An Efficient Method for Detection of Outliers in Tracer Curves Derived from Dynamic Contrast-Enhanced Imaging

Figure 3

An example to illustrate the clustering process, where “x” stands for the data point of interest with the local neighborhood consisting of 4 points to the left and right of “x” and circles and squares represent the two clusters: (a) initialization of the first cluster, (b) next three datasets classified into the first cluster, (c) the fifth data initialized to the second cluster, and (d) the rest classified into the first cluster.

(a)

(b)

(c)

(d)