A robust and scalable framework for hallucination detection in virtual tissue staining and digital pathology
arXiv:2404.18458 · doi:10.1038/s41551-025-01421-9
Abstract
Histopathological staining of human tissue is essential for disease diagnosis. Recent advances in virtual tissue staining technologies using artificial intelligence (AI) alleviate some of the costly and tedious steps involved in traditional histochemical staining processes, permitting multiplexed staining and tissue preservation. However, potential hallucinations and artifacts in these virtually stained tissue images pose concerns, especially for the clinical uses of these approaches. Quality assessment of histology images by experts can be subjective. Here, we present an autonomous quality and hallucination assessment method, AQuA, for virtual tissue staining and digital pathology. AQuA autonomously achieves 99.8% accuracy when detecting acceptable and unacceptable virtually stained tissue images without access to histochemically stained ground truth, and presents an agreement of 98.5% with the manual assessments made by board-certified pathologists, including identifying realistic-looking images that could mislead diagnosticians. We demonstrate the wide adaptability of AQuA across various virtually and histochemically stained human tissue images. This framework enhances the reliability of virtual tissue staining and provides autonomous quality assurance for image generation and transformation tasks in digital pathology and computational imaging.
45 Pages, 22 Figures, 2 Tables
References in corpus (16)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue
- TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
- PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learning
- Deep Learning-enabled Virtual Histological Staining of Biological Samples
- Deep learning-based transformation of the H&E stain into special stains
- Comparison of Image Quality Models for Optimization of Image Processing Systems
- Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissue
- HoloStain: Holographic virtual staining of individual biological cells
- Self-supervised learning of hologram reconstruction using physics consistency
- Label-free virtual HER2 immunohistochemical staining of breast tissue using deep learning
- Virtual stain transfer in histology via cascaded deep neural networks
- Digital staining in optical microscopy using deep learning -- a review
- Virtual staining of defocused autofluorescence images of unlabeled tissue using deep neural networks
- Cycle Consistency-based Uncertainty Quantification of Neural Networks in Inverse Imaging Problems