The technology uses abdominal CT scans of prepped patients to create a 3D model of the human colon and enable visible inspection of the luminal surface in same manner as performed physically on prepped patients by gastroenterologists using optical colonoscopy (OC). Computed-Tomography Colonography (CTC) is non-invasive and can serve as a prelude to OC, if warranted; thus enabling large scale screening of colorectal cancer and minimizing healthcare cost. Our purpose is to create an entirely model-based CTC system, which would enable expert CTC radiologists as well as AI-based examination of the luminal surface to detect and classify colonic polyps as a way for early detection of colorectal cancer. Fig. 1 shows the layout of the CTC system.
This project aims to build a front-end visualization system for CTC.
CTC involves 3 steps: segmentation, flight path generation, and visualization of the internal views of the anatomical structures. In this project, we focus on the last two steps. In the first phase of this project, we propose a general framework for computing flight paths of tubular anatomical structures for virtual endoscopy applications using level set methods. The new technique works in two passes. In the first pass, the overall topology of the organ is analyzed and its important topological nodes are identified, while in the second pass, the actual flight paths are computed by tracking them starting from each identified node. The proposed framework is robust, fully automatic, computationally efficient, and computes CS that are centered, connected, thin, and less sensitive to boundary noise. We have extensively validated the robustness of the proposed method both quantitatively and qualitatively against several synthetic phantoms and clinical datasets.
to be added later
We would like to thank the Psychiatry Department, University of Louisville.