DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer Grading

TL;DR

This paper introduces DISC, a novel self-distillation framework for latent diffusion models that generates multi-grade prostate cancer histopathology tiles, significantly improving grading accuracy with synthetic data augmentation.

Contribution

The study presents a new self-distillation method for LDMs to generate multi-grade cancer tiles, enhancing prostate cancer grading accuracy with synthetic data.

Findings

Generated tiles better represent Gleason Grade patterns.

Synthetic data improves grading model performance, especially for rare grades.

The approach surpasses previous methods in generating accurate cancer histopathology images.

Abstract

Latent Diffusion Models (LDMs) can generate high-fidelity images from noise, offering a promising approach for augmenting histopathology images for training cancer grading models. While previous works successfully generated high-fidelity histopathology images using LDMs, the generation of image tiles to improve prostate cancer grading has not yet been explored. Additionally, LDMs face challenges in accurately generating admixtures of multiple cancer grades in a tile when conditioned by a tile mask. In this study, we train specific LDMs to generate synthetic tiles that contain multiple Gleason Grades (GGs) by leveraging pixel-wise annotations in input tiles. We introduce a novel framework named Self-Distillation from Separated Conditions (DISC) that generates GG patterns guided by GG masks. Finally, we deploy a training framework for pixel-level and slide-level prostate cancer grading, where synthetic tiles are effectively utilized to improve the cancer grading performance of existing models. As a result, this work surpasses previous works in two domains: 1) our LDMs enhanced with DISC produce more accurate tiles in terms of GG patterns, and 2) our training scheme, incorporating synthetic data, significantly improves the generalization of the baseline model for prostate cancer grading, particularly in challenging cases of rare GG5, demonstrating the potential of generative models to enhance cancer grading when data is limited.