BIOGRAPHICAL SKETCH

Provide the following information for the Senior/key personnel and other significant contributors.

Follow this format for each person. DO NOT EXCEED FIVE PAGES.

EDUCATION/TRAINING (Begin with baccalaureate or other initial professional education, such as nursing, include postdoctoral training and residency training if applicable. Add/delete rows as necessary.)

A. Personal Statement

I have always been interested in medical informatics. This was the reason I pursued my specialty in radiology. Few specialties are as dependent on computers and software. My research interest is in the application of machine learning to develop tools to assist radiologists. I’m hopeful that machine learning will bring about a wave of technological advances that will profound affect how radiology will be practiced in the future. My training in Electrical Engineering has provided me with the technical background to feel comfortable with machine learning, a field that requires programming and linear algebra. Hence, as deep learning techniques gain popularity in radiology research, I was able to climb the learning curve with relative ease. One of my research work that I have successfully applied machine learning is on the use of Spectral Detector Computed Tomography (SDCT) for segmentation of the liver. The project won an award at a national meeting and led to a publication. I’ve also taken interest in data science competitions. I have led a team to represent my institution in the last three RSNA machine learning challenges, and was awarded Kaggle silver medals in each of them. In the last competition on pulmonary embolism detection, my team achieved our best results yet and was placed 14^th position out of 784 teams. My dual expertise in machine learning and radiology will be useful to this project, one that explores the use of machine learning for a radiology application.

1. Ng YS, Xi Y, Qian Y, Ananthakrishnan L, Soesbe TC, Lewis M, Lenkinski R, Fielding JR. Use of Spectral Detector Computed Tomography to Improve Liver Segmentation and Volumetry. J Comput Assist Tomogr. 2020 Mar/Apr;44(2):197-203. doi: 10.1097/RCT.0000000000000987. PMID: 32195798.
2. O’Neill, T. J., Xi, Y., Stehel, E., Browning, T., Ng, YS., Baker, C., & Peshock, R. M. Active Reprioritization of the Reading Worklist Using Artificial Intelligence Has a Beneficial Effect on the Turnaround Time for Interpretation of Head CTs with Intracranial Hemorrhage. Radiology: Artificial Intelligence, 0(ja), e200024. doi:10.1148/ryai.2020200024
3. Browning T, O'Neill T, Ng Y, Fielding JR, Peshock RM. Special Considerations for Integrating Artificial Intelligence Solutions in Urban Safety-Net Hospitals. J Am Coll Radiol. 2020 Jan;17(1 Pt B):171-174. doi: 10.1016/j.jacr.2019.08.016. PMID: 31918876.
4. Ng YS., Ananthakrishnan L. Imaging of the Gallbladder with Multi-energy CT. Curr Radiol Rep 6, 46 (2018). https://doi.org/10.1007/s40134-018-0305-5
5. Akrawinthawong K, Leelasinjaroen P, Ng YS, Dean MN, Piyaskulkaew C, Al-najafi S, Mazimba SE. Seizure-induced acute coronary syndrome: the value of postictal screening. Am J Emerg Med. 2014 Dec;32(12):1538-43. PubMed PMID: 25440003.
6. Ng YS, Roca H, Fuller D, Sud S, Pienta KJ. Chemical transfection of dye-conjugated microRNA precursors for microRNA functional analysis of M2 macrophages. J Cell Biochem. 2012 May;113(5):1714-23. PubMed PMID: 22213010; PubMed Central PMCID: PMC3681413.
7. Gregory J, Ng Y, Jung EM, Kodandaramaiah S. Dielectric Whole Blood Separation Device Integrating a Spiral Pump and Cytometry. The sixth IEEE conference on sensors. 2007; :736-739.

B. Positions and Honors

Positions and Employment

2018-            Assistant Professor of Radiology, UT Southwestern Medical Center

2018-            Deputy CMIO of Radiology, UT Southwestern Medical Center

Other Experience and Professional Memberships

Honors

C. Contribution to Science

1. Wrote a custom software as a pyOsiriX plugin to OsiriX DICOM viewer. The plugin performs semiautomatic segmentation of the liver based on Spectral Detector CT (SDCT) data. This plugin demonstrated superior segmentation performance compared to segmentation using conventional CT attenuation. This work was presented as an electronic poster presentation presented at SAR annual meeting 2018, won the Power Science Merit award, and led to a publication in JCAT.

1. Ng YS, Xi Y, Qian Y, Ananthakrishnan L, Soesbe TC, Lewis M, Lenkinski R, Fielding JR. Use of Spectral Detector Computed Tomography to Improve Liver Segmentation and Volumetry. J Comput Assist Tomogr. 2020 Mar/Apr;44(2):197-203. doi: 10.1097/RCT.0000000000000987. PMID: 32195798.

2. Created and wrote a custom software to analyze multi-echo GRE MRI images of the liver to calculate R2* and estimate liver iron concentration. This work was presented as a poster at SCBTMR Annual Meeting.
   1. Ng Y, Pedrosa I, Yokoo T. Real-Time Interactive R2* Fitting of Multiecho GRE Liver MRI Using PACS Extension Software. Society of Computed Body Tomography and Magnetic Resonance 2015 Annual Meeting; 2015 October 10; Toronto, Ontario, Canada.
3. This work was done as part of a larger project to study Tumor associated macrophages. Tumor associated macrophages are known to be difficult to transfect. To facilitate studying microRNAs and how they influence differentiation of tumor associated macrophages, I compared different ways of transfecting microRNA precursors into peripheral blood monocytes, and determined the best way to perform the task. As a sub-project I have written a python script to compare three different databases of predicted microRNA targets.
   1. Ng YS, Roca H, Fuller D, Sud S, Pienta KJ. Chemical transfection of dye-conjugated microRNA precursors for microRNA functional analysis of M2 macrophages. J Cell Biochem. 2012 May;113(5):1714-23. PubMed PMID: 22213010; PubMed Central PMCID: PMC3681413.

D. Additional Information: Research Support and/or Scholastic Performance

Research Support

Ongoing Research Support

None

Completed Research Support

None