Wookjin Choi, Ph.D.


Post Doctoral Fellow, Physics
Department of Radiation Oncology
University of Maryland School of Medicine

Tel.: +1-410-706-6513
Mobile: +1-443-255-5481
Email: wchoi1022@gmail.com



Work Experience


2014.7 ~ present

University of Maryland School of Medicine, Baltimore, MD, USA.

(Post Doctoral Fellow - Department of Radiation Oncology, Physics)


2013.8 ~ 2014.7

Gwangju Institute of Science and Technology (GIST), Gwangju, Korea.

(Research Fellow - School of Mechatronics)



Education


2008.3 ~ 2013.8

Gwangju Institute of Science and Technology (GIST), Gwangju, Korea.

(Ph.D. - School of Mechatronics)

2006.9 ~ 2008.2

GIST Gwangju, Korea.

(M.S. - School of Information & Mechatronics)

2002.3 ~ 2006.8

Korea University of Technology and Education (KoreaTech), Cheonan, Korea.

(B.S. - School of Computer Science and Engineering)



Research Area

  1. Medical Image Analysis

  2. Computer Vision

  3. Pattern Recognition




Research Grant

  1. 2013 ~ 2016, 3D Image Analysis for Computer Aided Diagnosis in Lung CT Image, Basic Science Research Program, National Research Foundation of Korea (No. NRF-2013R1A1A2058113)




Publication [Google scholar][Scopus]

  1. International Journal

  2. 1.Wook-Jin Choi, Tae-Sun Choi, “Automated Pulmonary Nodule Detection based on Three-dimensional Shape-based Feature Descriptor”, Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, January 2014, pp. 37–54, doi: http://dx.doi.org/10.1016/j.cmpb.2013.08.015

  3. In pulmonary nodule CAD systems, feature extraction is very important for describing the characteristics of nodule candidates. In this paper, we propose a novel three-dimensional shape-based feature descriptor to detect pulmonary nodules in CT scans. After lung volume segmentation, nodule candidates are detected using multi-scale dot enhancement filtering in the segmented lung volume. Next, we extract feature descriptors from the detected nodule candidates, and these are refined using an iterative wall elimination method. Finally, a support vector machine-based classifier is trained to classify nodules and non-nodules.



  
  
  


  1. 2.Wook-Jin Choi, Tae-Sun Choi, “Automated Pulmonary Nodule Detection System in Computed Tomography Images: A Hierarchical Block Classification Approach”, Entropy, Vol. 15, No. 2, pp. 507-523, February 2013, doi: http://dx.doi.org/10.3390/e15020507

  2. We propose a novel pulmonary nodule detection method based on hierarchical block classification. The proposed CAD system consists of three steps. In the first step, input computed tomography images are split into three-dimensional block images, and we apply entropy analysis on the block images to select informative blocks. In the second step, the selected block images are segmented and adjusted for detecting nodule candidates. In the last step, we classify the nodule candidate images into nodules and non-nodules. We extract feature vectors of the objects in the selected blocks. Lastly, the support vector machine is applied to classify the extracted feature vectors.



  3. 3.Wook-Jin Choi, Tae-Sun Choi, “Genetic programming-based feature transform and classification for the automatic detection of pulmonary nodules on computed tomography images”, Information Sciences, Vol. 212, pp. 57-78, December 2012, doi: http://dx.doi.org/10.1016/j.ins.2012.05.008

  4. We propose a novel pulmonary nodule detection system based on a genetic programming (GP)-based classifier. The proposed system consists of three steps. In the first step, the lung volume is segmented using thresholding and 3D-connected component labeling. In the second step, optimal multiple thresholding and rule-based pruning are applied to detect and segment nodule candidates. In this step, a set of features is extracted from the detected nodule candidates, and essential 3D and 2D features are subsequently selected. In the final step, a GP-based classifier (GPC) is trained and used to classify nodules and non-nodules. GP is suitable for detecting nodules because it is a flexible and powerful technique; as such, the GPC can optimally combine the selected features, mathematical functions, and random constants.

  5.  
     
     


  6. 4.M.T. Mahmood, Wook-Jin Choi, Tae-Sun Choi, “PCA-Based Method for 3-D Shape Recovery of Microscopic Objects From Image Focus Using Discrete Cosine Transform”, Microscopy Research and Technique, Vol. 71, No. 12, pp. 897-907, December 2008. doi: http://dx.doi.org/10.1002/jemt.20635

  7. This article introduces a new algorithm for shape from focus (SFF) based on discrete cosine transform (DCT) and principal component analysis (PCA). DCT is applied on a small 3D neighborhood for each pixel in the image volume. Instead of summing all focus values in a window, AC parts of DCT are collected and then PCA is applied to transform this data into eigenspace. The first feature, containing maximum variation is employed to compute the depth. DCT and PCA are computationally intensive; however, the reduced data elements and algorithm iterations have made the new approach competitive and efficient.






  1. Domestic Journals

  2. 1.Wook-Jin Choi, Tae-Sun Choi, “Log-polar Sampling based Voxel Classification for Pulmonary Nodule Detection in Lung CT scans”, Journal of Korean Institute of Information, Electronics and Communication Technology, Vol. 6, No. 1, pp. 37-44, April 2013

  3. 2.Wook-Jin Choi, Tae-Sun Choi, “Pulmonary Nodule Detection based on Hierarchical 3D Block Analysis in Chest CT scans”, Journal of Korean Institute of Information, Electronics and Communication Technology, Vol. 5, No. 1, pp.13-19, April 2012

  4. 3.Wook-Jin Choi, Mannan Saeed Muhammad, Tae-Sun Choi, "3D Shape Recovery Algorithm with Reduction of 3D Spatial Complexity", Journal of Korean Institute of Information Technology, Vol. 6, No. 4, pp.108-114, August 2008.


  1. International Conference

  2. 1.Wook-Jin Choi, Ayyaz Hussain, Ik-Hyun Lee, Tae-Sun Choi, “Automatic Detection of Pulmonary Nodules based on Optimal Fuzzy Rules”, US-Korea Conference on Science, Technology, and Entrepreneurship (UKC), East Ruderford, NJ, USA, Aug. 9, 2013.

  3. 2.M. Arfan Jaffar, Wook-Jin Choi, Tae-Sun Choi, “Classification of pulmonary Nodule from Low Dose CT Scan Images using Neural Networks”, Advanced Signal Processing 2012, Seoul, Korea, March 2012.  

  4. 3.M.T.Mahmood, Ik-Hyun Lee, Wook-Jin Choi, Tae-Sun Choi, "A Nonlinear Approach for Depth From Focus for Digital Cameras", IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, January 2011.

  5. 4.Wook-Jin Choi, Tae-Sun Choi, “Computer-aided detection of pulmonary nodules using genetic programming”, IEEE International Conference on Image Processing (ICIP), Hong Kong, pp. 4353-4356, September 2010.

  6. 5.Wook-Jin Choi, Tae-Sun Choi, “False positive reduction for pulmonary nodule detection using two-dimensional principal component analysis”, SPIE Optics + Photonics, San Diego, CA, USA, August 2009.

  7. 6.Wook-Jin Choi, A.Majid, Tae-Sun Choi, “Computerized Detection of Pulmonary Nodule based on Two-Dimensional PCA”, International Conference on Computational Science and Its Applications (ICCSA), Suwon, Korea, June 2009.

  8. 7.M.T. Mahmood, Wook-Jin Choi, Tae-Sun Choi, “DCT and PCA based method for shape from focus”, ICCSA, Perugia, Italy, July 2008.

  9. 8.Wook-Jin Choi, Tae-Sun Choi, “Fast three-dimensional shape recovery in TFT-LCD manufacturing”, SPIE Optics + Photonics, San Diego, CA, USA, August 2008.


  1. Domestic Conferences

  2. 1.Wook-Jin Choi, Tae-Sun Choi, “Statistical Shape Model based Three Dimensional Shape Modeling for Knee Joint on Magnetic Resonance Images”, Korean Institute of Information Technology (KIIT) Conference, pp. 461-465, November 2012.

  3. 2.Wook-Jin Choi, Tae-Sun Choi, “Pulmonary Nodule Detection using Voxel Classification in Lung CT scans”, Korean Institute of Information, Electronics and Communication Technology (KIIECT) Conference, pp. 152-155, May 2012.

  4. 3.Wook-Jin Choi, Tae-Sun Choi, “Pulmonary Structures Segmentation and Nodule Detection using 3D Block Analysis of Chest CT scans”, KIIECT Conference, pp. 197-200, October 2011.

  5. 4.Wook-Jin Choi, Tae-Sun Choi, “Pulmonary Nodule Candidate Detection using Modified Circular Hough Transform”, KIIT Conference, pp. 8-11, May 2011.

  6. 5.Wook-Jin Choi, Tae-Sun Choi, " Pulmonary Nodule Detection using Genetic Programming", KIIECT Conference, pp.100-103, Vol.3, No.2, October 2010.

  7. 6.Wook-Jin Choi, Ik-Hyun Lee, Tae-Sun Choi, “Adaptive Lung Region Segmentation using Graph-cuts”, KIIT Conference, pp. 7-10, May 2010.

  8. 7.Wook-Jin Choi, Tae-Sun Choi, “False Positive Reduction in Pulmonary Nodule Detection using Principal Component Analysis”, KIIT Conference, pp. 202-207, June. 2009.

  9. 8.Wook-Jin Choi, Tae-Sun Choi, “Pulmonary Nodule Detection System based on 2DPCA”, Korea Information Technology Conference, 2008.

  10. 9.Wook-Jin Choi, Mannan Saeed Muhammad, Tae-Sun Choi, “3D Space Complexity Reducing Method for 3D Camera”, KIIT Conference, 2008.

  11. 10.Wook-Jin Choi, Tae-Sun Choi, “Three dimensional Shape Recovery for Measuring the Protrusion on Color Filter”, KIIT Conference, 2008.

  12. 11.Wook-Jin Choi, Mannan Saeed Muhammad, Minji Lee, Tae-Sun Choi, “Depth Measurement Using Pixel Intensities”, Institute of Electronics Engineers of Korea (IEEK) Conference, June 2008.

  13. 12.Wook-Jin Choi, Tae-Sun Choi, “Three Dimensional Shape Recovery for Measuring LCD Color Filter”, Workshop on Image Processing and Image Understanding, 2008.

  14. 13.Wook-Jin Choi, Seongeun Eom, Heegon Moon, Tae-Sun Choi, "Daphnia Tracking Algorithm for Monitoring Water Quality", Korea Signal Processing Conference, Daegu, Korea, October 2007.


  1. Patents

  2. 1.Korea Patent 10-1085949, “Apparatus for classifying a lung and a method thereof, capable of automatically determining the state of a lung”, Tae-Sun Choi, Wook-Jin Choi, Issued November 16, 2011

  3. 2.Korea Patent 10-1066468, “Method and device for discriminating a honeycombed lung from a normal lung and a computer readable recording medium”, Tae-Sun Choi, Wook-Jin Choi, Aamir Saeed Malik, Issued September 15, 2011

  4. 3.Korean Patent Application 10-2013-0127923, “Method and apparatus for generating 3-D knee joint image”, Tae-Sun Choi, Wook-Jin Choi, Filed October 10, 2013


Award

  1. 1.Best paper award, KIIECT, May 2012

  2. 2.2nd place in Dasan best student research award, GIST, 2012

  3. 3.Best presentation award, KIIT, 2011

  4. 4.Best paper award, KIIT, 2008


Scholarship

  1. 1.Dasan scholarship recipient, GIST, 2008

  2. 2.Brain Korea 21 scholarship recipient, GIST, 2006-2012

  3. 3.Korean government supported full scholarship recipient, GIST, 2006-2012

  4. 4.Brain Korea 21 scholarship recipient, Korea Tech, 2003-2005

  5. 5.Korea Tech scholarship recipient, Korea Tech, 2003-2005