Fully Automatic Deep Learning Pipeline for Whole Slide Image Quality Assessment

2024-11-25

arXiv.org

AI Summary

Artifacts (e.g., folds, blur, background regions) in whole-slide images (WSIs) degrade the performance of downstream deep learning models in computational pathology. Method: We propose an end-to-end WSI quality assessment and artifact region removal framework. Our approach integrates CNN and Vision Transformer (ViT) modules into a pixel-level semantic segmentation architecture, enabling unsupervised preprocessing-free quality grading. The model is trained on a large-scale, multi-source WSI dataset encompassing diverse organs, scanners, and staining protocols. Contribution/Results: Extensive internal and external multi-center validation demonstrates superior generalizability: artifact detection achieves >95% accuracy, precision, recall, and F1-score—significantly outperforming current state-of-the-art methods. By automatically identifying and excluding artifact-contaminated regions, our method substantially enhances the reliability and robustness of training data for computational pathology models.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Deep Neural Architectures and Foundation Models
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

In recent years, the use of deep learning (DL) methods, including convolutional neural networks (CNNs) and vision transformers (ViTs), has significantly advanced computational pathology, enhancing both diagnostic accuracy and efficiency. Hematoxylin and Eosin (H&E) Whole Slide Images (WSI) plays a crucial role by providing detailed tissue samples for the analysis and training of DL models. However, WSIs often contain regions with artifacts such as tissue folds, blurring, as well as non-tissue regions (background), which can negatively impact DL model performance. These artifacts are diagnostically irrelevant and can lead to inaccurate results. This paper proposes a fully automatic supervised DL pipeline for WSI Quality Assessment (WSI-QA) that uses a fused model combining CNNs and ViTs to detect and exclude WSI regions with artifacts, ensuring that only qualified WSI regions are used to build DL-based computational pathology applications. The proposed pipeline employs a pixel-based segmentation model to classify WSI regions as either qualified or non-qualified based on the presence of artifacts. The proposed model was trained on a large and diverse dataset and validated with internal and external data from various human organs, scanners, and H&E staining procedures. Quantitative and qualitative evaluations demonstrate the superiority of the proposed model, which outperforms state-of-the-art methods in WSI artifact detection. The proposed model consistently achieved over 95% accuracy, precision, recall, and F1 score across all artifact types. Furthermore, the WSI-QA pipeline shows strong generalization across different tissue types and scanning conditions.

Problem

• Detects artifacts in Whole Slide Images
• Improves DL model accuracy in pathology
• Ensures only qualified WSI regions used

Innovation

• Fused CNNs and ViTs model
• Pixel-based segmentation for WSI
• Automated artifact detection pipeline