Abstract
Purpose
To develop and implement a method for identification and quantification of gadolinium (Gd) enhancements with minimal human intervention.
Materials and Methods
Dual fast spin echo (FSE), fluid attenuation inversion recovery (FLAIR), and preβ and postcontrast T1βweighted spin echo were acquired on 22 subjects. The enhancements were identified on the postcontrast T1βweighted images based on morphological operations. A single threshold based on the ratio of the difference of postcontrast and precontrast T1 images with that of precontrast T1 images is applied to the reconstructed images to reduce the false classifications. False classification of enhancements arising from enhancing vasculature and structures such as the choroid plexus that lack a bloodβbrain barrier were reduced by assuming that the true enhancements are always associated with hyperintense lesions on T2βweighted images (T2 lesions). The enhanced lesions were further delineated based on fuzzy connectivity.
Results
The segmented Gd enhancements were evaluated quantitatively with manually identified enhancements based on similarity measures. The average similarity index (SI) of 0.76 suggests excellent performance of the proposed methodology. The BlandβAltman plot shows a close agreement between the results obtained manually and those based on the proposed methodology.
Conclusion
The proposed algorithm identifies and quantifies Gd enhancements accurately with minimal human intervention. J. Magn. Reson. Imaging 2007;25:932β937. Β© 2007 WileyβLiss, Inc.