논문] Dynamic detector offsets for field of view extension in C-arm computed tomography with application to weight-bearing imaging MEDICAL PHYSICS, 2015, v.42 no.5 , 2718-2729
    SCI
  • [학술지논문] Practical dose point-based methods to characterize dose distribution in a stationary elliptical body phantom for a cone-beam C-arm CT system MEDICAL PHYSICS, 2015, v.42 no.8 , 4920-4932
    SCI
  • [학술지논문] Fiducial marker-based correction for involuntary motion in weight-bearing C-arm CT scanning of knees. II. Experiment MEDICAL PHYSICS, 2014, v.41 no.6 , 061902-1-061902-16
    SCI
  • [학술지논문] CONRAD—A software framework for cone-beam imaging in radiology MEDICAL PHYSICS, 2013, v.40 no.11 , 111914-1-111914-8
    SCI
  • [학술지논문] Fiducial marker-based correction for involuntary motion in weight-bearing C-arm CT scanning of knees. Part I. Numerical model-based optimization MEDICAL PHYSICS, 2013, v.40 no.9 , 091905-1-091905-12
    SCI
  • [학술발표] Inertial Measurements for Motion Compensation in Weight-bearing Cone-beam CT of the Knee MICCAI 2020, 페루, 2020-10-04 International Conference on Medical image computing and computer-assisted intervention, 2020
  • [학술발표] NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results Conference on Computer Vision and Pattern Recognition, 미국, 2020-06-13 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020
  • [학술발표] Deep Convolutional Neural Network-Based Automated Lesion Detection in Wireless Capsule Endoscopy The International Forum on Medical Imaging in Asia (IFMIA), 싱가폴, 싱가폴, 2019-01-07 The PROCEEDINGS of The Joint 2019 International Workshop on Advanced Image Technology & International Forum on Medical Imaging in Asia, 2019
  • [학술발표] Differential phase contrast imaging using the phase retrieval of Hilbert Transform and noise filtering by low rank method The International Forum on Medical Imaging in Asia (IFMIA), 싱가폴, 싱가폴, 2019-01-07 The PROCEEDINGS of The Joint 2019 International Workshop on Advanced Image Technology & International Forum on Medical Imaging in Asia, 2019
  • [학술발표] Multi-Channel Volumetric Neural Network for Knee Cartilage Segmentation in Cone-beam CT Bildverarbeitung für die Medizin 2020, 독일, Berlin, 2019-12-15 Bildverarbeitung für die Medizin 2020, 2019
  • [학술발표] Multidimensional Noise Reduction in C-arm Cone-beam CT via 2D-based Landweber Iteration and 3D-based Deep Neural Networks SPIE Medical Imaging 2019, 미국, 샌디에고, 2019-02-17 Medical Imaging 2019: Physics of Medical Imaging, PROCEEDINGS VOLUME 10948, 2019
  • [학술발표] Noise Reduction Methods in Low-dose CT Data Combining Neural Networks and an Iterative Reconstruction Technique The International Forum on Medical Imaging in Asia (IFMIA), 싱가폴, Singapore, 2019-01-07 The PROCEEDINGS of The Joint 2019 International Workshop on Advanced Image Technology & International Forum on Medical Imaging in Asia, 2019
  • [학술발표] Noise Reduction Method in Low-dose CT Data Combining Neural Networks and An Iterative Reconstruction Technique 제4회 바이오영상신호처리 여름학교 바이오의료영상 딥러닝, 대한민국, 서울, 2018-08-30 제4회 바이오영상신호처리 여름학교, 2018
  • [학술발표] Precision Learning: Towards Use of Known Operators in Neural Networks International Conference on Pattern Recognition, 중국, 2018-08-21 24rd International Conference on Pattern Recognition (ICPR), 2018, 183-188
강의
  • 2020-2학기

    • 통계적학습이론

      • 학수번호 38586분반 01
      • 2학년 ( 3학점 , 3시간) 월 6~6 (공학) , 수 5~5 (159)
      • 영어강의 [비대면수업]
    • 의학영상처리

      • 학수번호 38601분반 01
      • 3학년 ( 3학점 , 3시간) 화 4~4 (연구) , 금 5~5 (101)
      • [비대면수업]
    • 융합캡스톤디자인II

      • 학수번호 38606분반 01
      • 4학년 ( 3학점 , 4.5시간) 수 3~3 (공학) , 금 2~3 (154)
      • [혼합수업]
    • 데이터사이언스

      • 학수번호 G18080분반 01
      • 학년 ( 3학점 , 3시간) 목 4~5 (캠)
  • 2020-1학기

    • 융합캡스톤디자인I

      • 학수번호 38588분반 01
      • 4학년 ( 3학점 , 4.5시간) 화 5~5 (공대강당) , 목 6~7 (공대강당)
    • 기초전산공학

      • 학수번호 38657분반 01
      • 2학년 ( 3학점 , 3시간) 화 4~4 (공학A125) , 금 5~5 (공학A125)
      • 영어강의
    • 딥러닝과바이오의료영상

      • 학수번호 G17650분반 01
      • 학년 ( 3학점 , 3시간) 목 4~5 (공학)
  • 2019-2학기

    • 통계적학습이론

      • 학수번호 38586분반 01
      • 2학년 ( 3학점 , 3시간) 수 6~6 (공학) , 금 4~4 (161)
      • 영어강의
    • 의학영상처리

      • 학수번호 38601분반 01
      • 3학년 ( 3학점 , 3시간) 월 5~5 (공학A107) , 수 4~4 (공학A107)
  • 2019-1학기

    • 기초전산공학

      • 학수번호 38657분반 01
      • 2학년 ( 3학점 , 3시간) 월 6~6 (공학A125) , 수 5~5 (공학A125)
      • 영어강의
    • 컴퓨터단층영상과딥러닝

      • 학수번호 G17673분반 01
      • 학년 ( 3학점 , 3시간) 금 5~6 (공학)
  • 2018-2학기

    • 통계적학습이론

      • 학수번호 38586분반 01
      • 2학년 ( 3학점 , 3시간) 화 6~6 (공학) , 목 4~4 (159)
      • 영어강의
    • 딥러닝과바이오의료영상

      • 학수번호 G17650분반 01
      • 학년 ( 3학점 , 3시간) 금 3~4 (공학)
  • 2018-1학기

    • 수치해석

      • 학수번호 20642분반 01
      • 2학년 ( 3학점 , 3시간) 수 6~6 (공학A101) , 금 4~4 (공학A101)
      • 언어변경,ABEEK 컴퓨터공학과 3학년 전공기초필수
    • 기초전산공학

      • 학수번호 38657분반 02
      • 2학년 ( 3학점 , 3시간) 월 5~5 (공학A125) , 수 4~4 (공학A125)
      • 영어강의,ABEEK
  • 2017-2학기

    • 미분적분학

      • 학수번호 20406분반 03
      • 1학년 ( 3학점 , 3시간) 월 7~7 (종) , 목 7~7 (101)
      • 영어강의,ABEEK 자연대 및 엘텍공대
    • 공학제도

      • 학수번호 38558분반 02
      • 1학년 ( 2학점 , 2시간) 목 4~5 (공학)
      • 영어강의,ABEEK
  • 2017-1학기

    • 컴퓨터프로그래밍및실습 강의 계획서 상세보기

      • 학수번호 36339분반 01
      • 1학년 ( 3학점 , 3시간) 월 7~7 (공학A102) , 목 7~7 (공학A125)
      • 교수결정,ABEEK 삼성전자 SW, 수강대상: 휴먼기계바이오공학부 1학년
    • 응용수학및연습

      • 학수번호 36563분반 02
      • 2학년 ( 4학점 , 4.5시간) 월 5~5 (공학) , 수 4~5 (159)
      • 교수변경,교수결정,영어강의,ABEEK 화학신소재공학과 2학년 수강
학력

Stanford University Ph.D.(Mechanical Engineering)