Detection Of Polyps In Computed Tomography Colonography Research Articles

Novel 3D Radiomic Features for Computer-Aided Polyp Detection in CT Colonography

State-of-the-art computer-aided detection (CAD) systems for colonic polyps in computed tomographic colonography (CTC) tend to yield high detection sensitivities with high false positive (FP) rates. This paper proposes a novel CTC CAD system using 3-D radiomic features that can obtain high detection sensitivity at low FP rate. Our previous shape-based methods are used to generate polyp candidates. Then, a wide variety of radiomic features are developed in the 3-D domain for each initial candidate, including the multiscale Weber local descriptors and the statistical descriptors calculated from various volumetric feature maps on the basis of computed tomography (CT) density, CT gradient, fractal dimension, curvature, and fast radial symmetry transform. These new 3-D radiomic features can characterize polyp candidates in terms of the shape, texture heterogeneity, and salient pattern. FP reduction is finally performed by Random Forests with a developed score rank method to tune the training set. 510 fluid-tagging CT scans from 255 patients with 130 polyps ≥5 mm were utilized to validate the proposed system in the fivefold cross-validation strategy. The detection result reached 98.5% by-polyp sensitivity at 2.0 FPs per scan for polyps ≥5 mm. Experimental results indicate that the proposed system yielded a detection performance with high sensitivity and low FP rate. We believe that the proposed system would assist radiologists in increasing the detection accuracy and reducing the interpretation time during colon cancer screening.

Computed Tomography Colonography: The Robley Rex VAMC Experience

Introduction: Computed tomography colonography (CTC) was introduced as a non-invasive option for colorectal cancer screening in the 1990's. In the past couple of decades, studies have shown this to be a highly sensitive and specific, minimally invasive diagnostic technique for the detection of colon polyps and cancers. This alternative means of screening has the potential to improve patient compliance and therefore could have a significant impact on the prevention of colorectal cancer. Methods: In January 2012 CT colonography was introduced at the Robley Rex VA in Louisville Kentucky. A chart review was performed on all patients who underwent CTC from 2012 to 2015 as a quality improvement project. 35 patient charts (demographics table 1) were reviewed to evaluate the indication for CTC (table 2), results of the diagnostic exam (table 3), comorbidities for colon cancer and any secondary outcome that resulted from this non-invasive examination (table 4). CTCs were performed by 320-row CT scan in both the supine and prone position without any intravenous contrast. Colonic and extracolonic findings were evaluated. Results: 33/35 patients underwent CTC evaluation between 2012 to 2015, with prior difficult colonoscopy being the most common indication (63.6%), followed by CTC being the patient's preferred method of surveillance (15%) and increased bleeding risk (12.1%). Diverticulosis was the most common finding (27.3% of CTCs), with only two CTCs showing polyps (6.1%). These patients had a variety of comorbidities, including tobacco abuse, diabetes, hyperlipidemia, obesity and hyperlipidemia. Only one patient used CTC as their initial screening method at age 50. All patients tolerated CTC diagnostic evaluation well without difficulty. No adverse effects were noted. Conclusion: Based on the results, CTC was primarily used when colonoscopy was difficult for the patient, or increased risk for bleeding or sedation as a result of patient comorbidities (table 4). CTC may become the method of choice for those patients that prefer not to have colonoscopy. The study number is small and is limited to one center's experience with CTC that was reviewed and interpreted by one radiologist. A head-to-head study assessing polyp detection in CTC interpreted by an expert radiologist and colonoscopy for initial screening may provide valuable information.Figure 1Figure 2Figure 3