New discrepancy measures for segmentation evaluation

Goumeidane, Aicha Baya; Khamadja, Mohammed; Belaroussi, Boubakeur; Benoit-Cattin, Hugues; Odet, C.

doi:10.1109/icip.2003.1246704

Cited by 15 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An empirical discrepancy method can still be more general since the evaluation is based on contrasting the algorithm's output with an already computed reference. The number of pixels incorrectly classified as edge pixels or the number of incorrectly segmented pixels, their position and the number of regions are among the different discrepancy measures proposed in the literature (Baddeley, 1992;Goumeidane et al, 2003;Heyden, 1989;Huang and Dom, 1995;Lewis and Brown, 2001;Lim and Lee, 1990;Odet et al, 2002;Pratt, 1978;Rees et al, 2002;RomanRoldan et al, 2001;Strasters and Gerbrands, 1991;Weszka and Rosenfeld, 1978;Yasnoff and Bacus, 1984;Yasnoff et al, 1977). Additional discrepancy measures based on region features such as area, eccentricity or perimeter, among others, have also been considered (Zhang, 1995;Gerbrands, 1992, 1994).…”

Section: Discussion On General Work On Segmentation Performance Evalumentioning

confidence: 99%

On the use of the overlapping area matrix for image segmentation evaluation: A survey and new performance measures

Ortiz

Oliver

2006

Pattern Recognition Letters

View full text Add to dashboard Cite

Section: Discussion On General Work On Segmentation Performance Evalumentioning

confidence: 99%

On the use of the overlapping area matrix for image segmentation evaluation: A survey and new performance measures

Ortiz

Oliver

2006

Pattern Recognition Letters

View full text Add to dashboard Cite

“…Goumeidane et al [53] proposed an empirical discrepancy method that relies on the position of missegmented pixels ii), but excluding the features i), iii), and iv). Still, they obtained a reasonable measure of discrepancy between a segmented region and a reference region by a spatial overlay of these.…”

Section: E Methods For Segmentation Evaluationmentioning

confidence: 99%

A Unified Framework for Automated 3-D Segmentation of Surface-Stained Living Cells and a Comprehensive Segmentation Evaluation

Hodneland

Bukoreshtliev

Eichler

et al. 2009

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Abstract-This work presents a unified framework for whole cell segmentation of surface stained living cells from 3-D data sets of fluorescent images. Every step of the process is described, image acquisition, prefiltering, ridge enhancement, cell segmentation, and a segmentation evaluation. The segmentation results from two different automated approaches for segmentation are compared to manual segmentation of the same data using a rigorous evaluation scheme. This revealed that combination of the respective cell types with the most suitable microscopy method resulted in high success rates up to 97%. The described approach permits to automatically perform a statistical analysis of various parameters from living cells.

show abstract

“…Those measures are either edge or volume oriented. Although widely used for validation in general image processing [21,22], especially for edge-oriented segmentation algorithms, geometrical measures are less often used for medical applications, mostly because they are not sufficiently clinically intuitive, as for instance sensitivity and specificity are.…”

Section: Introductionmentioning

confidence: 99%

Statistical validation metric for accuracy assessment in medical image segmentation

et al. 2007

View full text Add to dashboard Cite

Objective Validation of medical image segmentation algorithms is an open question, considering variance of individual pathologies and the related clinical requirements for accuracy. In this paper, we propose a validation metric capable to distinguish between an over and under-segmentation and account for different clinical applications. Materials and methods In this paper, we propose a validation metric representing a tradeoff between sensitivity and specificity. The metric has an advantage of differentiating between an over or under-segmentation which is an important feature for validating large sets of segmentation results, as human inspection is exhausting and time consuming. Although it is oriented to the accuracy measurement it is also closely related to the robustness of a method. Results Features of the metrics are analyzed alongside their medical impact. A set of numerical simulations is performed in order to compare the proposed metric with standardly used discrepancy measures. The metric is illustrated with a clinical case study, presenting accuracy assessment of an algorithm for calvarial tumor segmentation, validated on six patients.

show abstract

New discrepancy measures for segmentation evaluation

Cited by 15 publications

References 14 publications

On the use of the overlapping area matrix for image segmentation evaluation: A survey and new performance measures

On the use of the overlapping area matrix for image segmentation evaluation: A survey and new performance measures

A Unified Framework for Automated 3-D Segmentation of Surface-Stained Living Cells and a Comprehensive Segmentation Evaluation

Statistical validation metric for accuracy assessment in medical image segmentation

Contact Info

Product

Resources

About