Classification of mass and normal breast tissue: A convolution neural network classifier with spatial domain and texture images
Classification of mass and normal breast tissue: A convolution neural network classifier with spatial domain and texture images
复制标题
DOI：
10.1109/42.538937
复制
发表时间：
1996-10-01
影响因子：
10.6
通讯作者：
Goodsitt, MM
中科院分区：
文献类型：
--
作者：
Sahiner, B;Chan, HP;Goodsitt, MM
我们研究了使用卷积神经网络（CNN）将乳房X线照片上的感兴趣区域（ROI）分类为肿块或正常组织。CNN是一种反向传播神经网络，具有对图像进行操作的二维（2-D）权重内核。开发了CNN的通用，快速和稳定的实现。使用两种技术从ROI获得CNN的输入图像。第一种技术采用平均和二次采样。第二种技术采用纹理特征提取方法，适用于小的ROI内的子区域。在不同子区域上计算的特征被排列为纹理图像，随后被用作CNN输入。研究了CNN结构和纹理特征参数对分类精度的影响。采用受试者工作特征（ROI）方法评价分类准确性，由经验丰富的放射科医师从168张乳腺X线照片中提取168个包含活检证实的肿块的ROI和504个包含正常乳腺组织的ROI。该数据集用于训练和测试CNN。在CNN架构和纹理特征参数的最佳组合下，测试ROC曲线下的面积达到0.87，这对应于90%的真阳性分数和31%的假阳性分数。我们的研究结果证明了使用CNN对乳房X光片上的肿块和正常组织进行分类的可行性。
We investigated the classification of regions of interese (ROI's) on mammograms as either mass or normal tissue using a convolution neural network (CNN). A CNN is a back-propagation neural network with two-dimensional (2-D) weight kernels that operate on images. A generalized, fast and stable implementation of the CNN was developed. The input images to the CNN were obtained from the ROI's using two techniques. The first technique employed averaging and subsampling. The second technique employed texture feature extraction methods applied to small subregions inside the ROI. Features computed over different subregions were arranged as texture images, which were subsequently used as CNN inputs. The effects of CNN architecture and texture feature parameters on classification accuracy were studied. Receiver operating characteristic (ROI) methodology was used to evaluate the classification accuracy, a data set consisting of 168 ROI's containing biopsy-proven masses and 504 ROI's containing normal breast tissue was extracted from 168 mammograms by radiologists experienced in mammography. This data set was used for training and testing the CNN. With the best combination of CNN architecture and texture feature parameters, the area under the test ROC curve reached 0.87, which corresponded to a true-positive fraction of 90% at a false positive fraction of 31%. Our results demonstrate the feasibility of using a CNN for classification of masses and normal tissue on mammograms.