Sun Young Park

University of Texas at Austin, Texas City, TX, United States

Are you Sun Young Park?

Claim your profile

Publications (15)19.32 Total impact

  • [show abstract] [hide abstract]
    ABSTRACT: This paper presents an automated video analysis framework for the detection of colonic polyps in optical colonoscopy. Our proposed framework departs from previous methods in that we include spatial frame-based analysis and temporal video analysis using time-course image sequences. We also provide a video quality assessment scheme including two measures of frame quality. We extract colon-specific anatomical features from different image regions using a windowing approach for intraframe spatial analysis. Anatomical features are described using an eigentissue model. We apply a conditional random field to model interframe dependences in tissue types and handle variations in imaging conditions and modalities. We validate our method by comparing our polyp detection results to colonoscopy reports from physicians. Our method displays promising preliminary results and shows strong invariance when applied to both white light and narrow-band video. Our proposed video analysis system can provide objective diagnostic support to physicians by locating polyps during colon cancer screening exams. Furthermore, our system can be used as a cost-effective video annotation solution for the large backlog of existing colonoscopy videos.
    IEEE transactions on bio-medical engineering 02/2012; 59(5):1408-18. · 2.15 Impact Factor
  • CSCW '12 Computer Supported Cooperative Work, Seattle, WA, USA, February 11-15, 2012; 01/2012
  • [show abstract] [hide abstract]
    ABSTRACT: There has been a growing interest in the HCI community to study Health, with particular focus in understanding healthcare practices and designing technologies to support and to enhance these practices. A majority of current health studies in HCI have focused on either clinical settings, such as hospitals and clinics, or non-clinical spaces, like patients' homes and senior centers. Yet, there has been little work investigating how patient care in clinical and non-clinical settings connect with each other. Building on the illness trajectory concept, this workshop aims to explore the interplay between, and the challenges and opportunities in designing healthcare technologies for bridging the clinical and the non-clinical settings, as well as their impact on the continuum of patient care.
    01/2012;
  • [show abstract] [hide abstract]
    ABSTRACT: Image-based camera motion estimation from video or still images is a difficult problem in the field of computer vision. Many algorithms have been proposed for estimating intrinsic camera parameters, detecting and matching features between images, calculating extrinsic camera parameters based on those features, and optimizing the recovered parameters with nonlinear methods. These steps in the camera motion inference process all face challenges in practical applications: locating distinctive features can be difficult in many types of scenes given the limited capabilities of current feature detectors, camera motion inference can easily fail in the presence of noise and outliers in the matched features, and the error surfaces in optimization typically contain many suboptimal local minima. The problems faced by these techniques are compounded when they are applied to medical video captured by an endoscope, which presents further challenges such as non-rigid scenery and severe barrel distortion of the images. In this paper, we study these problems and propose the use of prior probabilities to stabilize camera motion estimation for the application of computing endoscope motion sequences in colonoscopy. Colonoscopy presents a special case for camera motion estimation in which it is possible to characterize typical motion sequences of the endoscope. As the endoscope is restricted to move within a roughly tube-shaped structure, forward/backward motion is expected, with only small amounts of rotation and horizontal movement. We formulate a probabilistic model of endoscope motion by maneuvering an endoscope and attached magnetic tracker through a synthetic colon model and fitting a distribution to the observed motion of the magnetic tracker. This model enables us to estimate the probability of the current endoscope motion given previously observed motion in the sequence. We add these prior probabilities into the camera motion calculation as an additional penalty term in RANSAC to help reject improbable motion parameters caused by outliers and other problems with medical data. This paper presents the theoretical basis of our method along with preliminary results on indoor scenes and synthetic colon images.
    Proc SPIE 03/2011;
  • [show abstract] [hide abstract]
    ABSTRACT: With colonoscopy becoming a common procedure for individuals aged 50 or more who are at risk of developing colorectal cancer (CRC), colon video data is being accumulated at an ever increasing rate. However, the clinically valuable information contained in these videos is not being maximally exploited to improve patient care and accelerate the development of new screening methods. One of the well-known difficulties in colonoscopy video analysis is the abundance of frames with no diagnostic information. Approximately 40% - 50% of the frames in a colonoscopy video are contaminated by noise, acquisition errors, glare, blur, and uneven illumination. Therefore, filtering out low quality frames containing no diagnostic information can significantly improve the efficiency of colonoscopy video analysis. To address this challenge, we present a quality assessment algorithm to detect and remove low quality, uninformative frames. The goal of our algorithm is to discard low quality frames while retaining all diagnostically relevant information. Our algorithm is based on a hidden Markov model (HMM) in combination with two measures of data quality to filter out uninformative frames. Furthermore, we present a two-level framework based on an embedded hidden Markov model (EHHM) to incorporate the proposed quality assessment algorithm into a complete, automated diagnostic image analysis system for colonoscopy video.
    Proc SPIE 03/2011;
  • Soyoung Lee, Sun Young Park, Yunan Chen
    [show abstract] [hide abstract]
    ABSTRACT: Previous studies suggest that mobile phones could prevent many communication and information breakdowns that commonly occur in a hospital environment. However, the actual benefits of mobile phones in medical work remain unexplored. We studied mobile phone usage among nurses in an Emergency Department (ED). Surprisingly, mobile phones were not favored by our study participants. We found that mobile phones do not support essential characteristics of nursing work in ED because they lack support for group awareness, informative interruption, and role-based calling. The findings suggest that the design of mobile devices should support nurses' share of work responsibilities and the need for information transparency.
    Proceedings of the International Conference on Human Factors in Computing Systems, CHI 2011, Extended Abstracts Volume, Vancouver, BC, Canada, May 7-12, 2011; 01/2011
  • IEEE Trans. Med. Imaging. 01/2011; 30:867-878.
  • [show abstract] [hide abstract]
    ABSTRACT: This paper presents an automated semantic image analysis method for cervical cancerous lesion detection. We model colposcopic image semantics in a novel probabilistic manner using conditional random fields. We extract the anatomical structure of the cervix from colposcopic images, and identify and summarize different tissue types and their locations in an image semantics map. The conditional random field model uses the semantic information to model the unique optical properties of each tissue type and the diagnostic relationships between neighboring regions. We validate our method using clinical data from 48 patients, and the results demonstrate its diagnostic potential in detecting neoplastic areas. Our automated diagnostic approach has the potential to support or substitute for conventional colposcopy. Furthermore, our generalized framework can be applied to other cancers such as skin, oral and colon cancer.
    Semantic Computing (ICSC), 2010 IEEE Fourth International Conference on; 10/2010
  • [show abstract] [hide abstract]
    ABSTRACT: Digital colposcopy is a promising technology for the detection of cervical intraepithelial neoplasia. Automated analysis of colposcopic images could provide an inexpensive alternative to existing screening tools. Our goal is to develop a diagnostic tool that can automatically identify neoplastic tissue from digital images. A multispectral digital colposcope (MDC) is used to acquire reflectance images of the cervix with white light before and after acetic-acid application in 29 patients. A diagnostic image analysis tool is developed to identify neoplasia in the digital images. The digital image analysis is performed in two steps. First, similar optical patterns are clustered together. Second, classification algorithms are used to determine the probability that these regions contain neoplastic tissue. The classification results of each patient's images are assessed relative to the gold standard of histopathology. Acetic acid induces changes in the intensity of reflected light as well as the ratio of green to red reflected light. These changes are used to differentiate high-grade squamous intraepithelial (HGSIL) and cancerous lesions from normal or low-grade squamous intraepithelial (LGSIL) tissue. We report diagnostic performance with a sensitivity of 79% and a specificity of 88%. We show that diagnostically useful digital images of the cervix can be obtained using a simple and inexpensive device, and that automated image analysis algorithms show a potential to identify histologically neoplastic tissue areas.
    Journal of Biomedical Optics 01/2008; 13(1):014029. · 2.88 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: The diagnostic ability of algorithms developed for the Multispectral Digital Colposcope (MDC) is highly dependent on the quality of the image. The field of objective medical image quality analysis has great potential but has not been well exploited. Various researchers have reported different measures of image quality but with an existence of a reference image. The quality of an image can be attributed to several sources of errors, a few of which would be inclusion of presence of extraneous components, improper illumination, or an image out of focus. This can be due to motion artifact or the region of interest out of the focal plane. With spectroscopic measurements, assessment of data quality has been used by our group in the past to avoid hardware errors at the time of acquisition. We are currently developing algorithms that will help identify hardware and acquisition errors to the clinician in under a few seconds. Minimizing these errors not only provides quality images for a diagnostic algorithm, but reduces the necessity for complex and time intensive post-processing software for enhancing the images. We propose a no reference image quality system specifically designed for MDC that can be modified to similar spectroscopic imaging applications.
    Gynecologic Oncology 11/2007; 107(1 Suppl 1):S215-22. · 3.93 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: An effective cancer control strategy requires improved early detection methods, patient-specific drug selection, and the ability to assess response to targeted therapeutics. Recently, plasmon resonance coupling between closely spaced metal nanoparticles has been used to develop ultrasensitive bioanalytical assays in vitro. We demonstrate the first in vivo application of plasmon coupling for molecular imaging of carcinogenesis. We describe molecular-specific gold bioconjugates to image epidermal growth factor receptor (EGFR); these conjugates can be delivered topically and imaged noninvasively in real time. We show that labeling with gold bioconjugates gives information on the overexpression and nanoscale spatial relationship of EGF receptors in cell membranes, both of which are altered in neoplasia. EGFR-mediated aggregation of gold nanoparticles in neoplastic cells results in more than a 100-nm color shift and a contrast ratio of more than tenfold in images of normal and precancerous epithelium in vivo, dramatically increasing contrast beyond values reported previously for antibody-targeted fluorescent dyes.
    Journal of Biomedical Optics 01/2007; 12(3):034007. · 2.88 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Fluorescence spectroscopy is a promising technology for the detection of cervical squamous intraepithelial precancers and cancers. To date, many investigators have focused on point spectroscopy as an adjunct to diagnostic colposcopy. A device that visualizes the whole field of the cervix is needed for screening. To that end, we have developed a multispectral digital colposcope that works through the colposcope to image with white light, UV excitation at 345 nm, and blue light at 440 nm excitation. Here, we report the pilot study that precedes a Phase I trial. The MDC system is composed of a light source, a colposcope, and a video rate color CCD camera with a frame grabber and takes approximately less than 1 min to make images of the cervix. Patients were measured at baseline and after acetic acid placement with white light, 345 nm excitation, and 440 nm excitation from the xenon arc lamp. The white light is in the visible spectrum, 345 nm excitation is in the UV spectrum and is not visible, and 440 nm excitation is blue light in the visible spectrum. White light generates a pink image of the cervix. 345 nm excitation, the UV light, excites fluorophores to emit a blue image. 440 nm excitation, the blue light, excites fluorophores to emit a green image. The patients underwent a loop excision procedure and the histopathology was inked and cut into 12 sections by the study pathologists. The histopathologic slides were scanned and the images were then reconstructed into maps. A diagnostic algorithm was calculated. The data were preprocessed, transformed, and analyzed by the K-means clustering method. Disease maps were generated using the algorithm and classifier and compared to white light colposcopy and the blue and green images obtained at 345 and 440 nm. Forty-six patients were measured at four clinical sites. Images were made of the cervix with white light, 345 nm excitation, and 440 nm excitation and are presented in the figures. As the study went on, images improved with improvements in the instrument. The white light and fluorescence images are presented with crudely constructed histopathologic maps and algorithmic maps. At 345 nm excitation, the UV light, histologically confirmed CIN appears darker blue; while at 440 nm excitation, the blue light, histologically confirmed CIN appears lighter green. This pilot study shows that MDC images can be matched to both histopathologic and algorithmic maps. The device and the algorithm are evolving but show promise. A Phase I trial is planned.
    Gynecologic Oncology 01/2006; 99(3 Suppl 1):S67-75. · 3.93 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In this study we use a multi-spectral digital microscope (MDM) to measure multi-spectral auto-fluorescence and reflectance images of the hamster cheek pouch model of DMBA (dimethylbenz[alpha]anthracene)- induced oral carcinogenesis. The multi-spectral images are analyzed both in the RGB (red, green, blue) color space as well as in the YCbCr (luminance, chromatic minus blue, chromatic minus red) color space. Mean image intensity, standard deviation, skewness, and kurtosis are selected as features to design a classification algorithm to discriminate normal mucosa from neoplastic tissue. The best diagnostic performance is achieved using features extracted from the YCbCr space, indicating the importance of chromatic information for classification. A sensitivity of 96% and a specificity of 84% were achieved in separating normal from abnormal cheek pouch lesions. The results of this study suggest that a simple and inexpensive MDM has the potential to provide a cost-effective and accurate alternative to standard white light endoscopy.
    Optics Express 03/2005; 13(3):749-62. · 3.55 Impact Factor
  • Sun Young Park, Yunan Chen
    [show abstract] [hide abstract]
    ABSTRACT: We conducted an observational study in an Emergency Department (ED) to examine the adaptation process after deploying an Electronic Medical Records (EMR) system. We investigated how EMR was adapted to the complex clinical work environment and how doctors and nurses engaged in the adaptation process. In this paper, we present three cases in which ED clinicians designed workarounds in order to adapt to the new work practice. Our findings reveal a rich picture of ED clinicians' active reinterpretation and modification of their work practice through their engagement with the system-in-use and its organizational and physical context. These findings call for the adaptation period in designing a socio-technical system in healthcare settings to be critically considered as an active end-user design process, a negotiating process, and a re-routinized process.
  • Source
    Sun Young Park
    [show abstract] [hide abstract]
    ABSTRACT: Not available Biomedical Engineering