Jacob E D Levman1, Petrina Causer, Ellen Warner, Anne L Martel. 1. Sunnybrook Research Institute, Department of Medical Biophysics, University of Toronto, 2075 Bayview Avenue, Room S605, Toronto, ON, Canada. jacob.levman@sri.utoronto.ca
Abstract
RATIONALE AND OBJECTIVES: To evaluate the effect that variations in the enhancement threshold have on the diagnostic accuracy of two computer-aided detection (CAD) systems for magnetic resonance based breast cancer screening. MATERIALS AND METHODS: Informed consent was obtained from all patients participating in cancer screening and this study was approved by the participating institution's review board. This retrospective study was nested in a prospective, single-institution, high-risk, breast screening study involving dynamic contrast-enhanced magnetic resonance imaging. Only those screening examinations (n = 223) for which a histopathological diagnosis was available were included. Two CAD methods were performed: the signal enhancement ratio (SER) and support vector machines (SVMs). Statistical analysis was performed by tracking changes in each CAD test's diagnostic accuracy (eg, receiver-operating characteristic [ROC] curve area, maximum possible sensitivity) with changes in the enhancement threshold. RESULTS: The enhancement threshold plays a significant role in affecting a CAD test's potential sensitivity, ROC curve area, and number of assumed true and false-positive predictions per cancerous examination. A high threshold can also limit the CAD-based detection of the full size of a lesion. CONCLUSIONS: Enhancement thresholds can limit a CAD test's ability to diagnose a lesion's full size and as such should not be raised above 60%. The clinically used SER method exhibits a high rate of false positives at low enhancement thresholds and as such the threshold should not be set lower than 50%. The SVM method yielded better results in our study than the SER method at clinically realistic enhancement thresholds.
RATIONALE AND OBJECTIVES: To evaluate the effect that variations in the enhancement threshold have on the diagnostic accuracy of two computer-aided detection (CAD) systems for magnetic resonance based breast cancer screening. MATERIALS AND METHODS: Informed consent was obtained from all patients participating in cancer screening and this study was approved by the participating institution's review board. This retrospective study was nested in a prospective, single-institution, high-risk, breast screening study involving dynamic contrast-enhanced magnetic resonance imaging. Only those screening examinations (n = 223) for which a histopathological diagnosis was available were included. Two CAD methods were performed: the signal enhancement ratio (SER) and support vector machines (SVMs). Statistical analysis was performed by tracking changes in each CAD test's diagnostic accuracy (eg, receiver-operating characteristic [ROC] curve area, maximum possible sensitivity) with changes in the enhancement threshold. RESULTS: The enhancement threshold plays a significant role in affecting a CAD test's potential sensitivity, ROC curve area, and number of assumed true and false-positive predictions per cancerous examination. A high threshold can also limit the CAD-based detection of the full size of a lesion. CONCLUSIONS: Enhancement thresholds can limit a CAD test's ability to diagnose a lesion's full size and as such should not be raised above 60%. The clinically used SER method exhibits a high rate of false positives at low enhancement thresholds and as such the threshold should not be set lower than 50%. The SVM method yielded better results in our study than the SER method at clinically realistic enhancement thresholds.
Authors: Savannah C Partridge; Jessica E Gibbs; Ying Lu; Laura J Esserman; Debasish Tripathy; Dulcy S Wolverton; Hope S Rugo; E Shelley Hwang; Cheryl A Ewing; Nola M Hylton Journal: AJR Am J Roentgenol Date: 2005-06 Impact factor: 3.959
Authors: Tim W Nattkemper; Bert Arnrich; Oliver Lichte; Wiebke Timm; Andreas Degenhard; Linda Pointon; Carmel Hayes; Martin O Leach Journal: Artif Intell Med Date: 2004-12-16 Impact factor: 5.326
Authors: Ellen Warner; Donald B Plewes; Kimberley A Hill; Petrina A Causer; Judit T Zubovits; Roberta A Jong; Margaret R Cutrara; Gerrit DeBoer; Martin J Yaffe; Sandra J Messner; Wendy S Meschino; Cameron A Piron; Steven A Narod Journal: JAMA Date: 2004-09-15 Impact factor: 56.272
Authors: Ludguier D Montejo; Jingfei Jia; Hyun K Kim; Uwe J Netz; Sabine Blaschke; Gerhard A Müller; Andreas H Hielscher Journal: J Biomed Opt Date: 2013-07 Impact factor: 3.170
Authors: Jacob E D Levman; Cristina Gallego-Ortiz; Ellen Warner; Petrina Causer; Anne L Martel Journal: J Digit Imaging Date: 2016-02 Impact factor: 4.056
Authors: Vignesh A Arasu; Ryan C-Y Chen; David N Newitt; C Belinda Chang; Hilda Tso; Nola M Hylton; Bonnie N Joe Journal: Acad Radiol Date: 2011-03-21 Impact factor: 3.173