Original investigationImproved Curvature Estimation for Computer-aided Detection of Colonic Polyps in CT Colonography
Section snippets
Methods
In this section, we outline three curvature estimation techniques: Knutsson mapping and two widely used kernel methods. The details of each technique can be found in the related references. The focus of this section is on the immunity property of Knutsson mapping to the discontinuity problem for CAD of colon polyps.
Phantom Study
By inspecting the plots in Figure 3, the error of a small object (theoretically with a larger curvature) is higher than that of a large object, which agrees with the results of Rieger et al (23). For objects with different sizes, the optimal parameters of σT and σk may vary. The optimal values are about σT = 4 and σk = 1.
So far, for the three curvature estimation methods, we have obtained their optimal parameters, which are (0.7, 0.1) for (α1, α2), (1, 2) for (σ1, σ2), and (1, 4, 1) for (σg, σT
Phantom Study
For two traditional kernel methods, KM1 and KM2, the optimal parameters have been extensively explored in previous works. In this study, we focused on investigating the optimal configuration for a new method, KMM. Bearing in mind that the purpose of the investigation was for CAD in CTC, we constructed phantom images with similar image contrast and noise level to those of clinical patient images. The phantom sizes are specified analogously to the sizes of typical polyps in the CTC database (
Conclusion
With the two widely used kernel methods, KM1 and KM2, spurious calculations in curvature estimation were frequently observed (22) because of the gradient discontinuity problem, indicating false high curvature. In this study, we applied a new method, KMM, to improve the curvature computation and investigated the potential benefits of KMM for CAD of colon polyps on CTC.
From the results of the phantom study, the new method with optimized parameters greatly improved the curvature estimation for the
Acknowledgment
We would like to acknowledge the use of the Viatronix V3D-Colon Module (Viatronix, Inc, Stony Brook, NY).
References (31)
- et al.
Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population
Gastroenterology
(2005) - et al.
Computing the differential characteristics of isointensity surfaces
Comput Vis Image Understand
(1995) - et al.
Analysis of kernel method for surface curvature estimation
Int Congr Ser
(2004) - et al.
Colon polyp detection using smoothed shape operator: preliminary results
Med Image Anal
(2008) Cancer facts & figures 2008
(2008)Screening for colorectal cancer
Ann Intern Med
(1990)- et al.
Colorectal cancer screening with CT colonography, colonoscopy, and double-contrast barium enema examination: prospective assessment of patient perceptions and preferences
Radiology
(2003) - et al.
Emerging technologies in screening for colorectal cancer: CTC, immunochemical fecal occult blood tests, stool screening using molecular markers
CA Cancer J Clin
(2002) - et al.
Computed tomographic virtual colonoscopy to screen for colorectal neoplasia in asymptomatic adults
N Engl J Med
(2003) - et al.
Computer-aided diagnosis in virtual colonography via combination of surface normal and sphere fitting methods
Eur Radiol
(2002)
Automated polyp detector for CT colonography: feasibility study
Radiology
Computer-assisted reader software versus expert reviewers for polyp detection on CT colonography
AJR Am J Roentgenol
Computer-aided detection for CT colonography: update 2007
Abdom Imaging
From voxel to intrinsic surface features
Image Vis Comput
Cited by (21)
Review of computational methods for the detection and classification of polyps in colonoscopy imaging
2020, Gastroenterologia y HepatologiaA Simultaneous Polyp and Lumen Detection Framework Toward Autonomous Robotic Colonoscopy
2024, IEEE Transactions on Medical Robotics and BionicsEnsemble Learning based on Classifier Prediction Confidence and Comprehensive Learning Particle Swarm Optimisation for Medical Image Segmentation
2022, Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence, SSCI 2022Segmentation and volumetric analysis of colon wall for detection of flat polyp candidates via CT colonography
2019, Proceedings - 6th Annual Conference on Computational Science and Computational Intelligence, CSCI 2019Texture Feature Analysis of Neighboring Colon Wall for Colorectal Polyp Classification
2018, 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings
This work was partially supported by grants CA082402 and CA120917 from the National Cancer Institute (Bethesda, MD).
Dr Lu is supported by the National Nature Science Foundation of China under grant 60772020.