Quantitative Morphometric Analysis of Oral Epithelial Dysplasia using Deep Learning-Based Nuclear Segmentation

• Lucca S. P. Lacerda PUC Minas
• Marcela F. A. Ribeiro PUC Minas
• Martinho C. R. Horta PUC Minas
• Giovanna R. Souto PUC Minas
• Alexandre X. Falcão UNICAMP
• Gustavo K. Rohde University of Virginia
• Zenilton K. G. Patrocínio Jr PUC Minas
• Silvio Jamil F. Guimarães PUC Minas

Resumo

Oral Epithelial Dysplasia (OED) is a histopathological diagnosis for potentially malignant lesions with a variable risk of malignant transformation. The conventional grading of OED relies on morphological assessment, a process known for significant inter-observer variability, which limits its prognostic reliability. This study leverages computational pathology to address this challenge by employing a deep learning-based tool, Cellpose, for the precise segmentation of epithelial cell nuclei. The objective was to facilitate the objective extraction and analysis of key nuclear morphometric features, such as area, perimeter, and compactness, from digitized histological images of OED. We utilized 30 H&E-stained images from a spectrum of diagnostic categories, including normal oral mucosa, dysplasias of varying grades, and oral squamous cell carcinoma (OSCC). The results demonstrated that quantitative features, particularly the variance in nuclear area (anisonucleosis), serve as a robust differentiator between diagnostic grades, with the most significant changes observed in OSCC. By providing a reproducible and quantitative framework, this deep learning-driven approach represents a significant step towards a standardized diagnostic support system for OED, with future potential for accurately predicting malignant transformation risk.

Palavras-chave: Oral Epithelial Dysplasia, Image Segmentation, Computational Pathology, Nuclear Morphometry, Malignant Transformation, Artificial Intelligence

Referências

H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, and F. Bray, “Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries,” CA: A Cancer Journal for Clinicians, vol. 71, no. 3, pp. 209–249, 2021.

S. Warnakulasuriya, “Global epidemiology of oral and oropharyngeal cancer,” Oral Oncology, vol. 45, no. 4-5, pp. 309–316, 2009.

P. M. Speight, S. A. Khurram, and O. Kujan, “Oral potentially malignant disorders: a practical approach to diagnosis and management,” Journal of Oral Pathology & Medicine, vol. 47, no. 8, pp. 723–732, 2018.

A. K. El-Naggar, J. K. C. Chan, J. R. Grandis, T. Takata, and P. J. Slootweg, Eds., WHO Classification of Head and Neck Tumours, 4th ed., ser. World Health Organization Classification of Tumours. Lyon, France: IARC Press, 2017, vol. 9.

O. Kujan, R. J. Oliver, A. Khattab, S. A. Roberts, N. Thakker, and P. Sloan, “Evaluation of a new binary system of grading oral epithelial dysplasia with correlation to clinical outcome,” Oral Oncology, vol. 42, no. 10, pp. 987–993, 2006.

D. J. Fischer, J. B. Epstein, T. H. Morton, and S. M. Schwartz, “Interobserver reliability in the histopathologic grading of oral epithelial dysplasia,” Oral Surgery, Oral Medicine, Oral Pathology, Oral Radiology, and Endodontology, vol. 97, no. 5, pp. 604–610, 2004.

L. M. Abbey, G. E. Kaugars, J. C. Gunsolley, J. C. Burns, D. G. Page, J. A. Svirsky, S. M. Hahn, W. C. Cothran, and C. A. Gendusa, “Interexaminer and intraexaminer reliability in the diagnosis of oral epithelial dysplasia,” Oral Surgery, Oral Medicine, Oral Pathology, Oral Radiology, and Endodontology, vol. 80, no. 2, pp. 188–191, 1995.

O. Iocca, T. P. Sollecito, F. Alawi, G. S. Weinstein, J. G. Newman, A. De Virgilio, P. Di Maio, G. Spriano, M. Pardiñas, R. M. Shanti, D. C. Lanza, and A. D. Le, “A systematic review of the prognostic significance of the clinical and histopathologic grading of oral epithelial dysplasia,” Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology, vol. 113, no. 6, pp. 799–809, 2012.

A. Madabhushi and G. Lee, “Image analysis and machine learning in digital pathology: Challenges and opportunities,” Medical Image Analysis, vol. 33, pp. 170–175, 2016.

C. Lu, D. Wang, P. Wang, T. Li, and H. Liu, “Nuclear morphometry for grading oral epithelial dysplasia,” Journal of Pathology Informatics, vol. 7, p. 31, 2016.

C. Stringer, T. Wang, M. Michaelos, and M. Pachitariu, “Cellpose: a generalist algorithm for cellular segmentation,” Nature Methods, vol. 18, no. 1, pp. 100–106, 2021.

J. P. Vink, J. A. W. M. van der Laak, B. de Hoop, C. A. H.-v. van de Kaa, E. A. Janssen, H. van Boven, and J. Bulten, “A comparison of five different automated and semi-automated nuclear segmentation methods for cervical cytology,” Cytometry Part B: Clinical Cytometry, vol. 84, no. 5, pp. 322–331, 2013.

T. Rau, E. Horing, N. Stathonikos, M. de Wit, E. Hoving, T. Offermans, M. Trajkovic-Arsic, F. Ciompi, J. van der Laak, and I. D. Nagtegaal, “The application of quantitative image analysis and machine learning in the classification of colorectal polyps,” Modern Pathology, vol. 34, no. 5, pp. 1010–1020, 2021.

H. R. Tizhoosh and L. Pantanowitz, “Artificial intelligence and digital pathology: challenges and opportunities,” Journal of Pathology Informatics, vol. 9, p. 38, 2018.

P. Krishnan, R. D. Uthoff, H. An, W. Chen, A. Tanna, T. Tanna, S. Kalmady, H. McGehee, M. Brandwein-Weber, A. K. Lee, R. B. Smith, R. Ganti, and C. Raman, “Quantitative histopathology and nuclear-scale architecture analysis of oral dysplasia,” Scientific Reports, vol. 9, no. 1, p. 12921, 2019.

R. M. Bremnes, T. Dønnem, S. Al-Saad, K. Al-Shibli, S. Andersen, R. Sirera, C. Camps, and L.-T. Busund, “The role of tumor stroma in cancer progression and therapy: revelation of a new therapeutic target,” Expert Opinion on Therapeutic Targets, vol. 15, no. 3, pp. 315–325, 2011.