Key result
K-means analysis yielded more accurate and robust arterial input function results compared to the fuzzy c-means method, despite a longer execution time.
Why the study?
Does the K-means clustering algorithm improve the accuracy and robustness of automated arterial input function detection compared to fuzzy c-means in cerebral perfusion imaging?
Does the K-means clustering algorithm improve the accuracy and robustness of automated arterial input function detection compared to fuzzy c-means in cerebral perfusion imaging?
The K-means clustering algorithm provides more accurate and robust automated detection of the arterial input function for cerebral perfusion quantification compared to fuzzy c-means.
May warrant testing K-means AIF detection in perfusion workflows; leaves open clinical adoption pending prospective validation.
The arterial input function (AIF) plays a crucial role in the quantification of cerebral perfusion parameters. The traditional method for AIF detection is based on manual operation, which is time-consuming and subjective. Two automatic methods have been reported that are based on two frequently used clustering algorithms: fuzzy c-means (FCM) and K-means. However, it is still not clear which is better for AIF detection. Hence, we compared the performance of these two clustering methods using both simulated and clinical data. The results demonstrate that K-means analysis can yield more accurate and robust AIF results, although it takes longer to execute than the FCM method. We consider that this longer execution time is trivial relative to the total time required for image manipulation in a PACS setting, and is acceptable if an ideal AIF is obtained. Therefore, the K-means method is preferable to FCM in AIF detection.
No takes yet. Share an insight, caveat, or question.
Yin et al. (2014) studied Arterial Input Function (AIF) detection for cerebral perfusion. K-means algorithm vs. Fuzzy c-means (FCM) algorithm was evaluated on Accuracy and robustness of AIF detection. K-means analysis yielded more accurate and robust arterial input function results compared to the fuzzy c-means method, despite a longer execution time.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: