Comparison of algorithms for ultrasound image segmentation without ground truth
Abstract
Image segmentation is a pre-requisite to medical image analysis. A variety of segmentation algorithms have been proposed, and most are evaluated on a small dataset or based on classification of a single feature. The lack of a gold standard (ground truth) further adds to the discrepancy in these comparisons. This work proposes a new methodology for comparing image segmentation algorithms without ground truth by building a matrix called region-correlation matrix. Subsequently, suitable distance measures are proposed for quantitative assessment of similarity. The first measure takes into account the degree of region overlap or identical match. The second considers the degree of splitting or misclassification by using an appropriate penalty term. These measures are shown to satisfy the axioms of a quasi-metric. They are applied for a comparative analysis of synthetic segmentation maps to show their direct correlation with human intuition of similar segmentation. Since ultrasound images are difficult to segment and usually lack a ground truth, the measures are further used to compare the recently proposed spectral clustering algorithm (encoding spatial and edge information) with standard k-means over abdominal ultrasound images. Improving the parameterization and enlarging the feature space for k-means steadily increased segmentation quality to that of spectral clustering.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The region-correlation matrix method [30] cannot evaluate segmentation performance of a particular method on a particular image independently.
“Another work by [30] has quantitatively evaluated the performance of several segmentation algorithms by regioncorrelation matrix. The limitation of this work is that it cannot evaluate the segmentation performance of a particular method on a particular image independently.”
From Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth (2017) · cites this paper as [30]
Cites
A tutorial on spectral clustering
von Luxburg, U. (2007) · Statistics and Computing · doi:10.1007/s11222-007-9033-z · Cited by 10,519 · see citing works
On Spectral Clustering: Analysis and an algorithm
Ng, A. Y., Jordan, M. I., & Weiss, Y. (2001) · Cited by 8,159 · see citing works
Lehoucq, R. B., Sorensen, D. C., & Yang, C. (1998) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9780898719628 · Cited by 2,971 · see citing works
Haralick, R. M., & Shapiro, L. G. (1985) · Computer Vision Graphics and Image Processing · doi:10.1016/s0734-189x(85)90153-7 · Cited by 2,256 · see citing works
Warfield, S. K., Zou, K. H., & Wells, W. M. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.828354 · Cited by 2,072 · see citing works
Ultrasound image segmentation: a survey
Noble, J. A., & Boukerroui, D. (2006) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2006.877092 · Cited by 1,157 · see citing works
Contour and Texture Analysis for Image Segmentation
Malik, J., Belongie, S., Leung, T., & Shi, J. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011174803800 · Cited by 1,107 · see citing works
A survey on evaluation methods for image segmentation
Zhang, Y. J. (1996) · Pattern Recognition · doi:10.1016/0031-3203(95)00169-7 · Cited by 1,060 · see citing works
Multiclass spectral clustering
Yu, & Shi (2003) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238361 · Cited by 983 · see citing works
Image segmentation evaluation: A survey of unsupervised methods
Zhang, H., Fritts, J. E., & Goldman, S. A. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.08.003 · Cited by 963 · see citing works
Consistency of spectral clustering
von Luxburg, U., Belkin, M., & Bousquet, O. (2008) · The Annals of Statistics · doi:10.1214/009053607000000640 · Cited by 540 · see citing works
A framework for evaluating image segmentation algorithms
Udupa, J. K., LeBlanc, V. R., Zhuge, Y., Imielińska, C., Schmidt, H. J., Currie, L. M., Hirsch, B. E., & Woodburn, J. (2006) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2005.12.001 · Cited by 410 · see citing works
A Metric and an Ordering on Sets
Restle, F. (1959) · Psychometrika · doi:10.1007/bf02289843 · Cited by 125 · see citing works
Content-based image retrieval in medical applications: a novel multistep approach
Lehmann, T., WEIN, B. B., Dahmen, J., Bredno, J., Vogelsang, F., & Kohnen, M. (1999) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.373563 · Cited by 119 · see citing works
On the Approximability of Numerical Taxonomy (Fitting Distances by Tree Metrics)
Agarwala, R., Bafna, V., Farach-Colton, M., Paterson, M., & Thorup, M. (1998) · SIAM Journal on Computing · doi:10.1137/s0097539795296334 · Cited by 114 · see citing works
Song, Y., Chen, W.-Y., Bai, H., Lin, C., & Chang, E. Y. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87481-2_25 · Cited by 83 · see citing works
The CLEF 2005 Automatic Medical Image Annotation Task
Deselaers, T., Müller, H., Clough, P. D., Ney, H., & Lehmann, T. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-0007-y · Cited by 68 · see citing works
Automatic medical image annotation in ImageCLEF 2007: Overview, results, and discussion
Deselaers, T., Deserno, T. M., & Müller, H. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.03.001 · Cited by 53 · see citing works
Self-citationSegmentation of Ultrasound Image Based on Texture Feature and Graph Cut
Chang-ming, Z., Gu, G., Hai-bo, L., Jing, S., & Yu, H. (2008) · doi:10.1109/csse.2008.294 · Cited by 30 · see citing works
Evaluation of uterine cervix segmentations using ground truth from multiple experts
Shiri Gordon, A., Lotenberg, S., Long, L. R., Antani, S., Jerónimo, J., & Greenspan, H. K. (2009) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2008.12.002 · Cited by 29 · see citing works
Spectral Clustering Algorithms for Ultrasound Image Segmentation
Archip, N., Rohling, R. N., Cooperberg, P. L., Tahmasebpour, H., & Warfield, S. K. (2005) · Lecture notes in computer science · doi:10.1007/11566489_106 · Cited by 21 · see citing works
Two-Dimensional Fuzzy Clustering for Ultrasound Image Segmentation
Yu, J., Wang, Y., Chen, P., & Xu, H. (2007) · International Conference on Bioinformatics and Biomedical Engineering · doi:10.1109/icbbe.2007.157 · Cited by 7 · see citing works
Flagged first, then by citations
1 of the 23 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth
Valindria, V. V., Lavdas, I., Bai, W., Kamnitsas, K., Aboagye, E. O., Rockall, A. G., Rueckert, D., & Glocker, B. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2665165 · Cited by 152 · see citing works
Li, J., Udupa, J. K., Tong, Y., Wang, L., & Torigian, D. A. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.101980 · Cited by 10 · see citing works
Comparative Analysis of Temporal Segmentation Methods of Video Sequences
Saval-Calvo, M., Azorín-López, J., & Fuster-Guilló, A. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-2672-0.ch003 · Cited by 4 · see citing works
CASAD -- Computer-Aided Sonography of Abdominal Diseases - the concept of joint technique impact
Deserno, T., Burtseva, L., Secrieru, I., & Popcova, O. (2010) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 2 · see citing works
Self-citation
- Authors
- Sikka, K., & Deserno, T. M.
- Affiliations
- Indian Institute of Technology Guwahati (IN)
- RWTH Aachen University (DE)
- ORCID
- Sikka, Karan
- Venue
- SPIE Proceedings
- Publisher
- SPIE
- Published
- 2010-03-04
- Volume
- 7627
- Pages
- 76271C
- ISSN
- 0277-786X (ISSN-L)
- OpenAlex
- W2107468972
- Cited by
- 4
- References
- 23
- Citations by year
- 2021: 1 · 2017: 1 · 2012: 1
- FWCI
- 0.55
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (publishedVersion)
- RWTH Publications (RWTH Aachen) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Clustering Algorithms Research
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Ultrasound in Clinical Applications
- Keywords
- ultrasound image segmentation, quasi-metrics, distance measures, spectral clustering, K-means clustering, abdominal ultrasound
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
