Cervical cancer is a kind of common female malignancy ranking fourth for mortality worldwide. Traditional histopathological examination, an important diagnosis method of cervical cancer, is still manually performed by pathologists under the microscope, which is labor intensive and error‐prone. In this article, deep learning is used for whole slide cervical image (WSCI) analysis to explore an automatic and effective method for the diagnosis of cervical cancer. We combine convolutional neural network (CNN) and random forest (RF) classifier for whole slide cervical image classification. A new multilevel feature fusion strategy named Ensemble is used for features extraction from the features extracted by CNN. Ensemble that fuses features extracted by convolution layers with different depths in CNN together is capable of capturing fusional features which can describe patches at different levels from different convolutional layers. Principal component analysis (PCA) algorithm is introduced for feature reduction of the multilevel features. Our experiments are carried out on WSCI dataset which consists of a total of 163 WSCIs from 27 patients. We combine CNN + PCA + RF model and CNN + RF model, respectively, with four feature extraction strategies to conduct eight comparative experiments on the 163 WSCIs. Experimental results demonstrate that when using multilevel feature fusion strategy, the classification accuracy of the CNN + PCA + RF model reaches the highest to 99.39%. In addition, the CNN + PCA + RF model conducting the multilevel feature fusion strategy performs better than that conducting single‐level feature extraction strategies.

The automatic and accurate identification of apoptosis facilitates large-scale cell analysis. Most identification approaches using nucleus fluorescence imaging are based on specific morphological parameters. However, these parameters cannot completely describe nuclear morphology, thus limiting the identification accuracy of models. This paper proposes a new feature extraction method to improve the performance of the model for apoptosis identification. The proposed method uses a histogram of oriented gradient (HOG) of high-frequency wavelet coefficients to extract internal and edge texture information. The HOG vectors are classified using support vector machine. The experimental results demonstrate that the proposed feature extraction method well performs apoptosis identification, attaining [Formula: see text] accuracy with low cost in terms of time. We confirmed that our method has potential applications to cell biology research.