Histopathological Diagnosis for Viable and Non-viable Tumor Prediction for Osteosarcoma Using Convolutional Neural Network

Pathologists often deal with high complexity and sometimes disagreement over Osteosarcoma tumor classification due to cellular heterogeneity in the dataset. Segmentation and classification of histology tissue in H&E stained tumor image datasets is challenging due to intra-class variations and inter-class similarity, crowded context, and noisy data. In recent years, deep learning approaches have led to encouraging results in breast cancer and prostate cancer analysis. In this paper, we propose a Convolutional neural network (CNN) as a tool to improve efficiency and accuracy of Osteosarcoma tumor classification into tumor classes (viable tumor, necrosis) vs non-tumor. The proposed CNN architecture contains five learned layers: three convolutional layers interspersed with max pooling layers for feature extraction and two fully-connected layers with data augmentation strategies to boost performance. We conclude that the use of neural network can assure high accuracy and efficiency in Osteosarcoma classification.