Automated detection of the arterial input function using normalized cut clustering to determine cerebral perfusion by dynamic susceptibility contrast-magnetic resonance imaging.

Purpose: To propose a new clustering method for the automatic detection of arterial input function (AIF) with high accuracy in dynamic susceptibility contrast-magnetic resonance imaging (DSC-MRI).

Materials And Methods: A novel method for automatically determining the AIF was proposed to facilitate the analysis of MR perfusion, which relied on normalized cut (Ncut) clustering. Its performance was compared with those of two other previously reported clustering methods: k-means and fuzzy c-means (FCM) techniques, in terms of the detection accuracy and computational time. Both simulated perfusion data and data collected from 42 healthy human subjects were applied to investigate the feasibility of the proposed approach.

Results: In the simulation study, the partial volume effect (PVE) level, peak value (PV), time to peak (TTP), full width at half maximum (FWHM), area under AIF curve (AUC), root mean square error (RMSE) between the estimated AIF and true AIF, and M value given by [PV/(FWHM×TTP)] were 45.45, 4.2737, 29.92, 6.4563, 76.4836, 0.0519, and 0.0221 for Ncut-based AIF, 96.45, 3.8385, 31.74, 7.5133, 75.7364, 0.3295, and 0.0161 for FCM-based AIF, 91.18, 3.8990, 31.73, 7.4544, 76.0476, 0.3128, and 0.0165 for k-means-based AIF, 0, 4.4592, 29.51, 6.2016, 76.8669, 0, and 0.0244 for true AIF. In the clinical study, the mean PV, TTP, FWHM, AUC, M, error between estimated AIF and manual AIF were 1.7395, 30.95, 5.5923, 19.1081, 0.0397, and 0.4406 for Ncut-based AIF, 1.3629, 31.31, 6.8616, 17.9992, 0.0123, and 0.0846 for k-means-based AIF, 1.2101, 31.61, 7.1729, 16.6238, 0.0102, and 0.1016 for FCM-based AIF. The differences in PV, M, FWHM, and error reached a significant level (P = 0.032, 0.010, 0.003, and 0.002, respectively) between Ncut and k-means methods as well as between Ncut and FCM methods (P = 0.013, 0.008, 0.007, and 0.009, respectively). There was no significant difference in TTP between Ncut and each of the other two methods (P = 0.173 and 0.097, respectively). For AUC, a significant difference was found between Ncut and FCM algorithms (P = 0.025), but not between Ncut and k-means methods (P = 0.138). The mean execution time was 0.4406 for the Ncut method, 0.2649 for the k-means method, and 0.1371 for the FCM method, and the differences were significant both between Ncut and k-means methods (P = 0.002) and between Ncut and FCM methods (P = 0.004).

Conclusion: Ncut clustering yield AIFs more in line with the expected AIF, and might be preferred to FCM and k-means clustering methods sensitive to randomly selected initial centers.