CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification

TL;DR

CellGAN is a novel generative model that synthesizes realistic cervical cell images to enhance the training of classifiers in cytopathological image analysis, reducing annotation needs.

Contribution

The paper introduces CellGAN, a lightweight conditional GAN with a class mapping network and a Skip-layer Global Context module for high-fidelity cervical cell image synthesis.

Findings

CellGAN produces visually plausible cytopathological images.

Using CellGAN significantly improves cell classification accuracy.

Synthesized images effectively augment training data.

Abstract

Automatic examination of thin-prep cytologic test (TCT) slides can assist pathologists in finding cervical abnormality for accurate and efficient cancer screening. Current solutions mostly need to localize suspicious cells and classify abnormality based on local patches, concerning the fact that whole slide images of TCT are extremely large. It thus requires many annotations of normal and abnormal cervical cells, to supervise the training of the patch-level classifier for promising performance. In this paper, we propose CellGAN to synthesize cytopathological images of various cervical cell types for augmenting patch-level cell classification. Built upon a lightweight backbone, CellGAN is equipped with a non-linear class mapping network to effectively incorporate cell type information into image generation. We also propose the Skip-layer Global Context module to model the complex spatial relationship of the cells, and attain high fidelity of the synthesized images through adversarial learning. Our experiments demonstrate that CellGAN can produce visually plausible TCT cytopathological images for different cell types. We also validate the effectiveness of using CellGAN to greatly augment patch-level cell classification performance.