Thinning Methodologies-A Comprehensive Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
In this research we developed a computer-aided image processing method for differentiating oral borderline grades in hematoxylin-eosin stained microscopic images. Oral dysplasia and carcinoma in-situ (CIS) are two different borderline grades similar to each other and it is difficult to distinguish between them. A new histological method has been invented in this study and shows the possibility for differentiating the oral borderline grades automatically. The method is based on comparing the drop-shaped similarity level between the best matching pair of neighboring rete ridges. It was found that the considered similarity level in dysplasia was higher than those in epithelial CIS. The developed image processing method shows good promise for the computer-aided pathological assessment of oral borderline malignancy differentiation in clinical practice.