Abstract
Effective extraction and visualization of complex target features from volume data are an important task, which allows the user to analyze and get insights of the complex features, and thus to make reasonable decisions. Some state-of-the-art techniques allow the user to perform such a task by interactively exploring in multiple linked parameter space views. However, interactions in the parameter space using trial and error may be unintuitive and time-consuming. Furthermore, switching between multiple views may be distracting. Some other state-of-the-art techniques allow the user to extract the complex features by directly interacting in the data space and subsequently visualize the extracted features in 3D view. They are intuitive and effective techniques for the user, as the user is familiar with the data space, and they do not require many trial and error to get the features. However, these techniques usually generate less accurate features. In this paper, we proposed a semiautomatic Gaussian mixture model-based target feature extraction and visualization method, which allows the user to quickly label single or multiple complex target features using lasso on two slices of the volume data and subsequently visualize the automatically extracted features in 3D view. We have applied it to various univariate or multivariate volume datasets from the medical field to demonstrate its effectiveness. Moreover, we have performed both qualitative and quantitative experiments to compare its results against the results from two state-of-the-art techniques and the ground truths. The experimental results showed that our method is able to generate the closest results to the ground truth.
Graphic abstract
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bao XK, Wang YH, Cheng ZL, Tu CH, Zhou FF, Chen BQ (2018) Analogy-based volume exploration using ellipsoidal Gaussian transfer functions. J Vis 21:511–523
Cai LL, Nguyen BP, Chui CK, Ong SH (2015) Rule-enhanced transfer function generation for medical volume visualization. Comput Graph Forum 34(3):121–130
Cai LL, Nguyen BP, Chui CK, Ong SH (2017) A two-level clustering approach for multidimensional transfer function specification in volume visualization. Vis Comput 33(2):163–177
Chuang KS, Tzeng HL, Chen S, Wu J, Chen TJ (2006) Fuzzy c-means clustering with spatial information for image segmentation. Comput Med Imaging Graph 30:9–15
Correa CD, Ma KL (2009) The occlusion spectrum for volume visualization and classification. IEEE Trans Vis Comput Graph 15(6):1465–1472
Dijkstra EW (1959) A note on two problems in connexion with graphs. Numetische Mathematik 1:269–271
Dutta S, Shen HW (2016) Distribution driven extraction and tracking of features for time-varying data analysis. IEEE Trans Vis Comput Graph 22(1):837–846
Guo H, Xiao H, Yuan X (2011) Multi-dimensional transfer function design based on flexible dimension projection embedded in parallel coordinates. In: PacificVis, pp 19–26
Haidacher M, Patel D, Bruckner S, Kanitsar A, Groller M (2010) Volume visualization based on statistical transfer-function spaces. In: PacificVis, pp 17–24
Hladuvka J, Konig A, Groller E (2000) Curvature-based transfer function for direct volume rendering. In: Proceedings of spring conference on computer graphics, vol 16, pp 58–65
Johnson CR, Huang J (2009) Distribution-driven visualization of volume data. IEEE Trans Vis Comput Graph 15(5):734–746
Kim HS, Schulze JP, Cone AC, Sosinsky GE, Martone ME (2010) Dimensionality reduction on multi-dimensional transfer function for multi-channel volume data sets. Inf Vis 9(3):167–180
Kindlmann G, Durkin JW (1998) Semi-automatic generation of transfer functions for direct volume rendering. In: Proceedings of IEEE symposium on volume visualization, pp 79–86
Kniss J, Wang G (2011) Supervised manifold distance segmentation. IEEE Trans Vis Comput Graph 17(11):1637–1649
Liu S, Levine J, Bremer P, Pascucci V (2012) Gaussian mixture model based volume visualization. In: IEEE symposium on large-scale data analysis and visualization, pp 73–7
Lp CY, Varshney A, Jaja J (2012) Hierarchical exploration of volumes using multilevel segmentation of the intensity-gradient histograms. IEEE Trans Vis Comput Graph 18(12):2355–2363
Maier O, Wilms M, Gablentz JVD, Kramer UM, Munte TF, Handels H (2015) Extra tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences. J Neurosci Methods 240:89–100
Menze BH et al (2015) The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans Med Imaging 34(10):1993–2024
Nguyen BP, Tay WL, Chui CK, Ong SH (2012) A clustering-based system to automate transfer function design for medical image visualization. Vis Comput 28(2):181–191
Obermaier H, Joy KI (2013) Local data models for probabilistic transfer function design. In: EuroVis, pp 43–47
Sereda P, Bartroli AV, Serlie IWO, Gerritsen FA (2006) Visualization of boundaries in volumetric data sets using LH histograms. IEEE Trans Vis Comput Graph 12(2):208–218
Tzeng FY, Lum EB, Ma KL (2005) An intelligent system approach to higher-dimensional classification of volume data. IEEE Trans Vis Comput Graph 11(3):273–284
Vania M, Mureja D, Lee D (2019) Automatic spine segmentation from CT images using convolutional neural network via redundant generation of class labels. J Comput Des Eng 6(2):224–232
Wang YH, Chen W, Zhang J, Dong TX, Shan GH, Chi XB (2011) Efficient volume exploration using the Gaussian mixture model. IEEE Trans Vis Comput Graph 17(11):1560–1573
Wang L, Zhao X, Kaufman AE (2012a) Modified dendrogram of attribute space for multidimensional transfer function design. IEEE Trans Vis Comput Graph 18(1):121–131
Wang Y, Zhang J, Lehmann D, Theisel H, Chi X (2012b) Automating transfer function design with valley cell-based clustering of 2D density plots. In: EuroVis, pp 1295–1304
Wesarg S, Kirschner M (2009) 3D visualization of medical image data employing 2D histograms. In: Proceedings of second international conference in visualization, pp 153–158
Wolfgang B (2014) Applied medial image processing: a basic course, 2nd edn. CRC Press, Boca Raton
Zhang HJ, Qu DZ, Liu QL, Shang Q, Hou YF, Shen HW (2018) Uncertainty visualization for variable associations analysis. Vis Comput 34:531–549
Zhao X, Kaufman A (2010) Multi-dimensional reduction and transfer function design using parallel coordinates. In: Proceedings of the 8th IEEE international conference on volume graphics, pp 69–76
Zhou L, Hansen C (2014) GuideME: slice-guided semiautomatic multivariate exploration of volumes. Comput Graph Forum 33(3):151–160
Acknowledgements
This work was supported by National Natural Science Foundation of China under Grants 61902350, 61972355, 6197070377, by Natural Science Foundation of Zhejiang Province under Grant LY20F020025, LY18F020035 and by Basic Welfare Research Project of Zhejiang Province under Grant LGG19F020012.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ma, J., Chen, J., Chen, L. et al. Gaussian mixture model-based target feature extraction and visualization. J Vis 24, 545–563 (2021). https://doi.org/10.1007/s12650-020-00724-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12650-020-00724-0