论著摘要 |【AI-CT】基于描述性CNN特征的三级乳房X线照片分类(双语版)

2018-01-23 13:10:53 admin 0
标签:  人工智能 卷积神经网络 CNN 支持向量机 SVM 乳房X线照片 乳腺癌

Three-Class Mammogram Classification Based on Descriptive CNN Features.

发表日期: 2017.01.15   来源:Biomed Res Int. 2017;2017:3640901.

作者:

Jadoon MM1, Zhang Q2, Haq IU3, Butt S3, Jadoon A3.

作者介绍:

1. Queen Mary University of London, London, UK; Faculty of Engineering and Technology, International Islamic University Islamabad, Islamabad, Pakistan.

2. Queen Mary University of London, London, UK.

3. Faculty of Engineering and Technology, International Islamic University Islamabad, Islamabad, Pakistan.

摘要

本文提出了一种基于深度学习的乳腺X线照片大数据组分类新方法。所提出的模型针对一项三级分类研究(正常,恶性和良性病例)。在我们的模型中,我们提出了两种方法,即卷积神经网络离散小波(CNN-DW)和卷积神经网络曲波变换(CNN-CT)。通过使用乳房X线照片块生成增强的数据集。为了增强乳房X线照片图像的对比度,数据集通过对比度受限自适应直方图均衡(CLAHE)进行滤波。在CNN-DW方法中,通过二维离散小波变换(2D-DWT)将增强的乳房X线照片图像分解为其四个子带,而在第二种方法中使用离散曲波变换(DCT)。在这两种方法中,提取所有子带的密集缩放不变特征(DSIFT)。输入数据矩阵包含所有乳房X线照片片块创建的这些子带特征,做为卷积神经网络(CNN)的输入。使用Softmax层和支持向量机(SVM)层来训练CNN进行分类。在准确率,错误率和各种验证评估措施方面,将所提出的方法与现有方法进行了比较。 CNN-DW和CNN-CT的准确率分别达到了81.83%和83.74%。与其他众所周知的现有技术相比,模拟结果清楚地验证了我们提出的模型的重要性和影响。

Abstact

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.

阅读原文:PMID: 28191461  PMCID: PMC5274695  DOI: 10.1155/2017/3640901


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片