Translator Disclaimer
Presentation + Paper
15 March 2019 Quantitative and qualitative methods for efficient evaluation of multiple 3D organ segmentations
Author Affiliations +
Quantitative comparison of automatic results for multi-organ segmentation by means of Dice scores often does not yield satisfactory results. It is especially challenging, when reference contours may be prone to errors. We developed a novel approach that analyzes regions of high mismatch between automatic and reference segmentations. We extract various metrics characterizing these mismatch clusters and compare them to other metrics derived from volume overlap and surface distance histograms by correlating them with qualitative ratings from clinical experts. We show that some novel features based on the mismatch sets or surface distance histograms performed better than the Dice score. We also show how the mismatch clusters can be used to generate visualizations to reduce the workload for visual inspection of segmentation results. The visualizations directly compare reference to automatic result at locations of high mismatch in orthogonal 2D views and 3D scenes zoomed to the appropriate positions. This can make it easier to detect systematic problems of an algorithm or to compare recurrent error patterns for different variants of segmentation algorithms, such as differently parameterized or trained CNN models.
Conference Presentation
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Volker Dicken, Annika Hänsch, Jan Moltz, Benjamin Haas, Thomas Coradi, Tomasz Morgas, and Jan Klein "Quantitative and qualitative methods for efficient evaluation of multiple 3D organ segmentations", Proc. SPIE 10949, Medical Imaging 2019: Image Processing, 1094914 (15 March 2019);

Back to Top