A spinning tangent based CAD system for detection of flat lesions in CT colonography

While many computer-aided detection (CADe) systems for CT colonography can detect polypoid lesions at a high sensitivity level, very few are targeted toward detecting flat lesions. Research has shown that flat lesions are more likely to contain carcinoma than polypoid lesions; therefore, it is imperative that they be adequately detected in screenings and examinations. However, current CADe systems systems have a low sensitivity for flat lesions, with a relatively high false-positive (FP) rate. By generating a surface mesh of the colon and spinning a tangent line at each point of the mesh, we have developed a new CADe system for detecting flat lesions. With our system, we detected 82% (23/28) of flat lesions in our dataset with a small number of FPs (4.5 per patient), whereas a modified shape-index-based CADe system detected 68% (19/28) of them with 10 FPs per patient.

[1]  Kenji Suzuki,et al.  A CAD utilizing 3D massive-training ANNs for detection of flat lesions in CT colonography: preliminary results , 2009, Medical Imaging.

[2]  Vitoantonio Bevilacqua,et al.  Combined Use of Densitometry and Morphological Analysis to Detect Flat Polyps , 2009, ICIC.

[3]  Hiroyuki Yoshida,et al.  Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps , 2001, IEEE Transactions on Medical Imaging.

[4]  Kenji Suzuki,et al.  CT colonography: advanced computer-aided detection scheme utilizing MTANNs for detection of "missed" polyps in a multicenter clinical trial. , 2009, Medical physics.

[5]  C. Johnson,et al.  Flat polyps of the colon: accuracy of detection by CT colonography and histologic significance , 2009, Abdominal Imaging.

[6]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[7]  Stanley R. Sternberg,et al.  Biomedical Image Processing , 1983, Computer.

[8]  Walter Park,et al.  Prevalence of nonpolypoid (flat and depressed) colorectal neoplasms in asymptomatic and symptomatic adults. , 2008, JAMA.

[9]  Hiroyuki Yoshida,et al.  Automated Segmentation of Colonic Walls for Computerized Detection of Polyps in CT Colonography , 2001, Journal of computer assisted tomography.

[10]  E. Paulson,et al.  Analysis of air contrast barium enema, computed tomographic colonography, and colonoscopy: prospective comparison , 2005, The Lancet.

[11]  A. Jemal,et al.  Cancer Statistics, 2009 , 2009, CA: a cancer journal for clinicians.

[12]  Hiroyuki Yoshida,et al.  Massive-training artificial neural network (MTANN) for reduction of false positives in computer-aided detection of polyps: Suppression of rectal tubes. , 2006, Medical physics.

[13]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[14]  S. Armato,et al.  Mixture of expert 3D massive-training ANNs for reduction of multiple types of false positives in CAD for detection of polyps in CT colonography. , 2008, Medical physics.

[15]  Stuart A. Taylor,et al.  Computed tomographic colonography: assessment of radiologist performance with and without computer-aided detection. , 2006, Gastroenterology.

[16]  Ronald M. Summers,et al.  Employing topographical height map in colonic polyp measurement and false positive reduction , 2009, Pattern Recognit..

[17]  Joyoni Dey,et al.  > Replace This Line with Your Paper Identification Number (double-click Here to Edit) < , 2022 .