Pathology Image Compression with Pre-trained Autoencoders

2025-03-14

AI Summary

Digital pathology whole-slide images (WSIs) pose significant challenges due to their enormous storage and transmission overhead, while generic compression methods (e.g., JPEG) discard diagnostically critical fine-grained phenotypic details. To address this, we propose the first learnable WSI compression framework based on a pretrained latent diffusion model (LDM) autoencoder—marking the first adaptation of an LDM encoder for pathological image compression. Our method introduces a pathology-aware fine-tuning strategy and a K-means-based latent variable quantization scheme to balance reconstruction fidelity and compression ratio. It integrates a pathology foundation model–driven perceptual loss, latent-space quantization, and multi-task downstream validation (segmentation, classification, and multiple-instance learning). Experiments demonstrate <1.5% degradation in downstream task performance, 3–8× higher compression ratios compared to baselines, and faithful preservation of diagnostically relevant fine-grained structures. All fine-tuned weights are publicly released.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Data Compression

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The growing volume of high-resolution Whole Slide Images in digital histopathology poses significant storage, transmission, and computational efficiency challenges. Standard compression methods, such as JPEG, reduce file sizes but often fail to preserve fine-grained phenotypic details critical for downstream tasks. In this work, we repurpose autoencoders (AEs) designed for Latent Diffusion Models as an efficient learned compression framework for pathology images. We systematically benchmark three AE models with varying compression levels and evaluate their reconstruction ability using pathology foundation models. We introduce a fine-tuning strategy to further enhance reconstruction fidelity that optimizes a pathology-specific learned perceptual metric. We validate our approach on downstream tasks, including segmentation, patch classification, and multiple instance learning, showing that replacing images with AE-compressed reconstructions leads to minimal performance degradation. Additionally, we propose a K-means clustering-based quantization method for AE latents, improving storage efficiency while maintaining reconstruction quality. We provide the weights of the fine-tuned autoencoders at https://huggingface.co/collections/StonyBrook-CVLab/pathology-fine-tuned-aes-67d45f223a659ff2e3402dd0.

Problem

• Address storage and transmission challenges in digital histopathology.
• Preserve fine-grained phenotypic details in compressed pathology images.
• Enhance computational efficiency for downstream pathology tasks.

Innovation

• Autoencoders repurposed for pathology image compression
• Fine-tuning strategy enhances reconstruction fidelity
• K-means clustering improves storage efficiency