Improving generalization of deep learning models for diagnostic pathology by increasing variability in training data: Experiments on osteosarcoma subtypes

Background: Artificial intelligence has an emerging progress in diagnostic pathology. A large number of studies of applying deep learning models to histopathological images have been published in recent years. While many studies claim high accuracies, they may fall into the pitfalls of overfitting and lack of generalization due to the high variability of the histopathological images. Aims and Objects: Use the model training of osteosarcoma as an example to illustrate the pitfalls of overfitting and how the addition of model input variability can help improve model performance. Materials and Methods: We use the publicly available osteosarcoma dataset to retrain a previously published classification model for osteosarcoma. We partition the same set of images into the training and testing datasets differently than the original study: The test dataset consists of images from one patient while the training dataset consists images of all other patients. We also show the influence of training data variability on model performance by collecting a minimal dataset of 10 osteosarcoma subtypes as well as benign tissues and benign bone tumors of differentiation. Results: The performance of the re-Trained model on the test set using the new partition schema declines dramatically, indicating a lack of model generalization and overfitting. We show the additions of more and moresubtypes into the training data step by step under the same model schema yield a series of coherent models with increasing performances. Conclusions: In conclusion, we bring forward data preprocessing and collection tactics for histopathological images of high variability to avoid the pitfalls of overfitting and build deep learning models of higher generalization abilities.