Statistical validation of image segmentation quality based on a spatial overlap index.

By Kelly H. Zou, Simon Keith Warfield, A. Bharatha, C. Tempany, M. Kaus, Steven Haker, William M. Wells, F. Jolesz, Ron Kikinis. Academic Radiology, 2004

1,839 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Pulmonary and Respiratory Medicine, Radiation

View Paper: https://www.semanticscholar.org/paper/77a1ca2df0871df21f85c2c2ca110946e350cfa5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Pulmonary and Respiratory Medicine

In Radiation

I. E. El Naqa

Citations in the corpus

Complex Wavelet Structural Similarity: A New Image Similarity Index (2009, methodology): “The Dice similarity coefficient [1] is commonly used (e.g., in medical imaging studies) to quantify the degree of overlap between objects in two binary images (e.g., two segmentations, [ 19 ], [20]).”
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) (2015, background): “…example deals with brain extraction (“masking”) [68]), although many of the validation frameworks that are used to compare different seg-menters and segmentation algorithms, such as STAPLE [69], [70], have been developed for applications in brain imaging, or even brain tumor segmentation [71].”
Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool (2015, methodology): “Zou et al. [1] used the DICE as a measure of the reproducibility as a statistical validation of manual annotation where segmenters repeatedly annotated the same MRI image, then the pair-wise overlap of the repeated segmentations is calculated using the DICE , which is defined by The Jaccard index (…”
User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability (2006, methodology): “To confirm this finding quantitatively, we perform an ANOVA experiment adopted from Zou et al. (2004), who studied repeatability in the context of pre- and postoperative prostate segmentation.”
PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques (2010, methodology): “Well-established figures of merit known to have a large influence on many types of task performance are generally used to assess the performance of image segmentation procedures [168, 169].”
Generalized Overlap Measures for Evaluation and Validation in Medical Image Analysis (2006, background): “[24] suggest a fuller statistical framework for the DSC.”
Non-local Deep Features for Salient Object Detection (2017, methodology): “Motivated by the signiﬁcant applications of Dice loss or IoU boundary loss in medical image segmentation [53, 40, 34], our proposed method approximates the penalty on boundary length of Eq.”