Medical Image Processing

Most medical image analysis applications require pre-processing steps including image segmentation (right) and deformable image registration (left). Registration is of particular importance the DMIC’s work on inferring patient-specific biomechanical properties from dynamic imaging.

In addition to biomechanical modeling, the development of medical image processing methods requires many aspects of applied mathematics, including the numerical solution of partial differential equations, iterative methods for large-scale linear systems, large-scale optimization, and parallel computing. Our recent work in this area has focused on how to incorporate deep learning methods into known algorithmic frameworks with well-defined numerical properties.

Selected Publications on Image Processing

1. Charles Vu, Zaid Siddiqui, Leonid Zamdborg, Andrew Thompson, Thomas Quinn, Edward Castillo, and Thomas Guerrero. Deep Convolutional Neural Networks for Automatic Segmentation of Thoracic Organs-At-Risk in Radiation Oncology – Use of Non-Domain Transfer Learning. Journal of Applied Clinical Medical Physics, 21(6): 108-113, 2020.
   
   
2. Edward Castillo. Quadratic Penalty Method for Intensity-Based Deformable Image Registration and 4DCT Lung Motion Recovery. Medical Physics, 46(5): 2194-2203, 2019.
   
   
3. Min Li, Sarah Castillo, Richard Castillo, Edward Castillo, Thomas Guerrero, Liang Xiao, and Xiao-Lin Zheng. Automated Identification and Reduction of Artifacts in Cine Four-Dimensional Computed Tomography (4DCT) Images using Respiratory Motion Model. International Journal of Computer Assisted Radiology and Surgery, 12(9): 1521-1532, 2017.
   
   
4. Edward Castillo, Richard Castillo, David Fuentes, and Thomas Guerrero. Computing Global Minimizers to a Constrained B-spline Image Registration Problem from Optimal Perturbations to Block Match Data. Medical Physics, 41(4), 2014.
   
   
5. Min Li, Edward Castillo, Xiao-Lin Zheng, Hong-Yan Luo, Richard Castillo, Yi Wu, and Thomas Guerrero. Modeling Lung Deformation: A Combined Deformable Image Registration Method with Spatially Varying Young’s Modulus Estimates. Medical Physics, 40(8), 2013.
   
   
6. Edward Castillo, Richard Castillo, Benjamin White, Javier Rojo, and Thomas Guerrero. Least Median of Squares Filtering of Locally Optimal Point Matches for Compressible Flow Image Registration. Physics in Medicine and Biology, 57: 4827-4833, 2012.
   
   
7. Edward Castillo, Jian Liang, and Hongkai Zhao. Point Cloud Segmentation and Denoising via Constrained Nonlinear Least Squares Normal Estimates. Book Chapter on: Innovations for Shape Analysis: Models and Algorithms, Springer, 2012.
   
   
8. Edward Castillo, Richard Castillo, Josue Martinez, Maithili Shenoy, and Thomas Guerrero. Four Dimensional Deformable Image Registration Using Trajectory Modeling. Physics in Medicine and Biology, 55: 305-327, 2010.
   
   
9. Xuejun Gu, Hubert Pan, Yun Liang, Richard Castillo, Deshan Yang, Dongju Choi, Edward Castillo, Amitava Majumdar, Thomas Guerrero, and Steve Jiang. Implementation and Evaluation of Various Demons Deformable Image Registration Algorithms on GPU. Physics in Medicine and Biology, 55: 207-219, 2010.
   
   
10. Richard Castillo, Edward Castillo, Rudy Guerra, Valen Johnson, Travis McPhail, Amit Garg, and Thomas Guerrero. A Framework for Evaluation of Deformable Image Registration Spatial Accuracy Using Large Landmark Point Sets. Physics in Medicine and Biology, 54: 1849-1870, 2009. (PMB Featured Article 2009)