Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

BMC Medical Imaging

Software

Allan Hanbury¹  Abdel Aziz Taha¹ 

[1] TU Wien, Institute of Software Technology and Interactive Systems, Favoritenstrasse 9-11, A-1040, Vienna, Austria;

关键词: Evaluation metrics;    Evaluation tool;    Medical volume segmentation;    Metric selection;   

DOI  :  10.1186/s12880-015-0068-x

 received in 2014-12-15, accepted in 2015-07-09,  发布年份 2015

来源: Springer

【 摘 要 】

BackgroundMedical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by existing metrics.ResultFirst we present an overview of 20 evaluation metrics selected based on a comprehensive literature review. For fuzzy segmentation, which shows the level of membership of each voxel to multiple classes, fuzzy definitions of all metrics are provided. We present a discussion about metric properties to provide a guide for selecting evaluation metrics. Finally, we propose an efficient evaluation tool implementing the 20 selected metrics. The tool is optimized to perform efficiently in terms of speed and required memory, also if the image size is extremely large as in the case of whole body MRI or CT volume segmentation. An implementation of this tool is available as an open source project.ConclusionWe propose an efficient evaluation tool for 3D medical image segmentation using 20 evaluation metrics and provide guidelines for selecting a subset of these metrics that is suitable for the data and the segmentation task.

【 授权许可】

CC BY   
© Taha and Hanbury. 2015

【 图 表 】

12864_2017_3527_Article_IEq6.gif

12914_2017_112_Article_IEq4.gif

12864_2017_4030_Article_IEq8.gif

12864_2016_3098_Article_IEq57.gif

12864_2017_4030_Article_IEq7.gif

12864_2017_4030_Article_IEq6.gif

12864_2017_4030_Article_IEq5.gif

12864_2017_4030_Article_IEq4.gif

12864_2017_4030_Article_IEq3.gif

12864_2017_4017_Article_IEq2.gif

12864_2017_4020_Article_IEq42.gif

12888_2016_848_Article_IEq2.gif

12888_2016_848_Article_IEq1.gif

12864_2015_2296_Article_IEq158.gif

12864_2017_4020_Article_IEq39.gif

12864_2017_4020_Article_IEq38.gif

12864_2017_4020_Article_IEq36.gif

12864_2017_3655_Article_IEq27.gif

12864_2015_2198_Article_IEq33.gif

12864_2017_3655_Article_IEq25.gif

12864_2015_2163_Article_IEq3.gif

12864_2017_3655_Article_IEq23.gif

12864_2015_2198_Article_IEq30.gif

12864_2017_4225_Article_IEq2.gif

12864_2017_3821_Article_IEq4.gif

12864_2016_3440_Article_IEq22.gif

12864_2017_3655_Article_IEq17.gif

12864_2017_3601_Article_IEq1.gif

12864_2016_2682_Article_IEq36.gif

12880_2015_Article_68_TeX2GIF_IEq4.gif

12864_2017_3742_Article_IEq2.gif

12864_2016_2821_Article_IEq16.gif

12880_2015_Article_68_TeX2GIF_IEq1.gif