A fully automated and explainable algorithm for predicting malignant transformation in oral epithelial dysplasia.

Autor: Shephard AJ; Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Coventry, UK., Bashir RMS; Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Coventry, UK., Mahmood H; School of Clinical Dentistry, University of Sheffield, Sheffield, UK., Jahanifar M; Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Coventry, UK., Minhas F; Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Coventry, UK., Raza SEA; Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Coventry, UK., McCombe KD; Precision Medicine Centre, Patrick G. Johnston Centre for Cancer Research, Queen's University Belfast, Belfast, UK., Craig SG; Precision Medicine Centre, Patrick G. Johnston Centre for Cancer Research, Queen's University Belfast, Belfast, UK., James J; Precision Medicine Centre, Patrick G. Johnston Centre for Cancer Research, Queen's University Belfast, Belfast, UK., Brooks J; Institute of Head and Neck Studies and Education, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK., Nankivell P; Institute of Head and Neck Studies and Education, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK., Mehanna H; Institute of Head and Neck Studies and Education, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK., Khurram SA; School of Clinical Dentistry, University of Sheffield, Sheffield, UK., Rajpoot NM; Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Coventry, UK. n.m.rajpoot@warwick.ac.uk.
Jazyk: angličtina
Zdroj: NPJ precision oncology [NPJ Precis Oncol] 2024 Jun 28; Vol. 8 (1), pp. 137. Date of Electronic Publication: 2024 Jun 28.
DOI: 10.1038/s41698-024-00624-8
Abstrakt: Oral epithelial dysplasia (OED) is a premalignant histopathological diagnosis given to lesions of the oral cavity. Its grading suffers from significant inter-/intra-observer variability, and does not reliably predict malignancy progression, potentially leading to suboptimal treatment decisions. To address this, we developed an artificial intelligence (AI) algorithm, that assigns an Oral Malignant Transformation (OMT) risk score based on the Haematoxylin and Eosin (H&E) stained whole slide images (WSIs). Our AI pipeline leverages an in-house segmentation model to detect and segment both nuclei and epithelium. Subsequently, a shallow neural network utilises interpretable morphological and spatial features, emulating histological markers, to predict progression. We conducted internal cross-validation on our development cohort (Sheffield; n = 193 cases) and independent validation on two external cohorts (Birmingham and Belfast; n = 89 cases). On external validation, the proposed OMTscore achieved an AUROC = 0.75 (Recall = 0.92) in predicting OED progression, outperforming other grading systems (Binary: AUROC = 0.72, Recall = 0.85). Survival analyses showed the prognostic value of our OMTscore (C-index = 0.60, p = 0.02), compared to WHO (C-index = 0.64, p = 0.003) and binary grades (C-index = 0.65, p < 0.001). Nuclear analyses elucidated the presence of peri-epithelial and intra-epithelial lymphocytes in highly predictive patches of transforming cases (p < 0.001). This is the first study to propose a completely automated, explainable, and externally validated algorithm for predicting OED transformation. Our algorithm shows comparable-to-human-level performance, offering a promising solution to the challenges of grading OED in routine clinical practice.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: