A Fully Automatic CAD-CTC System Based on Curvature Analysis for Standard and Low-Dose CT Data

Abstract

Abstract-Computed tomography colonography (CTC) is a rapidly evolving noninvasive medical investigation that is viewed by radiologists as a potential screening technique for the detection of colorectal polyps. Due to the technical advances in CT system design, the volume of data required to be processed by radiologists has increased significantly, and as a consequence the manual analysis of this information has become an increasingly time consuming process whose results can be affected by interand intrauser variability. The aim of this paper is to detail the implementation of a fully integrated CAD-CTC system that is able to robustly identify the clinically significant polyps in the CT data. The CAD-CTC system described in this paper is a multistage implementation whose main system components are: 1) automatic colon segmentation; 2) candidate surface extraction; 3) feature extraction; and 4) classification. Our CAD-CTC system performs at 100% sensitivity for polyps larger than 10 mm, 92% sensitivity for polyps in the range 5 to 10 mm, and 57.14% sensitivity for polyps smaller than 5 mm with an average of 3.38 false positives per dataset. The developed system has been evaluated on synthetic and real patient CT data acquired with standard and low-dose radiation levels.

CT colonography for synchronous colorectal lesions in patients with colorectal cancer: initial experience

“…Firstly, there is a potential to improve accuracy if CTC is read independently by two radiologists, as with barium enema reporting [25]. Secondly, computer-aided detection and diagnosis (CAD) promises more robust interpretation of images when combined with radiological analysis, with reported rates of sensitivity of 100% for polyps larger than 10 mm, 92% for polyps in the range 5-10 mm, and 57.14% for polyps smaller than 5 mm [26] and can even improve detection for experienced readers [27].…”

Detection and Segmentation of Colonic Polyps on Implicit Isosurfaces by Second Principal Curvature Flow

“…The first term is the second derivative in gradient direction; the second and third terms are the second derivatives in the directions of the principal curvatures of the isosurface perpendicular to the gradient vector. The latter two relate to the principal curvatures of the isosurface (6) With the definition of inward normals, the second principal curvature in the colon is everywhere smaller than or equal to zero, except on protruding regions. Here, both the first and second principal curvatures are positive and the corresponding second derivatives are negative.…”

A Two-Level Approach Towards Semantic Colon Segmentation: Removing Extra-Colonic Findings

“…Computed tomographic colonography (CTC) or virtual colonoscopy has been widely used for detecting colorectal neoplasms via 3D computed tomography (CT) abdomen scans of the cleansed and air-distended colon. In the last decade, many computer aided detection and diagnosis systems [4,5,6,7] have been proposed and actively studied to improve the performance and reliability of human radiologists as second readers.…”