WITHDRAWN: Histomorphometric Image Classifier of Different Grades of Oral Squamous Cell Carcinoma Using Transfer Learning and Convolutional Neural Network

This article has been withdrawn at the request of the authors. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at https://www.elsevier.com/about/policies/article-withdrawal

Fractal Dimension and Radiomorphometric analysis of Orthopanoramic radiographs in patients with tobacco and areca nut associated oral mucosal lesions: A pilot in-vivo study in a North Indian cohort.

OBJECTIVE: The aim of this study was to determine the fractal dimension (FD) and radiomorphometric indices (RMIs) in the mandible from orthopantomographic radiographs in patients with oral lesions associated with smokeless/smoking tobacco (SLT/ST) and areca nut habits in a North Indian cohort. STUDY DESIGN: A prospective, cross-sectional, observational pilot study was conducted of 120 subjects, including controls and 3 study groups of 30 patients each with oral submucous fibrosis, tobacco pouch keratosis, and oral leukoplakia (OL). Two observers calculated FD and the RMIs of mandibular cortical thickness (MCT), panoramic mandibular index (PMI), and mandibular cortical index (MCI). RESULTS: Mean FD was significantly reduced compared to controls with all oral lesions (P < .05) and with all habits in 3 of 4 regions of interest (P < .05). MCT was significantly reduced with OL (P < .005) and in ST users (P < .05). PMI did not differ regarding lesion status or habits. Compared to the controls, MCI C2 type was significantly more common in all oral lesions (P ≤ .005) and all types of habit (P < .005). Inter- and intraobserver agreement was strong to excellent. CONCLUSIONS: FD and RMI values were significantly altered compared to controls in oral lesions associated with tobacco and areca nut habits and in the dominant type of habit.