Medical Technology Department, Qiqihar Medical University, Qiqihar 161006, Heilongjiang, China.
Breast Department, Qiqihar First Hospital, Qiqihar 161006, Heilongjiang, China.
J Healthc Eng. 2021 Nov 24;2021:9610830. doi: 10.1155/2021/9610830. eCollection 2021.
To explore the application value of the multilevel pyramid convolutional neural network (MPCNN) model based on convolutional neural network (CNN) in breast histopathology image analysis, in this study, based on CNN algorithm and softmax classifier (SMC), a sparse autoencoder (SAE) is introduced to optimize it. The sliding window method is used to identify cells, and the CNN + SMC pathological image cell detection method is established. Furthermore, the local region active contour (LRAC) is introduced to optimize it and the LRAC fine segmentation model driven by local Gaussian distribution is established. On this basis, the sparse automatic encoder is further introduced to optimize it and the MPCNN model is established. The proposed algorithm is evaluated on the pathological image data set. The results showed that the Acc value, F value, and Re value of pathological cell detection of CNN + SMC algorithm were significantly higher than those of the other two algorithms ( < 0.05). The Dice, OL, Sen, and Spe values of pathological image regional segmentation of CNN algorithm were significantly higher than those of the other two algorithms, and the difference was statistically significant ( < 0.05). The accuracy, recall, and F-measure of the optimized CNN algorithm for detecting breast histopathological images were 85.25%, 89.27%, and 80.09%, respectively. In the two databases with segmentation standards, the segmentation accuracy of MPCNN is 55%, 73.1%, 78.8%, and 82.1%. In the deep convolution network model, the training time of the MPCNN algorithm is about 80 min. It shows that when the feature dimension is low, the feature map extracted by MPCNN is more effective than the traditional feature extraction method.
为了探索基于卷积神经网络（CNN）的多层次金字塔卷积神经网络（MPCNN）模型在乳腺组织病理学图像分析中的应用价值，本研究在 CNN 算法和软最大分类器（SMC）的基础上，引入稀疏自动编码器（SAE）对其进行优化。采用滑动窗口法识别细胞，建立 CNN+SMC 病理图像细胞检测方法。进一步引入局部区域主动轮廓（LRAC）对其进行优化，建立基于局部高斯分布的 LRAC 精细分割模型。在此基础上，进一步引入稀疏自动编码器对其进行优化，建立 MPCNN 模型。对病理图像数据集进行了算法评估。结果表明，CNN+SMC 算法的病理细胞检测的 Acc 值、F 值和 Re 值均明显高于另外两种算法（P<0.05）。CNN 算法的病理图像区域分割的 Dice、OL、Sen 和 Spe 值均明显高于另外两种算法，差异具有统计学意义（P<0.05）。优化后的 CNN 算法对乳腺组织病理图像的检测准确率、召回率和 F 值分别为 85.25%、89.27%和 80.09%。在具有分割标准的两个数据库中，MPCNN 的分割准确率为 55%、73.1%、78.8%和 82.1%。在深度卷积网络模型中，MPCNN 算法的训练时间约为 80 min。表明在特征维度较低时，MPCNN 提取的特征图比传统特征提取方法更有效。
