首页> 外文会议>International Conference on Artificial Intelligence and Soft Computing >Blue-White Veil Classification in Dermoscopy Images of the Skin Lesions Using Convolutional Neural Networks
【24h】

Blue-White Veil Classification in Dermoscopy Images of the Skin Lesions Using Convolutional Neural Networks

机译:使用卷积神经网络的皮肤病患者皮肤病的蓝白面纱分类

获取原文

摘要

In the dermatology, Three-Point Checklist of Dermatology is defined and it is proved to be a sufficient screening method in the skin lesions assessments during the checking by dermatology expert. In the method there is a criterion of blue-whitish veil appearance within the lesion defined and it can be classified using a binary classifier. In the paper, we show the results of CNN application to the problem of the assessment of whether the blue-white veil is present or absent within the lesion using the pre-trained VGG19 CNN network, trained and tested on the prepared images taken from the PH2 dataset.
机译:在皮肤病学中,定义了皮肤病学的三点清单,并且在皮肤科专家检查期间被证明是皮肤病因子评估中的足够筛查方法。在该方法中,存在在定义的病变内的蓝白面纱外观的标准,并且可以使用二进制分类器进行分类。在本文中,我们将CNN应用的结果显示出对使用预先训练的VGG19 CNN网络在病变中存在或不存在的问题的问题,培训和测试在从中拍摄的制备的图像上ph2数据集。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号