Fibro-osseous bone tumors occurring in the craniofacial skeleton represent a group of lesions with diverse clinical behavior. The pathogenesis of most of these lesions is not completely understood and current diagnostic tools are limited. Although their histological appearance may be similar, the clinical behavior of these entities varies from indolent to aggressive growth and/or metastatic spread. Therefore, an accurate diagnosis is crucial for an adequate treatment and prognosis.
We proposed an innovative extra approach to address the diagnostic challenges associated with fibro-osseous lesions in craniofacial bones. In our study we will use deep learning models for classifying whole slide images (WSIs) derived from haematoxylin and eosin stained tissue samples. We believe that using deep learning algorithm on WSI in an integrated multidisciplinary diagnostic approach will increase diagnostic accuracy for fibro-osseous lesions of craniofacial bone, especially for osteosarcomas.
