Real-time adaptive clustering of flow cytometric data

Pattern recognition in flow cytometry

“…Although ART does not appear to have been used for analysis of flow cytometry data, a similar approach has: real-time adaptive clustering (RTAC) (33,86). Like ART, RTAC does not make assumptions about the number of clusters, and it is adaptive to dynamically changing conditions.…”

Concept learning by fuzzy k-NN classification and relevance feedback for efficient image retrieval

“…We compared 11 similarity measures including L 1 , L 2 , L 1 (Theodoridis & Koutroumbas, 1999), angular (Androutsos, Plataniotis, & Venetsanopoulos, 1999), Canberra (Androutsos et al, 1999), Czekanowski (Theodoridis & Koutroumbas, 1999), v 2 (Antani et al, 2000), inner product (Theodoridis & Koutroumbas, 1999), Fu (Fu, Yang, Braylan, & Benson, 1993), Mahalanobis (Rubner et al, 2001), and weighted-mean-variance, WMV (Manjunath & Ma, 1996), for color histogram, edge histogram and Gabor features on the basis of classification rate [Nezam05a]. Among these measures, the v 2 was the best for color and Gabor features, while Euclidian distance performed better for edge histogram (Fig.…”

Comparison of five clustering algorithms to classify phytoplankton from flow cytometry data

“…There are some clustering approaches that do not require the number of clusters to be specified in advance, e.g., density clustering (23) and adaptive clustering (24). Density clustering is a nonparametric, noniterative statistical method that essentially examines the local event density (based on histogram counts) to determine modes, and then regions of monotonically decreasing density around each of these are grouped into a cluster (23).…”

“…However, a user-specified threshold determines the size of clusters, which is subjective. Real-time adaptive clustering is an ANN approach in which the data pattern for each cell is presented to the network and then allocated to a cluster of similar patterns (24). When a pattern is not similar to any existing cluster, it is allocated to a new cluster.…”

“…In future research, it would be valuable to compare AD with other clustering approaches that have been used with flow cytometric data including density clustering (23), real-time adaptive clustering (24), and Kohonen selforganizing maps (SOMs) (25)(26)(27). The first two approaches are important because they do not require specification of the number of clusters.…”