Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification

Cervical intraepithelial neoplasia (CIN) grade of histopathology images is a crucial indicator in cervical biopsy results. Accurate CIN grading of epithelium regions helps pathologists with precancerous lesion diagnosis and treatment planning. Although an automated CIN grading system has been desired, supervised training of such a system would require a large amount of expert annotations, which are expensive and time-consuming to collect. In this paper, we investigate the CIN grade classification problem on segmented epithelium patches. We propose to use conditional Generative Adversarial Networks (cGANs) to expand the limited training dataset, by synthesizing realistic cervical histopathology images. While the synthetic images are visually appealing, they are not guaranteed to contain meaningful features for data augmentation. To tackle this issue, we propose a synthetic-image filtering mechanism based on the divergence in feature space between generated images and class centroids in order to control the feature quality of selected synthetic images for data augmentation. Our models are evaluated on a cervical histopathology image dataset with a limited number of patch-level CIN grade annotations. Extensive experimental results show a significant improvement of classification accuracy from 66.3% to 71.7% using the same ResNet18 baseline classifier after leveraging our cGAN generated images with feature-based filtering, which demonstrates the effectiveness of our models.

[1]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[2]  Tanveer F. Syeda-Mahmood,et al.  Chest x-ray generation and data augmentation for cardiovascular abnormality classification , 2018, Medical Imaging.

[3]  Sansanee Auephanwiriyakul,et al.  Automatic cervical cell segmentation and classification in Pap smears , 2014, Comput. Methods Programs Biomed..

[4]  Xin Qi,et al.  Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images , 2018, MICCAI.

[5]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[6]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[7]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[8]  R. Joe Stanley,et al.  Nuclei-Based Features for Uterine Cervical Cancer Histology Image Analysis With Fusion-Based Classification , 2016, IEEE Journal of Biomedical and Health Informatics.

[9]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[10]  A. Jemal,et al.  Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries , 2018, CA: a cancer journal for clinicians.

[11]  Hayit Greenspan,et al.  GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification , 2018, Neurocomputing.

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[14]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.