Image Registration of Deformable Tissues using Physics-based Models

Physically-based simulations can improve the quality of registration of medical images by introducing context information that is not present in the matrices of pixel intensities that typically define images. We are developing image registration algorithms that achieve high accuracy by combining physics-based models of tissue deformation with optimization algorithms. Our methods have the potential to enable more precise radiation treatments for cancer and also facilitate guidance of medical instruments to clinical targets.

We developed an image registration system based on physically-based modeling and simulation of the prostate and surrounding tissues to register cancerous tumor locations for targeted prostate brachytherapy treatment planning. Cancerous tumors can be identified using magnetic resonance spectroscopy (MRS) imaging, which is acquired with an endorectal probe that causes significant nonlinear deformation of the prostate. The probe is removed during magnetic resonance (MR) imaging for brachytherapy planning and therapy.

Given probe-in image with MRS grid

(a) Given probe-in image with MRS grid

Given probe-out image

(b) Given probe-out image

Predicted probe-in image with MRS grid

(c) Predicted probe-in image with MRS grid

Given probe-out image with predicted MRS grid

(d) Given probe-out image with predicted MRS grid

MR Spectroscopy data, obtained within the yellow MRS grid, requires insertion of an endorectal probe (a). HDR brachytherapy treatment for prostate cancer is performed with the probe removed (b). Using a finite element-based biomechanical simulation, the rectum of the given probe-out image (b) is inflated to the shape of the probe in the given probe-in image with MRS grid (a) to produce a predicted probe-in image with MRS grid (c). The predicted probe-in image can then be easily undeformed to predict the MRS grid warping for the given probe-out image (d).

Given 2-dimensional segmented probe-in and probe-out images, our finite element based model defines a mapping between the images by estimating the deformation of the prostate and surrounding tissues due to endorectal probe insertion and balloon inflation. Treating uncertain patient-specific model parameters for tissue stiffness and external forces as variables, we compute a locally optimal solution to maximize image registration quality.

We visualize results by applying the computed mapping to the probe-out image to generate a predicted probe-in image. We compare the predicted probe-in images to the given probe-in images for 5 patients and obtain an average Dice Similarity Coefficient (DSC) of 95.6% for the prostate. Using the mapping, we warp a regular MRS grid from the given probe-in image to the given probe-out image for use during treatment planning.

Publications/Presentations

  1. Qingyu Zhao, Stephen Pizer, Ron Alterovitz, Marc Niethammer, and Julian Rosenman, "Orthotropic Thin Shell Elasticity Estimation for Surface Registration," in Proc. Information Processing in Medical Imaging (IPMI), June 2017, pp. 493-504. (Publisher) (Download PDF)
  2. Qingyu Zhao, True Price, Stephen Pizer, Marc Niethammer, Ron Alterovitz, and Julian Rosenman, "The Endoscopogram: A 3D Model Reconstructed from Endoscopic Video Frames," in Medical Image Computing and Computer Assisted Intervention (MICCAI), Oct. 2016, pp. 439-447. (Publisher) (Download PDF)
    (Selected for oral presentation; only 5.0% of submissions presented orally)
  3. Qingyu Zhao, James Price, Stephen Pizer, Marc Niethammer, Ron Alterovitz, and Julian Rosenman, "Surface Registration in the Presence of Missing Patches and Topology Change," in Proc. Medical Image Understanding and Analysis, July 2015, pp. 8-13.
    (Best Paper Award)
  4. Ron Alterovitz, Ken Goldberg, Jean Pouliot, I-Chow Joe Hsu, Yongbok Kim, Susan Moyher Noworolski, and John Kurhanewicz, "Registration of MR prostate images with biomechanical modeling and nonlinear parameter estimation," Medical Physics, vol. 33, no. 2, pp. 446-454, Feb. 2006. (Download PDF)
  5. Ron Alterovitz, Yongbok Kim, John Kurhanewicz, Jean Pouliot, I-Chow Joe Hsu, and Ken Goldberg, "Prostate MR Spectroscopy Image Registration Using Biomechanical Modeling of Tissue Deformations due to Endorectal Probe Insertion," American Brachytherapy Society (ABS) 26th Annual Meeting, San Francisco, CA, June 2005.
  6. Ron Alterovitz, Ken Goldberg, John Kurhanewicz, Jean Pouliot, I-Chow Hsu, "Image Registration for Prostate MR Spectroscopy Using Biomechanical Modeling and Optimization of Force and Stiffness Parameters," in Proc. 26th Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society (EMBS), Sept. 2004, pp. 1722-1725. (Download PDF)
  7. Ron Alterovitz, Ken Goldberg, John Kurhanewicz, Jean Pouliot, I-Chow Hsu, "Registering MR with MRS images for HDR prostate treatment using finite element modeling," 46th American Association of Physicists in Medicine (AAPM) Annual Meeting, Pittsburgh, PA, July 2004.