Benchmarking and Improvement of Artifact Segmentation Methods in H&E-Stained Whole Slide Imaging

Abstract

Technical artifacts introduced during tissue preparation or slide scanning remain a major obstacle to developing robust computational pathology algorithms for hematoxylin and eosin (HE)-stained whole-slide images (WSIs). Despite the growing number of quality-control tools, their real-world utility remains hard to assess because of the limited number of publicly available implementations and the lack of systematic, multi-dataset comparisons. This paper presents a benchmark of artifact segmentation methods for HE-stained WSIs. After a literature review, six publicly available algorithms were selected and compared in terms of their ability to segment artifact-free tissue and selected artifact classes. Two publicly available datasets and a newly introduced dataset released to support further research were used for evaluation. Tissue samples from multiple medical centers and different organs are included, enabling evaluation across heterogeneous data sources. Segmentation performance was assessed using Dice Index, pixel-level recall, and false discovery rate for artifact-free tissue segmentation. For algorithms supporting multiclass artifact segmentation, class-wise Dice Index and inter-class misclassification were evaluated. In addition to segmentation quality, processing time was assessed. Statistical analysis revealed significant differences in segmentation performance between methods. HistoKit, which incorporates a modified version of the GrandQC, was identified as the best-performing algorithm, while HistoQC was the worst. In terms of artifact types, dark spots and out of focus regions were harder to segment than others. Finally, a simple post-processing step was introduced for HistoKit, which further improved segmentation performance. The benchmark establishes a reference for evaluating and developing artifact segmentation methods for HE-stained WSIs.