Unleashing the Potential of Synthetic Images: A Study on Histopathology Image Classification

TL;DR

This study evaluates various generative models for creating synthetic histopathology images, demonstrating their effectiveness in dataset augmentation and improving classification accuracy.

Contribution

It systematically compares diffusion models, GANs, and transformer-based models for synthetic image generation in histopathology, highlighting their respective advantages.

Findings

Diffusion models excel in transfer learning scenarios.

GANs produce high-quality images suitable for dataset augmentation.

Transformer models generate realistic images without filtering requirements.

Abstract

Histopathology image classification is crucial for the accurate identification and diagnosis of various diseases but requires large and diverse datasets. Obtaining such datasets, however, is often costly and time-consuming due to the need for expert annotations and ethical constraints. To address this, we examine the suitability of different generative models and image selection approaches to create realistic synthetic histopathology image patches conditioned on class labels. Our findings highlight the importance of selecting an appropriate generative model type and architecture to enhance performance. Our experiments over the PCam dataset show that diffusion models are effective for transfer learning, while GAN-generated samples are better suited for augmentation. Additionally, transformer-based generative models do not require image filtering, in contrast to those derived from Convolutional Neural Networks (CNNs), which benefit from realism score-based selection. Therefore, we show that synthetic images can effectively augment existing datasets, ultimately improving the performance of the downstream histopathology image classification task.