乳腺肿瘤分类的集成卷积神经网络

Apr, 2023

乳腺肿瘤分类的集成卷积神经网络

Ensemble CNNs for Breast Tumor Classification

Muhammad Umar Farooq, Zahid Ullah, Jeonghwan Gwak

TL;DR本研究探索了三种分类网络，即 XceptionNet、DenseNet 和 EfficientNet，通过集成机制来提高计算机辅助乳腺肿块分类的识别能力。在公共数据集上验证该方案，可以获得88％的准确度，85％的精度和76％的召回率。

Abstract

To improve the recognition ability of computer-aided breast mass classification among mammographic images, in this work we explore the state-of-the-art classification networks to develop an ensemble mechanism. Fi