The preservation of morphological features, such as protrusions and concavities, and of the topology of input shapes is important when establishing reference data for benchmarking segmentation algorithms or when constructing a mean or median shape. We present a contourwise topology-preserving fusion method, called shape-aware topology-preserving means (SATM), for merging complex simply connected shapes. The method is based on key point matching and piecewise contour averaging. Unlike existing pixelwise and contourwise fusion methods, SATM preserves topology and does not smooth morphological features. We also present a detailed comparison of SATM with state-of-the-art fusion techniques for the purpose of benchmarking and median shape construction. Our experiments show that SATM outperforms these techniques in terms of shape-related measures that reflect shape complexity, manifesting itself as a reliable method for both establishing a consensus of segmentation annotations and for computing mean shapes.

Masaryk University Brno Czech Republic

Zobrazit více v PubMed

Prasad, A. & Alizadeh, E. Cell form and function: interpreting and controlling the shape of adherent cells. Trends Biotechnol.37, 347–357 (2019). PubMed

Alizadeh, E. et al. Cellular morphological features are predictive markers of cancer cell state. Comput. Biol. Med.126, 104044 (2020). PubMed

Bodor, D. L., Pönisch, W., Endres, R. G. & Paluch, E. K. Of cell shapes and motion: The physical basis of animal cell migration. Dev. Cell52, 550–562 (2020). PubMed

Pascual-Vargas, P. et al. RNAi screens for Rho GTPase regulators of cell shape and YAP/TAZ localisation in triple negative breast cancer. Sci. Data4, 1–13 (2017). PubMed PMC

Kyykallio, H. et al. The density and length of filopodia associate with the activity of hyaluronan synthesis in tumor cells. Cancers12, 1908 (2020). PubMed PMC

Gut, D. et al. Use of superpixels for improvement of inter-rater and intra-rater reliability during annotation of medical images. Med. Image Anal.94, 103141 (2024). PubMed

Maier-Hein, L. et al. Why rankings of biomedical image analysis competitions should be interpreted with care. Nat. Commun.9, 5217 (2018). PubMed PMC

Maier-Hein, L. et al. Metrics reloaded: recommendations for image analysis validation. Nat. Methods21, 195–212 (2024). PubMed PMC

Kittler, J., Hatef, M., Duin, R. P. & Matas, J. On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell.20, 226–239 (1998).

Akbaş, C. E., Ulman, V., Maška, M., Jug, F. & Kozubek, M. Automatic fusion of segmentation and tracking labels. In Computer Vision–ECCV 2018 Workshops: Munich, Germany, September 8-14, 2018, Proceedings, Part VI 15, 446–454 (Springer, 2019).

Warfield, S. K., Zou, K. H. & Wells, W. M. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging23, 903–921 (2004). PubMed PMC

Warfield, S. K., Zou, K. H. & Wells, W. M. Validation of image segmentation by estimating rater bias and variance. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2006: 9th International Conference, Copenhagen, Denmark, October 1-6, 2006. Proceedings, Part II 9, 839–847 (Springer, 2006). PubMed

Commowick, O. & Warfield, S. K. A continuous STAPLE for scalar, vector, and tensor images: an application to DTI analysis. IEEE Trans. Med. Imaging28, 838–846 (2008). PubMed PMC

Akhondi-Asl, A. & Warfield, S. K. Simultaneous truth and performance level estimation through fusion of probabilistic segmentations. IEEE Trans. Med. Imaging32, 1840–1852 (2013). PubMed PMC

Langerak, T. R. et al. Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (SIMPLE). IEEE Trans. Med. Imaging29, 2000–2008 (2010). PubMed

Audelan, B., Hamzaoui, D., Montagne, S., Renard-Penna, R. & Delingette, H. Robust bayesian fusion of continuous segmentation maps. Med. Image Anal.78, 102398 (2022). PubMed

Wang, M. & Li, P. Label fusion method combining pixel greyscale probability for brain MR segmentation. Sci. Rep.9, 17987 (2019). PubMed PMC

Pena, C. H., Ren, T. I., Fernandez, P. D. M., Guerrero-Peña, F. A. & Cunha, A. An ensemble learning method for segmentation fusion. In 2022 International Joint Conference on Neural Networks (IJCNN), 1–6 (IEEE, 2022).

Karcher, H. Riemannian center of mass and mollifier smoothing. Commun. Pure Appl. Math.30, 509–541 (1977).

Bauer, M., Bruveris, M., Harms, P. & Møller-Andersen, J. A numerical framework for Sobolev metrics on the space of curves. SIAM J. Imag. Sci.10, 47–73 (2017).

Fletcher, P. T., Venkatasubramanian, S. & Joshi, S. Robust statistics on Riemannian manifolds via the geometric median. In 2008 IEEE Conference on Computer Vision and Pattern Recognition, 1–8 (IEEE, 2008).

Cunha, A. GEMS-geometric median shapes. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 1492–1496 (IEEE, 2019).

Ulman, V. et al. An objective comparison of cell-tracking algorithms. Nat. Methods14, 1141 (2017). PubMed PMC

Moshkov, N., Mathe, B., Kertesz-Farkas, A., Hollandi, R. & Horvath, P. Test-time augmentation for deep learning-based cell segmentation on microscopy images. Sci. Rep.10, 5068 (2020). PubMed PMC

Hsu, K. et al. Improving performance of deep learning models using 3.5 d u-net via majority voting for tooth segmentation on cone beam computed tomography. Sci. Rep.12, 19809 (2022). PubMed PMC

Yao, X., Song, Y. & Liu, Z. A robust combined weighted label fusion in multi-atlas pancreas segmentation. Multimed. Tools Appl.83, 70143–70167 (2024).

Athanasiou, G. et al. Enhancing medical image segmentation: Ground truth optimization through evaluating uncertainty in expert annotations. Mathematics11, 3771 (2023).

Zhang, L. et al. Learning from multiple annotators for medical image segmentation. Pattern Recogn.138, 109400 (2023). PubMed PMC

McSweeney, D. M. et al. Fusion contours as a source of segmentation training data: A simulation study. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), 1–6 (IEEE, 2023).

Klassen, E., Srivastava, A., Mio, M. & Joshi, S. H. Analysis of planar shapes using geodesic paths on shape spaces. IEEE Trans. Pattern Anal. Mach. Intell.26, 372–383 (2004). PubMed

Hang, H., Bauer, M., Mio, W. & Mander, L. Geometric and topological approaches to shape variation in ginkgo leaves. R. Soc. Open Sci.8, 210978 (2021). PubMed PMC

Melnikova, A. & Matula, P. Topology preserving segmentation fusion for cells with complex shapes. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 204–207 (IEEE, 2021).

Maška, M. et al. The cell tracking challenge: 10 years of objective benchmarking. Nat. Methods, 1–11 (2023). PubMed PMC

Wu, S. G. et al. A leaf recognition algorithm for plant classification using probabilistic neural network. In 2007 IEEE International Symposium on Signal Processing and Information Technology, 11–16 (IEEE, 2007).

Soille, P. Generalized geodesic distances applied to interpolation and shape description. Mathematical Morphology and its Applications to Image Processing, 193–200 (1994).

Matula, P., Kozubek, M. & Dvorák, V. Fast point-based 3-D alignment of live cells. IEEE Trans. Image Process.15, 2388–2396 (2006). PubMed

Brown, L. G. A survey of image registration techniques. ACM Comput. Surv. (CSUR)24, 325–376 (1992).

Jacquemet, G. et al. Filoquant reveals increased filopodia density during breast cancer progression. J. Cell Biol.216, 3387–3403 (2017). PubMed PMC

Barry, D. J., Durkin, C. H., Abella, J. V. & Way, M. Open source software for quantification of cell migration, protrusions, and fluorescence intensities. J. Cell Biol.209, 163–180 (2015). PubMed PMC

Lowekamp, B. C., Chen, D. T., Ibáñez, L. & Blezek, D. The design of SimpleITK. Front. Neuroinform.7, 45 (2013). PubMed PMC

Tucker, J. D. fdasrsf package. GitHub repository (2013).

Srivastava, A., Wu, W., Kurtek, S., Klassen, E. & Marron, J. S. Registration of functional data using fisher-rao metric. arXiv preprint http://arxiv.org/abs/1103.3817 (2011).

Tucker, J. D., Wu, W. & Srivastava, A. Generative models for functional data using phase and amplitude separation. Comput. Stat. Data Anal.61, 50–66 (2013).

Kendall, M. G. A new measure of rank correlation. Biometrika30, 81–93 (1938).