Rationale and Objectives. The purpose of this study was to integrate contra
st material kinetic and architectural data from magnetic resonance (MR) ima
ges and to assess the improvement in diagnostic accuracy.
Materials and Methods. MR imaging data from a diagnostic cohort of 100 pati
ents (50 malignant and 50 benign cases) were analyzed.
Results. Qualitative classification of the enhancement curve was the most p
redictive kinetic feature. Receiver operating characteristic (ROC) curves w
ere calculated for the architectural model alone and for the architectural
model combined with the qualitative kinetic classification. The results dem
onstrated a statistically significant increase in ROC area (P = .03) of the
combined model compared with that of the architectural model alone.
Conclusion. The addition of qualitative classification of the time-signal i
ntensity curve to an architectural interpretation model results in signific
ant improvement in model performance as measured by the area under the ROC
curve.