A Two-Stage End-to-End Deep Learning Framework for Pathologic Examination in Skin Tumor Diagnosis

Abstract

Neurofibromas (NF), Bowen's disease (BD), and Seborrheic Keratosis (SK) are common skin tumors. Pathological examination is the golden standard for diagnosis of these tumors. Current pathological diagnosis is mainly based on the observation of naked eyes under microscope, which is laborious and time-consuming. Digitization of pathology brings the opportunity for AI technology to improve the efficiency of diagnosis. This research aims to develop an end-to-end extendable framework for the diagnosis of skin tumor based on pathological slide image. NF, BD, SK were selected as target skin tumors. A two-stage skin cancer diagnosis framework (TSSD) is proposed in this paper, which consists of two parts: patches-wise diagnosis and slide-wise diagnosis. Patches-wise diagnosis compares different Convolutional Neural Networks (CNN) to extract features and distinguish categories from patches generated in whole slide images. Slide-wise diagnosis combines Attention Graph Gated Network (AGGN) model prediction with post-processing algorithm. This approach can fuse information from feature embedding learning and domain knowledge to draw a conclusion. Training, validation and testing were performed on NF, BD, SK and negative samples. Accuracy and ROC curves were used to evaluate the classification performance. This study investigated on the feasibility of skin tumor diagnosis in pathological image and may be the first time that deep learning is applied to address these three kinds of tumor diagnosis in skin pathology.