Computational analysis of p63(+) nuclei distribution pattern by graph theoretic approach in an oral pre-cancer (sub-mucous fibrosis).

摘要: Background: Oral submucous fibrosis (OSF) is a pre-cancerous condition with features of chronic, inflammatory and progressive sub-epithelial fibrotic disorder the buccal mucosa. In this study, malignant potentiality OSF has been assessed by quantification immunohistochemical expression epithelial prime regulator-p63 molecule in correlation to its (oral squamous cell carcinoma [OSCC] normal counterpart [normal oral mucosa [NOM]). Attributes spatial extent distribution p63 + epithelium have investigated. Further, correlated assessment histopathological attributes inferred from H&E staining their mathematical counterparts (molecular pathology p63) proposed. The suggested analytical framework envisaged standardization immunohistochemistry evaluation procedure for molecular marker, using computer-aided image analysis, toward enhancing prognostic value. Subjects Methods: histopathologically confirmed OSF, OSCC NOM tissue sections, nuclei were localized segmented identifying regional maxima plateau-like intensity profiles nuclei. clustered concave points morphometry marker-controlled watersheds. Voronoi tessellations constructed around centroids mean values spatial-relation metrics such as tessellation area, perimeter, roundness factor area extracted. Morphology are characterized diameter, compactness, eccentricity density, fraction distance Results: Correlative between characterizing quantitative was developed. Statistical analyses trends evaluated different biologically relevant combinations: (i) without dysplasia (OSFWT) (ii) (OSFWD) (iii) OSFWT-OSFWD (iv) OSFWD-OSCC. Significant histopathogical correlates corroborative features, staining, also investigated into. Conclusion: Quantitative correlative analysis identified related hyperplasia, cellular stratification, differentiation maturation, shape size, nuclear crowding nucleocytoplasmic ratio. It that approach analyzing pattern may help establish it bio-marker predict progression. proposed work would be value addition gold standard incorporating an observer-independent associated pathology.