Dr. Subok Park Profile

Dr. Subok Park

Director of Clinical Strategy

Area of Expertise:

Regulatory Strategy for AI/ML-based Software As a Medical Device , Clinical Reader Study Design , Breast Imaging Evaluation , Model Observer Design , Real World Data , Real World Evidence

Websites:

Company Website

Publications (24)

Proceedings Article | 10 March 2017 Presentation + Paper

Presentation + Paper

Digital breast tomosynthesis for detecting multifocal and multicentric breast cancer: influence of acquisition geometry on model observer performance in breast phantom images

Gezheng Wen, Subok Park, Mia Markey

Proceedings Volume 10136, 101360V (2017) https://doi.org/10.1117/12.2254193

KEYWORDS: Digital breast tomosynthesis, Breast, 3D modeling, Breast cancer, Signal detection, X-rays, Image quality, Signal to noise ratio, 3D image processing, Lab on a chip, Tumors, Magnetic resonance imaging

Read Abstract +

Multifocal and multicentric breast cancer (MFMC), i.e., the presence of two or more tumor foci within the same breast, has an immense clinical impact on treatment planning and survival outcomes. Detecting multiple breast tumors is challenging as MFMC breast cancer is relatively uncommon, and human observers do not know the number or locations of tumors a priori. Digital breast tomosynthesis (DBT), in which an x-ray beam sweeps over a limited angular range across the breast, has the potential to improve the detection of multiple tumors.^{1, 2} However, prior efforts to optimize DBT image quality only considered unifocal breast cancers (e.g.,^3-9), so the recommended geometries may not necessarily yield images that are informative for the task of detecting MFMC. Hence, the goal of this study is to employ a 3D multi-lesion (ml) channelized-Hotelling observer (CHO) to identify optimal DBT acquisition geometries for MFMC. Digital breast phantoms and simulated DBT scanners of different geometries (e.g., wide or narrow arc scans, different number of projections in each scan) were used to generate image data for the simulation study. Multiple 3D synthetic lesions were inserted into different breast regions to simulate MF cases and MC cases. 3D partial least squares (PLS) channels, and 3D Laguerre-Gauss (LG) channels were estimated to capture discriminant information and correlations among signals in locally varying anatomical backgrounds, enabling the model observer to make both image-level and location-specific detection decisions. The 3D ml-CHO with PLS channels outperformed that with LG channels in this study. The simulated MC cases and MC cases were not equally difficult for the ml-CHO to detect across the different simulated DBT geometries considered in this analysis. Also, the results suggest that the optimal design of DBT may vary as the task of clinical interest changes, e.g., a geometry that is better for finding at least one lesion may be worse for counting the number of lesions.

Proceedings Article | 24 March 2016 Paper

Paper

Model observer design for detecting multiple abnormalities in anatomical background images

Gezheng Wen, Mia Markey, Subok Park

Proceedings Volume 9787, 97870S (2016) https://doi.org/10.1117/12.2217665

KEYWORDS: Tumor growth modeling, Performance modeling, Image analysis, Medical imaging, Image quality, Lab on a chip, Signal to noise ratio, Mammography, Neptunium

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Paper

Investigation on location-dependent detectability of a small mass for digital breast tomosynthesis evaluation

Changwoo Lee, Jongduk Baek, Subok Park

Proceedings Volume 9787, 97870V (2016) https://doi.org/10.1117/12.2216579

KEYWORDS: Digital breast tomosynthesis, Breast cancer, Image quality, Signal detection, Signal attenuation, 3D modeling, Breast, Data modeling, Reconstruction algorithms, Sensors, Thallium

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Paper

Effect of anatomical backgrounds on detectability in volumetric cone beam CT images

Minah Han, Subok Park, Jongduk Baek

Proceedings Volume 9787, 978717 (2016) https://doi.org/10.1117/12.2214689

KEYWORDS: Signal detection, Computed tomography, Medical imaging, Reconstruction algorithms, Signal to noise ratio, Sensors, Tissues

Read Abstract +

Proceedings Article | 22 March 2016 Paper

Paper

Eigenbreasts for statistical breast phantoms

Gregory Sturgeon, Daniel Tward, M. Ketcha, J. Ratnanather, M. Miller, Subok Park, W. Segars, Joseph Lo

Proceedings Volume 9783, 97832B (2016) https://doi.org/10.1117/12.2216398

KEYWORDS: Breast, Breast imaging, Principal component analysis, Mammography, Clinical trials, Statistical modeling, Optimization (mathematics), Statistical analysis, Computed tomography, Data modeling, Medical imaging, Image segmentation, 3D modeling

Read Abstract +

Proceedings Article | 11 March 2014 Paper

Paper

Comparing observer models and feature selection methods for a task-based statistical assessment of digital breast tomsynthesis in reconstruction space

Subok Park, George Zhang, Rongping Zeng, Kyle Myers

Proceedings Volume 9037, 90370M (2014) https://doi.org/10.1117/12.2043598

KEYWORDS: Digital breast tomosynthesis, 3D modeling, Neptunium, Scanning probe lithography, Data modeling, Signal detection, Breast, Performance modeling, Statistical modeling, Binary data

Read Abstract +

Proceedings Article | 28 March 2013 Paper

Paper

Investigating the feasibility of using partial least squares as a method of extracting salient information for the evaluation of digital breast tomosynthesis

George Zhang, Kyle Myers, Subok Park

Proceedings Volume 8673, 867311 (2013) https://doi.org/10.1117/12.2008018

KEYWORDS: Digital breast tomosynthesis, Scanning probe lithography, Data modeling, Neptunium, 3D modeling, Nanolithography, Binary data, Signal detection, Tolerancing, Performance modeling

Read Abstract +

Proceedings Article | 19 March 2013 Paper

Paper

Two methods for simulation of dense tissue distribution in software breast phantoms

Joseph Chui, Rongping Zeng, David Pokrajac, Subok Park, Kyle Myers, Andrew Maidment, Predrag Bakic

Proceedings Volume 8668, 86680M (2013) https://doi.org/10.1117/12.2008104

KEYWORDS: Tissues, Breast, Computer simulations, Nipple, Chest, Breast cancer, Statistical analysis, Matrices, Mammography, Breast imaging

Read Abstract +

Proceedings Article | 3 March 2012 Paper

Paper

A mathematical framework for including various sources of variability in a task-based assessment of digital breast tomosynthesis

Subok Park, Andreu Badal, Stefano Young, Kyle Myers

Proceedings Volume 8313, 83134S (2012) https://doi.org/10.1117/12.911241

KEYWORDS: Convolution, Breast, Monte Carlo methods, X-rays, Sensors, Digital breast tomosynthesis, X-ray detectors, Quantum electronics, Computer simulations, Chest

Read Abstract +

Proceedings Article | 23 March 2010 Paper

Paper

Singular system analysis of breast tomosynthesis systems for choosing projection angles

Subok Park, Rongping Zeng, Kyle Myers

Proceedings Volume 7622, 762243 (2010) https://doi.org/10.1117/12.844237

KEYWORDS: Digital breast tomosynthesis, Imaging systems, Sensors, Optical spheres, Neptunium, Image processing, X-ray imaging, X-rays, Breast, Medical imaging

Read Abstract +

Proceedings Article | 14 March 2009 Paper

Paper

Noise and signal detection in digital x-ray detectors using the spatial definition of SNR

Iacovos Kyprianou, Aldo Badano, Subok Park, Haimo Liu, Kyle Myers

Proceedings Volume 7258, 725819 (2009) https://doi.org/10.1117/12.813843

KEYWORDS: Signal to noise ratio, Sensors, Imaging systems, Modulation transfer functions, Interference (communication), Quantum electronics, Signal detection, X-ray detectors, Digital x-ray imaging, Arteries

Read Abstract +

Proceedings Article | 14 March 2009 Paper

Paper

Estimating breast tomosynthesis performance in detection tasks with variable-background phantoms

Stefano Young, Subok Park, S. Kyle Anderson, Aldo Badano, Kyle Myers, Predrag Bakic

Proceedings Volume 7258, 72580O (2009) https://doi.org/10.1117/12.813900

KEYWORDS: Digital breast tomosynthesis, Breast, Sensors, Imaging systems, Performance modeling, Mathematical modeling, Data modeling, Tumors, X-rays, Tissues

Read Abstract +

Digital breast tomosynthesis (DBT) shows potential for improving breast cancer detection. However, this technique has not yet been fully characterized with consideration of the various uncertainties in the imaging chain and optimized with respect to system acquisition parameters. To obtain maximum diagnostic information in DBT, system optimization needs to be performed across a range of patients and acquisition parameters to quantify their impact on tumor detection performance. In addition, a balance must be achieved between x-ray dose and image quality to minimize risk to the patient while maximizing the system's detection performance. To date, researchers have applied a task-based approach to the optimization of DBT with use of mathematical observers for tasks in the signal-known-exactly background-known-exactly (SKE/BKE) and signal-known-exactly background-known statistically (SKE/BKS) paradigms1-3. However, previous observer models provided insufficient treatment of the spatial correlations between multi-angle DBT projections, so we incorporated this correlation information into the modeling methodology. We developed a computational approach that includes three-dimensional variable background phantoms for incorporating background variability, accurate ray-tracing and Poisson distributions for generating noise-free and noisy projections of the phantoms, and a channelized-Hotelling observer4 (CHO) for estimating performance in DBT. We demonstrated our method for a DBT acquisition geometry and calculated the performance of the CHO with Laguerre-Gauss channels as a function of the angular span of the system. Preliminary results indicate that the implementation of a CHO model that incorporates correlations between multi-angle projections gives different performance predictions than a CHO model that ignores multi-angle correlations. With improvement of the observer design, we anticipate more accurate investigations into the impact of multi-angle correlations and background variability on the performance of DBT.

Proceedings Article | 13 March 2009 Paper

Paper

Using partial least squares to compute efficient channels for the Bayesian ideal observer

Joel Witten, Subok Park, Kyle Myers

Proceedings Volume 7263, 72630Q (2009) https://doi.org/10.1117/12.813550

KEYWORDS: Image quality, Imaging systems, Binary data, Algorithm development, Medical imaging, Image analysis, Signal detection, Computing systems, Receivers, Imaging devices

Read Abstract +

Proceedings Article | 13 March 2009 Paper

Paper

A task-based evaluation method for x-ray breast imaging systems using variable-background phantoms

Subok Park, Haimo Liu, Robert Jennings, Robert Leimbach, Iacovos Kyprianou, Aldo Badano, Kyle Myers

Proceedings Volume 7258, 72581L (2009) https://doi.org/10.1117/12.813572

KEYWORDS: Imaging systems, X-rays, X-ray imaging, 3D image processing, Signal to noise ratio, Breast imaging, Mammography, Signal detection, Breast, Optical spheres

Read Abstract +

Proceedings Article | 11 March 2009 Paper

Paper

SKE/BKE task-based methodology for calculating Hotelling observer SNR in mammography

Haimo Liu, Iacovos Kyprianou, Aldo Badano, Kyle Myers, Robert Jennings, Subok Park, Richard Kaczmarek, Kish Chakrabarti

Proceedings Volume 7258, 72581D (2009) https://doi.org/10.1117/12.813833

KEYWORDS: Signal to noise ratio, Sensors, Imaging systems, Mammography, Signal detection, Polymethylmethacrylate, X-rays, X-ray detectors, Interference (communication), Laser range finders

Read Abstract +

Proceedings Article | 24 March 2008 Paper

Paper

Singular vectors of a linear imaging system as efficient channels for the ideal observer in detection tasks involving non-Gaussian distributed lumpy images

Joel Witten, Subok Park, Kyle Myers

Proceedings Volume 6917, 69170U (2008) https://doi.org/10.1117/12.772054

KEYWORDS: Imaging systems, Signal detection, Binary data, Medical imaging, Image quality, Interference (communication), Diagnostics, Algorithm development, Data modeling, Matrices

Read Abstract +

Proceedings Article | 24 March 2008 Paper

Paper

Markov-chain Monte Carlo for the performance of a channelized-ideal observer in detection tasks with non-Gaussian lumpy backgrounds

Subok Park, Eric Clarkson

Proceedings Volume 6917, 69170T (2008) https://doi.org/10.1117/12.771704

KEYWORDS: Monte Carlo methods, Imaging systems, Statistical analysis, Binary data, Signal detection, Medical imaging, Interference (communication), Error analysis, Diagnostics, Receivers

Read Abstract +

Proceedings Article | 20 March 2007 Paper

Paper

A contrast-sensitive channelized-Hotelling observer to predict human performance in a detection task using lumpy backgrounds and Gaussian signals

Subok Park, Aldo Badano, Brandon Gallas, Kyle Myers

Proceedings Volume 6515, 65150V (2007) https://doi.org/10.1117/12.708582

KEYWORDS: Contrast sensitivity, Signal detection, Performance modeling, Visual system, Visual process modeling, Spatial frequencies, Imaging systems, Image processing, Medical imaging, Mathematical modeling

Read Abstract +

Proceedings Article | 8 March 2007 Paper

Paper

Effect of slow display on stack-mode reading of volumetric image datasets using an anthropomorphic observer

Hongye Liang, Subok Park, Brandon Gallas, Aldo Badano

Proceedings Volume 6515, 65150W (2007) https://doi.org/10.1117/12.708993

KEYWORDS: LCDs, Medical imaging, Signal detection, Computed tomography, Image quality, 3D volumetric displays, Contrast sensitivity, Performance modeling, Time metrology, Medical imaging applications

Read Abstract +

Proceedings Article | 17 March 2006 Paper

Paper

Human efficiency for detecting Gaussian signals in non-Gaussian distributed lumpy backgrounds using different display characteristics and scaling methods

Subok Park, Brandon Gallas, Aldo Badano, Nicholas Petrick, Kyle Myers

Proceedings Volume 6146, 61460Q (2006) https://doi.org/10.1117/12.653902

KEYWORDS: Signal detection, Error analysis, Medical imaging, LCDs, Imaging systems, Statistical analysis, Receivers, Image processing, Algorithm development, Calibration

Read Abstract +

Proceedings Article | 17 March 2006 Paper

Paper

Performance of a channelized-ideal observer using Laguerre-Gauss channels for detecting a Gaussian signal at a known location in different lumpy backgrounds

Subok Park, Eric Clarkson, Harrison Barrett, Matthew Kupinski, Kyle Myers

Proceedings Volume 6146, 61460P (2006) https://doi.org/10.1117/12.653931

KEYWORDS: Signal detection, Monte Carlo methods, Medical imaging, Image quality, Imaging systems, Computer simulations, Statistical analysis, Signal to noise ratio, Quality measurement, Image classification

Read Abstract +

Proceedings Article | 2 March 2006 Paper

Paper

A practical method for measuring the H matrix of digital x-ray and cone beam CT imaging systems

Iacovos Kyprianou, Aldo Badano, Brandon Gallas, Subok Park, Kyle Myers

Proceedings Volume 6142, 61421U (2006) https://doi.org/10.1117/12.654374

KEYWORDS: Sensors, Imaging systems, X-rays, X-ray imaging, X-ray detectors, Calibration, Scintillators, Image sensors, Convolution, Ytterbium

Read Abstract +

Proceedings Article | 6 April 2005 Paper

Paper

Efficiency of human and model observers for signal-detection tasks in non-Gaussian distributed lumpy backgrounds

Subok Park, Eric Clarkson, Matthew Kupinski, Harrison Barrett

Proceedings Volume 5749, (2005) https://doi.org/10.1117/12.592238

KEYWORDS: Signal detection, Imaging systems, Image processing, Statistical analysis, Systems modeling, Signal to noise ratio, Monte Carlo methods, Image quality, Medical imaging, Mathematical modeling

Read Abstract +

Proceedings Article | 4 May 2004 Paper

Paper

Efficient channels for the ideal observer

Subok Park, Matthew Kupinski, Eric Clarkson, Harrison Barrett

Proceedings Volume 5372, (2004) https://doi.org/10.1117/12.531614

KEYWORDS: Imaging systems, Signal detection, Californium, Monte Carlo methods, Image processing, Numerical analysis, Medical imaging, Performance modeling, Statistical analysis, Fourier transforms

Read Abstract +

Showing 5 of 24 publications

Conference Committee Involvement (3)

Image Perception, Observer Performance, and Technology Assessment

2 March 2016 | San Diego, California, United States

Image Perception, Observer Performance, and Technology Assessment

25 February 2015 | Orlando, Florida, United States

Image Perception, Observer Performance, and Technology Assessment

16 February 2014 | San Diego, California, United States

SIGN IN TO:

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Advertisement

Advertisement