GasHisSDB

GasHisSDB is a New Gastric Histopathology Sub-size Image Database with a total of 245196 images. GasHisSDB is divided into 160x160 pixels sub-database, 120x120 pixels sub-database and 80x80 pixels sub-database. GasHisSDB is made to realize the function of evaluating image classification. In order to prove that the methods of different periods in the field of image classification have discrepancies on GasHisSDB, we select a variety of classifiers for evaluation. Seven classical machine learning classifiers, three CNN classifiers and a novel transformer-based classifier are selected for testing on image classification tasks.

GasHisSDB（胃部病理亚尺寸图像数据库）是一款新型胃部病理亚尺寸图像数据集，总计包含245196张图像。该数据集被划分为160×160像素、120×120像素与80×80像素三个子数据集。本数据集的构建初衷是实现图像分类评估功能。为验证图像分类领域不同时期的各类方法在GasHisSDB上存在性能差异，我们选取了多种分类器开展评估测试。本次测试共选用7种经典机器学习分类器、3种卷积神经网络（Convolutional Neural Network, CNN）分类器，以及一款新型基于Transformer的分类器，用于图像分类任务的性能验证。