A Quantitative Object-Level Metric for Segmentation Performance and Its Application to Cell Nuclei

Laura E. Boucheron 1,2, Neal R. Harvey 2, and B.S. Manjunath 1
1 University of California Santa Barbara, Electrical and Computer Engineering,
Santa Barbara, CA 93106-9560
2 Los Alamos National Laboratory, Space and Remote Sensing Sciences, P.O. Box
1663, Los Alamos, NM 87545


We present an object-level metric for segmentation performance which was developed to quantify both over- and under-segmentation errors, as well as to penalize segmentations with larger deviations in object shape. This metric is applied to the problem of segmentation of cell nuclei in routinely stained H&E histopathology imagery. We show the correspondence between the metric terms and qualitative observations of segmentation quality, particularly the presence of over- and under-segmentation. The computation of this metric does not require the use of any point-to-point or region-to-region correspondences but rather simple computations using the object mask from both the segmentation and ground truth.
[PDF] [BibTex]
Laura E. Boucheron, Neal R. Harvey and B.S. Manjunath,
International Symposium on Visual Computing (ISVC), pp. 208-219, Lake Tahoe, Nevada/California, Nov. 2007.
Node ID: 512 , DB ID: 319 , VRLID: 186a , Lab: VRL , Target: Proceedings
Subject: [Object-Based Retrieval] « Look up more