Deep neural system for supporting tumor recognition of mammograms using modified GAN
Deep neural system for supporting tumor recognition of mammograms using modified GAN
复制标题
使用改进的 GAN 支持乳房 X 光检查肿瘤识别的深度神经系统
DOI：
10.1016/j.eswa.2020.113968
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
M. Kołodziej
中科院分区：
文献类型：
--
作者：
B. Świderski;Lukasz Gielata;Pawel Olszewski;S. Osowski;M. Kołodziej
本文提出了乳房 X 光检查分析中的自动编码器生成对抗网络（AGAN）。 AGAN 架构用于通过生成乳房 X 光图像的附加表示来增强数据，从而增强所分析问题的信息。这个深度网络生成的图像被附加到原始的乳房 X 光照片集，并馈送到卷积神经网络的输入，该网络起着最终分类器的作用。所提出的系统用于识别属于两类的乳房X光照片：正常和异常。调查是使用一个大型数据库进行的，该数据库包含来自 DDSM 基地的 11,218 个乳腺 X 线摄影图像的感兴趣区域。结果证明了所提出的深度学习系统相对于其他已知的乳房X线照片识别方法的优势。我们检测异常病例（恶性加良性与健康）的平均准确度为 89.71%，敏感性为 93.54%，特异性为 80.58%，AUC = 0.9410。这些结果对于这个大型数据库来说是最好的。
This paper presents the autoencoder-generative adversarial network (AGAN) in the analysis of mammograms. The AGAN architecture is used to augment the data by generating additional representations of the mammogram images, enhancing this way the information of the analyzed problem. The images generated by this this deep network are appended to the original set of mammograms and fed to the input of convolutional neural network, which plays the role of the final classifier. The proposed system was used to recognize the mammograms belonging to two classes: normal and abnormal. The investigations were performed using a large database consisting of 11,218 regions of interest of mammographic images from the DDSM base. The results demonstrate the advantage of this proposed deep learning system over other known approaches to mammogram recognition. Our average accuracy in detecting abnormal cases (malignant plus benign versus healthy) was 89.71%, sensitivity 93.54%, specificity 80.58% and AUC = 0.9410. These results are among the best for this large database.
DOI：
10.1007/978-1-4302-0248-6_11
发表时间：
2019-04
期刊：
Scalable Comput. Pract. Exp.
影响因子：
--
作者：
Chet Langin
通讯作者：
Chet Langin