Robust texture analysis via optimal mass transport: Application to medical images classification Conference Paper
| Authors: | Belkhatir, Z.; Iyer, A.; Mathews, J. C.; Pouryahya, M.; Nadeem, S.; Deasy, J. O.; Apte, A. P.; Tannenbaum, A. R. |
| Title: | Robust texture analysis via optimal mass transport: Application to medical images classification |
| Conference Title: | 8th International Conference on Engineering and Emerging Technologies (ICEET 2022) |
| Abstract: | The emerging field of radiomics, which consists of transforming standard-of-care images into quantifiable scalar statistics, endeavors to reveal the information hidden in these macroscopic images. This field of research has found different applications ranging from phenotyping and tumor classification to outcome prediction and treatment planning. Texture analysis, which often consists of reducing spatial texture matrices to summary scalar features, has been shown to be important in many of the later applications. However, as pointed out in many studies, some of the derived texture statistics are strongly correlated and tend to contribute redundant information; and are also sensitive to the parameters used in their computation, e.g., the number of gray intensity levels. In the present study, we propose new set of spatial texture features that consider texture matrices in general, with an emphasis here on gray-level co-occurrence matrix (GLCM), as non-parametric multivariate objects. The proposed modeling approach avoids evaluating redundant and strongly correlated features and also prevents the feature processing steps. Then, via the Wasserstein distance from optimal mass transport theory, we propose to compare these spatial objects to identify computerized tomography slices with dental artifacts in head and neck cancer. We demonstrate the robustness of the proposed classification approach with respect to the GLCM extraction parameters and the size of the training set. Comparisons with the random forest classifier, which is constructed on scalar texture features, demonstrate the efficiency and robustness of the proposed algorithm. © 2022 IEEE. |
| Keywords: | computerized tomography; medical imaging; texture features; matrix; texture analysis; textures; statistical mechanics; classification (of information); computation theory; standard of cares; gray-level co-occurrence matrix; image classification; optimal mass transport; matrix algebra; spatial texture; image texture; grey-level co-occurrence matrixes; medical image classification; transport applications |
| Journal Title | Conference Proceedings ICEET 2022 |
| Conference Dates: | 2022 Oct 27-28 |
| Conference Location: | Kuala Lumpar, Malaysia |
| ISBN: | 978-1-6654-9106-8 |
| Publisher: | Institute of Electrical and Electronics Engineers Inc. |
| Date Published: | 2022-01-01 |
| Language: | English |
| DOI: | 10.1109/iceet56468.2022.10007100 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Conference Paper -- Export Date: 1 March 2023 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work