Limits...
Computer-aided detection (CAD) for breast MRI: evaluation of efficacy at 3.0 T.

Meeuwis C, van de Ven SM, Stapper G, Fernandez Gallardo AM, van den Bosch MA, Mali WP, Veldhuis WB - Eur Radiol (2009)

Bottom Line: For the same two radiologists the mean sensitivity and specificity for CAD-based interpretation was 90.4% (not significant) and 81.3% (significant at p < 0.05), respectively.With one-way ANOVA no significant differences were found between the two breast radiologists and the two residents together, or between any two readers separately.Automated analysis at 50% and 100% thresholds showed a high sensitivity and specificity for readers with varying levels of experience.

View Article: PubMed Central - PubMed

Affiliation: Department of Radiology, Alysis Zorggroep, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands. CMeeuwis@alysis.nl

ABSTRACT

Objective: The purpose of the study was to evaluate the accuracy of 3.0-T breast MRI interpretation using manual and fully automated kinetic analyses.

Material and methods: Manual MRI interpretation was done on an Advantage Workstation. Retrospectively, all examinations were processed with a computer-aided detection (CAD) system. CAD data sets were interpreted by two experienced breast radiologists and two residents. For each lesion automated analysis of enhancement kinetics was evaluated at 50% and 100% thresholds. Forty-nine malignant and 22 benign lesions were evaluated.

Results: Using threshold enhancement alone, the sensitivity and specificity of CAD were 97.9% and 86.4%, respectively, for the 50% threshold, and 97.9% and 90%, respectively, for the 100% threshold. Manual interpretation by two breast radiologists showed a sensitivity of 84.6% and a specificity of 68.8%. For the same two radiologists the mean sensitivity and specificity for CAD-based interpretation was 90.4% (not significant) and 81.3% (significant at p < 0.05), respectively. With one-way ANOVA no significant differences were found between the two breast radiologists and the two residents together, or between any two readers separately.

Conclusion: CAD-based analysis improved the specificity compared with manual analysis of enhancement. Automated analysis at 50% and 100% thresholds showed a high sensitivity and specificity for readers with varying levels of experience.

Show MeSH
Flow chart of patient inclusion, with reasons for exclusion and total number of patients for each analysis method
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2822230&req=5

Fig1: Flow chart of patient inclusion, with reasons for exclusion and total number of patients for each analysis method

Mentions: Women who underwent breast MRI not for clinical indications but for research purposes were excluded from this study (n = 71). In addition, 286 patients were excluded because histology was not obtained. Of the 69 patients in whom histology was obtained, 4 patients with 5 lesions were excluded for technical reasons: severe patient motion (n = 2), failed fat suppression (n = 1) and a technical error with contrast material injection (n = 2), which caused an incomplete study. Finally 65 patients were included with a total of 71 breast lesions proven surgically or by core biopsy. The evaluation of the accuracy of CAD threshold enhancement was based on these 65 patients. The evaluation of the diagnostic accuracy of the four different readers was based on the same data set, with the exclusion of all 29 BI-RADS category 6 known cancers. Exclusion of known cancers was necessary because readers were blinded to the pathological results but not to patient history (Fig. 1).Fig. 1


Computer-aided detection (CAD) for breast MRI: evaluation of efficacy at 3.0 T.

Meeuwis C, van de Ven SM, Stapper G, Fernandez Gallardo AM, van den Bosch MA, Mali WP, Veldhuis WB - Eur Radiol (2009)

Flow chart of patient inclusion, with reasons for exclusion and total number of patients for each analysis method
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2822230&req=5

Fig1: Flow chart of patient inclusion, with reasons for exclusion and total number of patients for each analysis method
Mentions: Women who underwent breast MRI not for clinical indications but for research purposes were excluded from this study (n = 71). In addition, 286 patients were excluded because histology was not obtained. Of the 69 patients in whom histology was obtained, 4 patients with 5 lesions were excluded for technical reasons: severe patient motion (n = 2), failed fat suppression (n = 1) and a technical error with contrast material injection (n = 2), which caused an incomplete study. Finally 65 patients were included with a total of 71 breast lesions proven surgically or by core biopsy. The evaluation of the accuracy of CAD threshold enhancement was based on these 65 patients. The evaluation of the diagnostic accuracy of the four different readers was based on the same data set, with the exclusion of all 29 BI-RADS category 6 known cancers. Exclusion of known cancers was necessary because readers were blinded to the pathological results but not to patient history (Fig. 1).Fig. 1

Bottom Line: For the same two radiologists the mean sensitivity and specificity for CAD-based interpretation was 90.4% (not significant) and 81.3% (significant at p < 0.05), respectively.With one-way ANOVA no significant differences were found between the two breast radiologists and the two residents together, or between any two readers separately.Automated analysis at 50% and 100% thresholds showed a high sensitivity and specificity for readers with varying levels of experience.

View Article: PubMed Central - PubMed

Affiliation: Department of Radiology, Alysis Zorggroep, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands. CMeeuwis@alysis.nl

ABSTRACT

Objective: The purpose of the study was to evaluate the accuracy of 3.0-T breast MRI interpretation using manual and fully automated kinetic analyses.

Material and methods: Manual MRI interpretation was done on an Advantage Workstation. Retrospectively, all examinations were processed with a computer-aided detection (CAD) system. CAD data sets were interpreted by two experienced breast radiologists and two residents. For each lesion automated analysis of enhancement kinetics was evaluated at 50% and 100% thresholds. Forty-nine malignant and 22 benign lesions were evaluated.

Results: Using threshold enhancement alone, the sensitivity and specificity of CAD were 97.9% and 86.4%, respectively, for the 50% threshold, and 97.9% and 90%, respectively, for the 100% threshold. Manual interpretation by two breast radiologists showed a sensitivity of 84.6% and a specificity of 68.8%. For the same two radiologists the mean sensitivity and specificity for CAD-based interpretation was 90.4% (not significant) and 81.3% (significant at p < 0.05), respectively. With one-way ANOVA no significant differences were found between the two breast radiologists and the two residents together, or between any two readers separately.

Conclusion: CAD-based analysis improved the specificity compared with manual analysis of enhancement. Automated analysis at 50% and 100% thresholds showed a high sensitivity and specificity for readers with varying levels of experience.

Show MeSH