NAME: Yi Gao

eRA COMMONS USER NAME (credential, e.g., agency login): yigao16

POSITION TITLE: Professor of Biomedical Engineering, Shenzhen University

?

EDUCATION/TRAINING

?

A. Personal Statement

I have a broad background in biomedical engineering with specific training and expertise in the medical image computing that is necessary to contribute to the proposed development. I will work on the development and deep learning for the analysis as well as the deployment under the GPU environment. I have developed and published on interactive image segmentation, classification, and morphology analysis algorithms supported by various NIH projects, such as the National Alliance of Medical Image Computing. The segmentation algorithm I developed and implemented into the 3D Slicer is the only segmentation module with flexible handling of the target fidelity and shape smoothness. This module webpage alone has been visited >40,000 times. I have been the founding co-chair of the Interactive Medical Image Computing workshop of the MICCAI conference. These achievements laid a solid technical foundation for our proposed work in this grant.

?

B. Positions and Honors

2013-2014 Assistant Professor, Department of Electrical and Computer Engineering, University of?Alabama at Birmingham, Birmingham, AL

2014- Assistant Professor, Department of Biomedical Informatics, Stony Brook University, Stony?Brook, NY

?

C. Contribution to Science

1. My research and publications address the problems of the accuracy and robustly extract the anatomical and/or functional structures from biomedical images (segmentation), with or without user interaction. In my research I proposed the novel framework of combining the statistical estimation theory together with the image segmentation. This approach significantly stabilizes and improves the segmentation performance. In addition to the algorithm design, I have integrated the algorithm and deployed the software module into the widely adopted medical image computing open source platform 3D Slicer. Being an end-user operable software, the web page of one module I developed (item c below) has been visited >40,000 times.

?

a. Gao, Y., Sandhu, R., Fichtinger, G., & Tannenbaum, A. R. (2010). A coupled global registration and?segmentation framework with application to magnetic resonance prostate imagery. Medical Imaging?IEEE Transactions on, 29(10), 1781-1794.

b. Gao, Y., Corn, B., Schifter, D. & Tannenbaum, A. (2012) Multiscale 3D shape representation and?segmentation with applications to hippocampal/caudate extraction from brain MRI. Medical image?analysis, 16(2),374–385

c. Gao, Y., Kikinis, R., Bouix, S., Shenton, M., & Tannenbaum, A. (2012). A 3D interactive multi-object?segmentation tool using local robust statistics driven active contours. Medical image analysis, 16(6),1216-1227.

d. Gao, Y., Bouix, S., Shenton, M., & Tannenbaum, A. (2013). Sparse Texture Active Contour. IEEE?transactions on image processing, 22(10), 3866.

e. Gao, Y., Zhu, L., Cates, J., MacLeod, R. S., Bouix, S., & Tannenbaum, A. (2015). A Kalman Filtering?Perspective for Multiatlas Segmentation. SIAM Journal on Imaging Sciences, 8(2), 1007-1029.

?

2. The analysis of different groups of shapes can reveal the localized morphometric differences between different populations. In the last two decades, the statistical analysis of shapes has become an actively studied field and finds applications in a wide range of areas. However, there is little work on the evaluation and validation of these techniques, which poses a rather serious challenge when interpreting their results. To address this lack of validation, we designed a validation framework and then used it to test some of the most widely used toolboxes. Our initial results showed inconsistencies and disagreement between four different methods. In addition, we have designed a new shape analysis algorithm that is the first to be thoroughly and quantitatively evaluated.

?

a. Gao, Y., Riklin‐Raviv, T., & Bouix, S. (2014). Shape analysis, a field in need of careful validation. Human?brain mapping., 35(10), 4965-4978

b. Riklin Raviv, T., Gao, Y., Levitt, J. J., & Bouix, S. (2014). Statistical Shape Analysis of Neuroanatomical?Structures via Level-Set--based Shape Morphing. SIAM Journal on Imaging Sciences, 7(3), 1645-1668.

c. Hong, Y., Gao, Y., Niethammer, M., & Bouix, S. (2015). Shape analysis based on depth-ordering. Medical?image analysis, 25(1), 2-10.

d. Gao, Y., & Bouix, S. (2016). Statistical Shape Analysis using 3D Poisson Equation—A Quantitatively?Validated Approach. Medical Image Analysis, 30:72-84

?

3. I have been actively studying new techniques and systems in image-guided therapy. I have proposed methods to align the pre-operative brain volume with the intra-operative volume in a non-linear fashion in order to address brain deformation. Moreover, inspired by the algorithm used in brain white matter fiber tracking, I have developed a tracking algorithm for needle detection in gynecological brachytherapy. In order to optimally identify the tumor boundary in brain tumor resection, we have designed a method that accelerates mass-spectroscopy imaging that not only reduces the intra-operative data acquisition time to 1/3, but also provides probabilistic estimation of the underlying tissue type. This algorithm and system is being tested in the Advanced Multimodality Image Guided Operating suite in the Brigham and Women's Hospital, Harvard Medical School.

?

a. Gao, Y., Rathi, Y., Bouix, S., & Tannenbaum, A. (2012). Filtering in the diffeomorphism group and the?registration of point sets. Image Processing, IEEE Transactions on, 21(10), 4383-4396.

b. Gao, Y., Zhu, L., Norton, I., Agar, N. Y., & Tannenbaum, A. (2014, March). Reconstruction and feature?selection for desorption electrospray ionization mass spectroscopy imagery. In SPIE Medical Imaging (pp.?90360D-90360D). International Society for Optics and Photonics.

c. Gao, Y. Farhat, N., Agrawal, N., Pernelle, G., Chen, X., Egger, J., Blevins, S., Bouix, S., Tannenbaum, A.,?Wells, W., Kikinis, R., Schmidt, E., Viswanathan, A., & Kapur, T. (2012) Needle extraction for the?intraoperative MR image guided brachytherapy, 5th Image Guided Therapy Workshop

?

Complete List of Published Work in MyBibliography:?? http://www.ncbi.nlm.nih.gov/sites/myncbi/1pUbB1tclgoQ7/bibliography/49493812/public

?

D. Research Support

Ongoing Research Support

NIH U24 CA180924 ????????????????????????????????????????????????Saltz, Joel (PI) ????????????????????????????????????9/2014-

Tools to analyze morphology and spatially mapped molecular data

Role: Co-investigator.

?

Completed Research Support

?

NIH K23NS080912 ???????????????????????????????????????????????Amara, Amy (PI)? ??????????????????????????????????1/2014-7/2014

The Effect of Low Frequency STN DBS on Sleep and Vigilance in Parkinson’s Disease Patients

Study the effectiveness of the deep brain stimulation and its variant configurations on the sleeping condition of Parkinson patients.

Role: Co-investigator.

NIH K23NS067053 ???????????????????????????????????????????????Walker, Harrison (PI)????????????????????????????? 10/2013-07/2014

Clinical and Neurophysiological Study of Subthalamic Brain Stimulation In Parkinson’s Disease

Study the effectiveness of the deep brain stimulation for Parkinson Disease.

Role: Co-investigator.

?

The Michael J. Fox Foundation ?????????????????????????????Skidmore, Frank (PI) ????????????????????????????????5/2014-7/2014

A Diffusion Tensor Based Biomarker for Parkinson’s Disease

Nonlinear registration and statistical analysis for diffusion images in the Parkinson’s diseases.

Role: Co-Investigator

?

NIH R01 MH082918 ??????????????????????????????????????????????Bouix, Sylvain (PI)? ????????????????????????????????08/2011-08/2013

Computational Morphometry in Schizophrenia and Related Disorders

As a research fellow, I have developed an objective and quantitative framework for the evaluation of shape

analysis. This is the first such study in the shape analysis community.

Role: Postdoctoral researcher

?

NIH U54 EB005149 ????????????????????????????????????????????????Kikinis, Ron (PI)? ??????????????????????????????????08/2005-08/2013

National Alliance for Medical Image Computing

As a PhD student and then a research fellow, I have been working on projects involving Prostate cancer,

Heart disease, and Brain cancer.

Role: PhD student, Postdoctoral researcher

?

NIH P41 EB015902 ????????????????????????????????????????????????Kikinis, Ron (PI)? ??????????????????????????????????08/2005-08/2013

Neuroimage Analysis Center

As a PhD student and then a research fellow, I have been working on projects involving brain segmentation,

and brain fiber tracts alignment.

Role: PhD student, Postdoctoral researcher

?

Contact

Email:gaoyicn@outlook.com

OfficeTel:0755-26912142? ? ? ?