DEPAS: De-novo Pathology Semantic Masks using a Generative Model

TL;DR

This paper introduces DEPAS, a scalable generative model that creates high-quality, controllable semantic tissue masks and photorealistic histology images, enhancing data diversity and reducing bias in digital pathology AI applications.

Contribution

DEPAS is a novel generative model capable of producing high-resolution, realistic semantic tissue masks with controllable features for multiple organs, improving scalability and flexibility in synthetic histology image generation.

Findings

DEPAS generates high-quality semantic masks for skin, prostate, and lung tissues.

The model produces photorealistic histology images with controllable cellular features.

Synthetic images improve dataset diversity and reduce bias in AI pathology tasks.

Abstract

The integration of artificial intelligence into digital pathology has the potential to automate and improve various tasks, such as image analysis and diagnostic decision-making. Yet, the inherent variability of tissues, together with the need for image labeling, lead to biased datasets that limit the generalizability of algorithms trained on them. One of the emerging solutions for this challenge is synthetic histological images. However, debiasing real datasets require not only generating photorealistic images but also the ability to control the features within them. A common approach is to use generative methods that perform image translation between semantic masks that reflect prior knowledge of the tissue and a histological image. However, unlike other image domains, the complex structure of the tissue prevents a simple creation of histology semantic masks that are required as input to the image translation model, while semantic masks extracted from real images reduce the process's scalability. In this work, we introduce a scalable generative model, coined as DEPAS, that captures tissue structure and generates high-resolution semantic masks with state-of-the-art quality. We demonstrate the ability of DEPAS to generate realistic semantic maps of tissue for three types of organs: skin, prostate, and lung. Moreover, we show that these masks can be processed using a generative image translation model to produce photorealistic histology images of two types of cancer with two different types of staining techniques. Finally, we harness DEPAS to generate multi-label semantic masks that capture different cell types distributions and use them to produce histological images with on-demand cellular features. Overall, our work provides a state-of-the-art solution for the challenging task of generating synthetic histological images while controlling their semantic information in a scalable way.