We introduce a pointwise multiscale texture operator providing a mathematically grounded and interpretable description of how local image context evolves across observation scales. The operator is defined through the scale evolution of a contextual multiscale signature derived from Gaussian scale-space representations, thereby establishing direct connections with diffusion processes and multiresolution analysis. This formulation yields a stable descriptor of texture transitions that is robust to moderate noise, blurring, and acquisition variability, while remaining independent of any specific segmentation strategy. As a demonstration of its practical utility, we embed the proposed operator within a texture-coherence-driven region-growing framework for image segmentation. The resulting algorithm is dimension independent, computationally tractable, and does not rely on training data or complex architectural design. We illustrate its performance on 3D cone-beam computed tomography (CBCT) datasets, where it enables coherent segmentation and volumetric reconstruction of the dental pulp chamber under clinically relevant conditions involving low contrast, partial volume effects, and heterogeneous textures. Beyond this specific application, the proposed operator constitutes a general framework for multiscale texture analysis and structural characterization, particularly suited to imaging scenarios where interpretability, robustness to acquisition degradation, and limited annotated data are critical.
Citation: C. Coronado Gallardo, C. Fernández García, I. Suazo, J. A. Vega, Z. Fernández Muñiz. A pointwise contextual multiscale texture operator and its application to 3D medical image segmentation[J]. AIMS Mathematics, 2026, 11(5): 13530-13566. doi: 10.3934/math.2026557
We introduce a pointwise multiscale texture operator providing a mathematically grounded and interpretable description of how local image context evolves across observation scales. The operator is defined through the scale evolution of a contextual multiscale signature derived from Gaussian scale-space representations, thereby establishing direct connections with diffusion processes and multiresolution analysis. This formulation yields a stable descriptor of texture transitions that is robust to moderate noise, blurring, and acquisition variability, while remaining independent of any specific segmentation strategy. As a demonstration of its practical utility, we embed the proposed operator within a texture-coherence-driven region-growing framework for image segmentation. The resulting algorithm is dimension independent, computationally tractable, and does not rely on training data or complex architectural design. We illustrate its performance on 3D cone-beam computed tomography (CBCT) datasets, where it enables coherent segmentation and volumetric reconstruction of the dental pulp chamber under clinically relevant conditions involving low contrast, partial volume effects, and heterogeneous textures. Beyond this specific application, the proposed operator constitutes a general framework for multiscale texture analysis and structural characterization, particularly suited to imaging scenarios where interpretability, robustness to acquisition degradation, and limited annotated data are critical.
| [1] | R. C. Gonzalez, R. E. Woods, Digital image processing, New York: Pearson, 2018. |
| [2] | P. Soille, Morphological image analysis: principles and applications, Berlin: Springer, 1999. |
| [3] |
D. Mumford, J. Shah, Optimal approximations by piecewise smooth functions and associated variational problems, Commun. Pure Appl. Math., 42 (1989), 577–685. https://doi.org/10.1002/cpa.3160420503 doi: 10.1002/cpa.3160420503
|
| [4] |
A. Chambolle, Image segmentation by variational methods: Mumford and Shah functional and the discrete approximations, SIAM J. Appl. Math., 55 (1995), 827–863. https://doi.org/10.1137/S0036139993257132 doi: 10.1137/S0036139993257132
|
| [5] |
L. Alvarez, P. L. Lions, J. M Morel, Image selective smoothing and edge detection by nonlinear diffusion (Ⅱ), SIAM J. Numer. Anal., 29 (1992), 845–866. https://doi.org/10.1137/0729052 doi: 10.1137/0729052
|
| [6] | S. Mallat, A wavelet tour of signal processing, San Diego: Academic Press, 1999. |
| [7] | G. Aubert, P. Kornprobst, Mathematical problems in image processing: partial differential equations and the calculus of variations, Applied Mathematical Sciences, Vol. 147, New York: Springer, 2006. https://doi.org/10.1007/978-0-387-44588-5 |
| [8] |
Y. Yu, C. Wang, Q. Fu, R. Kou, F. Huang, B. Yang, et al., Techniques and challenges of image segmentation: a review, Electronics, 12 (2023), 1199. https://doi.org/10.3390/electronics12051199 doi: 10.3390/electronics12051199
|
| [9] |
M. L. Slim, R. Jacobs, R. M. de Souza Leal, R. C. Fontenele, AI-driven segmentation of the pulp cavity system in mandibular molars on CBCT images using convolutional neural networks, Clin. Oral Invest., 28 (2024), 650. https://doi.org/10.1007/s00784-024-06009-2 doi: 10.1007/s00784-024-06009-2
|
| [10] |
L. Hernández-Alvarez, I. Vila-García, Z. Fernández-Muñiz, A. Cernea, L. C. Hernández-González, T. Cobo, et al., Measuring dental chamber volume with DICOM images from cone-beam computed tomography can be improved with a simple algorithm, Appl. Sci., 14 (2024), 5365. https://doi.org/10.3390/app14135365 doi: 10.3390/app14135365
|
| [11] |
F. Akbarizadeh, B. M. Tabrizi, K. Fereidouni, M. M. K. Mazidi, Evaluation of the accuracy of age estimation based on ratio of pulp chamber to crown volume of the anterior teeth: a CBCT study, Forensic Sci. Int., 377 (2025), 112610. https://doi.org/10.1016/j.forsciint.2025.112610 doi: 10.1016/j.forsciint.2025.112610
|
| [12] |
R. M. Haralick, L. G. Shapiro, Image segmentation techniques, Comput. Vision Graphics Image Process., 29 (1985), 100–132. https://doi.org/10.1016/S0734-189X(85)90153-7 doi: 10.1016/S0734-189X(85)90153-7
|
| [13] |
N. Otsu, A threshold selection method from gray-level histograms, IEEE Trans. Syst. Man Cybern., 9 (1979), 62–66. https://doi.org/10.1109/TSMC.1979.4310076 doi: 10.1109/TSMC.1979.4310076
|
| [14] |
S. Li, L. Ye, Multi-level thresholding image segmentation for rubber tree secant using improved Otsu's method and snake optimizer, Math. Biosci. Eng., 20 (2023), 9645–9669. https://doi.org/10.3934/mbe.2023423 doi: 10.3934/mbe.2023423
|
| [15] |
O. Vite-Chávez, J. Flores-Troncoso, R. Olivera-Reyna, J. U. Muñoz-Minjares, Improvement procedure for image segmentation of fruits and vegetables based on the Otsu method, Image Anal. Stereol., 42 (2023), 185–196. https://doi.org/10.5566/ias.2939 doi: 10.5566/ias.2939
|
| [16] |
X. Liu, Z. Zhang, Y. Hao, H. Zhao, Y. Yang, Optimized Otsu segmentation algorithm-based temperature feature extraction method for infrared images of electrical equipment, Sensors, 24 (2024), 1126. https://doi.org/10.3390/s24041126 doi: 10.3390/s24041126
|
| [17] |
Y. Xu, R. Quan, W. Xu, Y. Huang, X. Chen, F. Liu, Advances in medical image segmentation: A comprehensive review of traditional, deep learning and hybrid approaches, Bioengineering, 11 (2024), 1034. https://doi.org/10.3390/bioengineering11101034 doi: 10.3390/bioengineering11101034
|
| [18] |
M. E. Rayed, S. M. S. Islam, S. I. Niha, J. R. Jim, M. M. Kabir, M. F. Mridha, Deep learning for medical image segmentation: state-of-the-art advancements and challenges, Inf. Med. Unlocked, 47 (2024), 101504. https://doi.org/10.1016/j.imu.2024.101504 doi: 10.1016/j.imu.2024.101504
|
| [19] |
Y. Gao, Y. Jiang, Y. Peng, F. Yuan, X. Zhang, J. Wan, Medical image segmentation: a comprehensive review of deep learning-based methods, Diagnostics, 11 (2025), 52. https://doi.org/10.3390/tomography11050052 doi: 10.3390/tomography11050052
|
| [20] |
R. M. Haralick, K. Shanmugam, I. Dinstein, Textural features for image classification, IEEE Trans. Syst. Man Cybern., SMC-3 (1973), 610–621. https://doi.org/10.1109/TSMC.1973.4309314 doi: 10.1109/TSMC.1973.4309314
|
| [21] |
C. E. Shannon, A mathematical theory of communication, Bell Syst. Tech. J., 27 (1948), 379–423. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x doi: 10.1002/j.1538-7305.1948.tb01338.x
|
| [22] |
H. Ibrar, J. Muhammad, Efficient convex region-based segmentation for noising and inhomogeneous patterns, Inverse Probl. Imag., 17 (2023), 708–725. https://doi.org/10.3934/ipi.2022074 doi: 10.3934/ipi.2022074
|
| [23] | X. Li, H. Ding, H. Yuan, W. Zhang, J. Pang, G. Cheng, et al., Transformer-based visual segmentation: a survey, arXiv, 2023. https://doi.org/10.48550/arXiv.2304.09854 |
| [24] | G. Csurka, R. Volpi, B. Chidlovskii, Semantic image segmentation: two decades of research, arXiv, 2023. https://doi.org/10.48550/arXiv.2302.06378 |
| [25] | Y. Wang, U. Ahsan, H. Li, M. Hagen, A comprehensive review of modern object segmentation approaches, arXiv, 2023. https://doi.org/10.48550/arXiv.2301.07499 |
| [26] |
H. Gao, O. Chae, Individual tooth segmentation from CT images using level set methods, Pattern Recognit., 43 (2010), 2406–2417. https://doi.org/10.1016/j.patcog.2010.01.010 doi: 10.1016/j.patcog.2010.01.010
|
| [27] |
W. Duan, Y. Chen, Q. Zhang, X. Lin, X. Yang, Refined tooth and pulp segmentation using U-Net in CBCT image, Dentomaxillofacial Rad., 50 (2021), 20200251. https://doi.org/10.1259/dmfr.20200251 doi: 10.1259/dmfr.20200251
|
| [28] |
Z. Chen, Q. Liu, J. Wang, N. Ji, Y. Gong, B. Gao, Tooth image segmentation and root canal measurement based on deep learning, Front. Bioeng. Biotechnol., 13 (2025), 1565403. https://doi.org/10.3389/fbioe.2025.1565403 doi: 10.3389/fbioe.2025.1565403
|
| [29] |
D. Sun, J. Wang, Z. Zuo, Y. Jia, Y. Wang, STS-transunet: semi-supervised tooth segmentation transformer U-net for dental panoramic image, Math. Biosci. Eng., 21 (2024), 2366–2384. https://doi.org/10.3934/mbe.2024104 doi: 10.3934/mbe.2024104
|
| [30] |
A. O. Santos-Junior, R. C. Fontenele, F. S. Neves, S. Ali, R. Jacobs, M. Tanomaru-Filho, A unique AI-based tool for automated segmentation of pulp cavity structures in maxillary premolars on CBCT, Sci. Rep., 15 (2025), 5509. https://doi.org/10.1038/s41598-025-86203-8 doi: 10.1038/s41598-025-86203-8
|
| [31] | M. Gamal, M. Baraka, M. Torki, Automatic mandibular semantic segmentation of teeth pulp cavity and root canals, and inferior alveolar nerve on Pulpy3D dataset, In: M. G. Linguraru, Q. Dou, A. Feragen, S. Giannarou, B. Glocker, K. Lekadir, et al., Medical image computing and computer assisted intervention – MICCAI 2024, Springer, 15008 (2024), 14–23. https://doi.org/10.1007/978-3-031-72111-3_2 |
| [32] | W. Cui, Y. Wang, Q. Zhang, H. Zhou, D. Song, X. Zuo, et al., CTooth: a fully annotated 3D dataset and benchmark for tooth volume segmentation on cone beam computed tomography images, arXiv, 2022. https://doi.org/10.48550/arXiv.2206.08778 |
| [33] | O. Boudraa, Segmentation of 3D dental images using deep learning, arXiv, 2022. https://doi.org/10.48550/arXiv.2207.09582 |
| [34] |
Y. Liu, C. Wang, M. Lu, J. Yang, J. Gui, S. Zhang, From simple to complex scenes: learning robust feature representations for accurate human parsing, IEEE Trans. Pattern Anal. Mach. Intell., 46 (2024), 5449–5462. https://doi.org/10.1109/TPAMI.2024.3366769 doi: 10.1109/TPAMI.2024.3366769
|
| [35] | A. Depeursinge, Multiscale and multidirectional biomedical texture analysis: finding the needle in the haystack, Biomed. Texture Anal., 2017, 1–36. https://doi.org/10.1016/B978-0-12-812133-7.00002-8 |
| [36] |
A. Fanizzi, T. M. A. Basile, L. Losurdo, R. Bellotti, U. Bottigli, R. Dentamaro, et al., A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis, BMC Bioinf., 21 (2020), 91. https://doi.org/10.1186/s12859-020-3358-4 doi: 10.1186/s12859-020-3358-4
|
| [37] |
S. T. M. Ataky, D. Saqui, J. de Matos, A. de Souza Britto Junior, A. Lameiras Koerich, Multiscale analysis for improving texture classification, Appl. Sci., 13 (2023), 1291. https://doi.org/10.3390/app13031291 doi: 10.3390/app13031291
|
| [38] | T. Lindeberg, Scale-space theory: a basic tool for analyzing structures at different scales, J. Appl. Stat., 21 (1994), 225–270. |
| [39] |
W. Liu, J. Hu, F. Lv, Z. Tang, A new method for long-term temperature compensation of structural health monitoring by ultrasonic guided wave, Measurement, 252 (2025), 117310. https://doi.org/10.1016/j.measurement.2025.117310 doi: 10.1016/j.measurement.2025.117310
|
| [40] |
J. J. Koenderink, The structure of images, Biol. Cybern., 50 (1984), 363–370. https://doi.org/10.1007/BF00336961 doi: 10.1007/BF00336961
|
| [41] | T. Lindeberg, Scale-space theory in computer vision, The Springer International Series in Engineering and Computer Science, Vol. 256, Springer, 1994. https://doi.org/10.1007/978-1-4757-6465-9 |
| [42] | G. T. Fechner, Elemente der psychophysik, Breitkopf und Härtel, Leipzig, 1860. |
Figures(13) / Tables(4)
C. Coronado Gallardo, C. Fernández García, I. Suazo, J. A. Vega, Z. Fernández Muñiz. A pointwise contextual multiscale texture operator and its application to 3D medical image segmentation[J]. AIMS Mathematics, 2026, 11(5): 13530-13566. doi: 10.3934/math.2026557
DownLoad: