Evaluation Metric for Quality Control and Generative Models in Histopathology Images

TL;DR

This paper introduces RL2, a new, efficient metric based on ResNet features and normalizing flows for evaluating the quality of generative models in histopathology images, especially effective with limited data.

Contribution

The paper presents RL2, a novel metric that overcomes limitations of traditional metrics like FID in histopathology, offering reliable, fast, and data-efficient image quality assessment.

Findings

RL2 shows a monotonic response to increasing image degradation.

RL2 outperforms traditional metrics in stability with fewer images.

RL2 is faster and lighter than existing evaluation metrics.

Abstract

Our study introduces ResNet-L2 (RL2), a novel metric for evaluating generative models and image quality in histopathology, addressing limitations of traditional metrics, such as Frechet inception distance (FID), when the data is scarce. RL2 leverages ResNet features with a normalizing flow to calculate RMSE distance in the latent space, providing reliable assessments across diverse histopathology datasets. We evaluated the performance of RL2 on degradation types, such as blur, Gaussian noise, salt-and-pepper noise, and rectangular patches, as well as diffusion processes. RL2's monotonic response to increasing degradation makes it well-suited for models that assess image quality, proving a valuable advancement for evaluating image generation techniques in histopathology. It can also be used to discard low-quality patches while sampling from a whole slide image. It is also significantly lighter and faster compared to traditional metrics and requires fewer images to give stable metric value.