Title :
Empirical comparison of cell segmentation algorithms using an annotated dataset
Author_Institution :
Dept. of Inf. Technol. & Electr. Eng., Queensland Univ., Brisbane, Qld., Australia
Abstract :
Three popular algorithms (Viterbi active contour, watershed and a thresholding-based method) for segmenting cell nuclei are compared empirically. This is achieved via a large (20,000) image dataset that has been annotated by three independent nonexpert observers. The Hausdorff distance is used as an error metric and Chalana´s modified Williams´ index is used to compare each algorithm´s output to the observers´ data.
Keywords :
image segmentation; Hausdorff distance; Viterbi active contour; annotated dataset; cell segmentation algorithms; thresholding-based method; Active contours; Humans; Image edge detection; Image segmentation; Information processing; Information technology; Performance evaluation; Robustness; Signal processing; Viterbi algorithm;
Conference_Titel :
Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
Print_ISBN :
0-7803-7750-8
DOI :
10.1109/ICIP.2003.1246871
