GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathology Image Classification
share
For deep learning methods applied to the diagnosis of gastric cancer intelligently, existing methods concentrate more on Convolutional Neural Networks (CNN) but no approaches are available using Visual Transformer (VT). VT's efficient and stable deep learning models with the most recent application in the field of computer vision, which is capable of improving the recognition of global information in images. In this paper, a multi-scale visual transformer model (GasHis-Transformer) is proposed for a gastric histopathology image classification (GHIC) task, which enables the automatic classification of gastric histological images of abnormal and normal cancer by obtained by optical microscopy to facilitate the medical work of histopathologists. This GasHis-Transformer model is built on two fundamental modules, including a global information module (GIM) and a local information module (LIM). In the experiment, an open source hematoxylin and eosin (H E) stained gastric histopathology dataset with 280 abnormal or normal images are divided into training, validation, and test sets at a ratio of 1:1:2 first. Then, GasHis-Transformer obtains precision, recall, F1-score, and accuracy on the testing set of 98.0 experiment also tests the generalization ability of the proposed GatHis-Transformer model with a lymphoma image dataset including 374 images and a breast cancer dataset including 1390 images in two extended experiments and achieves an accuracy of 83.9 GasHis-Transformer model demonstrates high classification performance and shows its effectiveness and enormous potential in GHIC tasks.
READ FULL TEXT