TY - JOUR
T1 - CT colonography
T2 - Influence of 3D viewing and polyp candidate features on interpretation with computer-aided detection
AU - Shi, Rong
AU - Schraedley-Desmond, Pamela
AU - Napel, Sandy
AU - Olcott, Eric W.
AU - Jeffrey, R. Brooke
AU - Yee, Judy
AU - Zalis, Michael E.
AU - Margolis, Daniel
AU - Paik, David S.
AU - Sherbondy, Anthony J.
AU - Sundaram, Padmavathi
AU - Beaulieu, Christopher F.
PY - 2006/6
Y1 - 2006/6
N2 - Purpose: To retrospectively determine if three-dimensional (3D) viewing improves radiologists' accuracy in classifying true-positive (TP) and false-positive (FP) polyp candidates identified with computer-aided detection (CAD) and to determine candidate polyp features that are associated with classification accuracy, with known polyps serving as the reference standard. Materials and Methods: Institutional review board approval and informed consent were obtained; this study was HIPAA compliant. Forty-seven computed tomographic (CT) colonography data sets were obtained in 26 men and 10 women (age range, 42-76 years). Four radiologists classified 705 polyp candidates (53 TP candidates, 652 FP candidates) identified with CAD; initially, only two-dimensional images were used, but these were later supplemented with 3D rendering. Another radiologist unblinded to colonoscopy findings characterized the features of each candidate, assessed co-Ion distention and preparation, and defined the true nature of FP candidates. Receiver operating characteristic curves were used to compare readers' performance, and repeated-measures analysis of variance was used to test features that affect interpretation. Results: Use of 3D viewing improved classification accuracy for three readers and increased the area under the receiver operating characteristic curve to 0.96-0.97 (P < .001). For TP candidates, maximum polyp width (P = .038), polyp height (P = .019), and preparation (P = .004) significantly affected accuracy. For FP candidates, colonic segment (P = .007), attenuation (P < .001), surface smoothness (P < .001), distention (P = .034), preparation (P < .001), and true nature of candidate lesions (P < .001) significantly affected accuracy. Conclusion: Use of 3D viewing increases reader accuracy in the classification of polyp candidates identified with CAD. Polyp size and examination quality are significantly associated with accuracy.
AB - Purpose: To retrospectively determine if three-dimensional (3D) viewing improves radiologists' accuracy in classifying true-positive (TP) and false-positive (FP) polyp candidates identified with computer-aided detection (CAD) and to determine candidate polyp features that are associated with classification accuracy, with known polyps serving as the reference standard. Materials and Methods: Institutional review board approval and informed consent were obtained; this study was HIPAA compliant. Forty-seven computed tomographic (CT) colonography data sets were obtained in 26 men and 10 women (age range, 42-76 years). Four radiologists classified 705 polyp candidates (53 TP candidates, 652 FP candidates) identified with CAD; initially, only two-dimensional images were used, but these were later supplemented with 3D rendering. Another radiologist unblinded to colonoscopy findings characterized the features of each candidate, assessed co-Ion distention and preparation, and defined the true nature of FP candidates. Receiver operating characteristic curves were used to compare readers' performance, and repeated-measures analysis of variance was used to test features that affect interpretation. Results: Use of 3D viewing improved classification accuracy for three readers and increased the area under the receiver operating characteristic curve to 0.96-0.97 (P < .001). For TP candidates, maximum polyp width (P = .038), polyp height (P = .019), and preparation (P = .004) significantly affected accuracy. For FP candidates, colonic segment (P = .007), attenuation (P < .001), surface smoothness (P < .001), distention (P = .034), preparation (P < .001), and true nature of candidate lesions (P < .001) significantly affected accuracy. Conclusion: Use of 3D viewing increases reader accuracy in the classification of polyp candidates identified with CAD. Polyp size and examination quality are significantly associated with accuracy.
UR - http://www.scopus.com/inward/record.url?scp=33744794891&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33744794891&partnerID=8YFLogxK
U2 - 10.1148/radiol.2393050418
DO - 10.1148/radiol.2393050418
M3 - Review article
C2 - 16714460
AN - SCOPUS:33744794891
SN - 0033-8419
VL - 239
SP - 768
EP - 776
JO - RADIOLOGY
JF - RADIOLOGY
IS - 3
ER -