Computer Graphics and Visualization › Publications › Effects of filtering on colorectal polyp detection in ultra low dose CT

In Proceedings of Medical imaging 2006 - Physiology, function, and structure from medical images

Effects of filtering on colorectal polyp detection in ultra low dose CT

G.A.F. Schoonenberg, A.H. de Vries, S.E. Grigorescu, J. Peters, Anna Vilanova, R. Truyen, J. Stoker, and F.A. Gerritsen

From left to right: Axial slice with boxed polyp; enlarged polyp, squares denote two locations, the left one is in air and the right one inside the polyp; Gaussian filtered result (σ =2.0 mm); Bilateral filtered result (σ dis = 3.0 mm and σ int = 250 HU)

Paper Cite More

We have evaluated the feasibility of polyp detection on simulated ultra low dose CT Colonography data by a computer aided polyp detection (CAD) algorithm. We compared the results of ultra low dose to normal dose data. Twenty-three extensively prepared patients were scanned in prone and supine position at 25 to 100 mAs (average 70 mAs) depending on their waist circumference. Noise was added and the scans were reconstructed at 6.25 and 1.39 mAs. To evaluate the performance of the CAD system, polyps detected by an experienced reviewer and confirmed at colonoscopy were used as ground truth. Curvature, concavity and sphericity of the colon surface were used to detect polyp candidates. Bilateral filtering was used to reduce noise. We present the results for 40 polyps of 6 mm or larger as measured during colonoscopy. The by-polyp sensitivity was 80% for medium size polyps (6-9 mm) and 97% for large polyps (10 mm or larger) at an average value of 5 false-positives per scan for normal dose data. The by-polyp sensitivity was 81% for medium size polyps and 85% for large size polyps at an average value of 5 false-positives per scan for low dose data (6.25 mAs). Finally for the ultra low dose data (1.39 mAs) we achieved a by-polyp sensitivity of 75% for medium size polyps and 97% for large polyps at an average value of 5 false-positives per scan. The conclusion of our study is that CAD for polyp detection is feasible on ultra low dose CT colonography data.

More Information

Paper preprint

Citation

G.A.F. Schoonenberg, A.H. de Vries, S.E. Grigorescu, J. Peters, Anna Vilanova, R. Truyen, J. Stoker, and F.A. Gerritsen, Effects of filtering on colorectal polyp detection in ultra low dose CT, In Proceedings of Medical imaging 2006 - Physiology, function, and structure from medical images, 6143, pp. 1–10, 2006.

BibTex 

@inproceedings{bib:schoonenberg:2006,
    author       = { Schoonenberg, G.A.F. and de Vries, A.H. and Grigorescu, S.E. and Peters, J. and Vilanova, Anna and Truyen, R. and Stoker, J. and Gerritsen, F.A. },    
    title        = { Effects of filtering on colorectal polyp detection in ultra low dose CT },
    booktitle    = { In Proceedings of Medical imaging 2006 - Physiology, function, and structure from medical images },
    editors      = { Maduca A. },
    volume       = { 6143 },
    year         = { 2006 },
    pages        = { 1--10 },
    publisher    = { SPIE },
    address      = { Bellingham, Wash. },
    url          = { https://publications.graphics.tudelft.nl/papers/537 },
}