Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.24037

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

Julia Merta·Daniel Mendelsohn·Benedikt Schoser·Joanna Polanska·Michal Marczyk
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

eess.IVcs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Julia Merta, Daniel Mendelsohn, Benedikt Schoser, Joanna Polanska, Michal Marczyk. 2026-10-16. Benchmarking and Improvement of Artifact Segmentation Methods in H&E-Stained Whole Slide Imaging. https://arxiv.org/abs/2610.24037

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Image CL-SEC: Cross-Layer Semantic Error Correction for Image Communication

Semantic error correction (SEC) uses the semantic knowledge of pretrained models to complement conventional channel decoding. By combining physical-layer decoding information with application-layer semantic predictions, cross-layer SEC (CL-SEC) has demonstrated substantial performance gains in text transmission; however, its applicability to image transmission remains largely unexplored. This paper proposes Image CL-SEC, which, to the best of our knowledge, is the first extension of the CL-SEC framework to image transmission. Image CL-SEC uses channel-decoding information together with contextual predictions from a pretrained visual model to resolve residual uncertainty after forward error correction (FEC) decoding. In our implementation, images are represented as discrete visual tokens. For each token position selected for re-evaluation, the probability distribution produced by the channel decoder is combined with the distribution predicted by the visual model to identify the most likely transmitted token. The resulting decision therefore reflects both channel evidence and visual context. Experiments across multiple channel conditions show that, at low and moderate signal-to-noise ratios (SNRs), Image CL-SEC improves pixel-level fidelity, perceptual similarity, and token-recovery accuracy relative to either channel decoding or visual-model inference alone. Supplementary experiments using different pretrained visual models further demonstrate that these gains are not specific to a single model.

eess.IV↗
arXiv2026

Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors

MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that magnitude-only measurements may provide complementary information for signal recovery. However, their use in MRI reconstruction remains largely unexplored, due to lack of practical settings where informative magnitude measurements can be obtained without additional scan time. In this work, we investigate the use of auxiliary k-space magnitude information for accelerated steady-state dynamic MRI reconstruction, and demonstrate strong consistency of k-space magnitudes across time-frames. Building on this observation, we propose $\mathbb{C}+\text{Mag}$, a magnitude-informed physics-driven deep learning reconstruction method. The proposed method employs an ADMM-based unrolling framework with a novel magnitude-aware data-fidelity formulation, where quadratically smoothed optimization and momentum-based updates are introduced to address the non-differentiability and non-convexity of the magnitude constraints. Experiments on retrospectively undersampled cine MRI and phase-contrast flow MRI datasets, as well as prospectively undersampled real-time cine MRI acquisitions, demonstrate improved artifact suppression, sharper anatomical recovery, and better preservation of phase information compared to conventional PD-DL methods, which is further supported through blinded expert reader evaluations.

eess.IV↗
arXiv2026

ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing

Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on frame-to-frame transition models. However, these models are fragile when observations are non-Markovian (when they form only a partial slice of a higher-dimensional latent state as in real-world weather data): they tend to accumulate errors over long horizons. At the same time, learned DA methods typically commit to a single regime, either filtering (nowcasting, real-time forecasting) or smoothing (retrospective reanalysis), which splits what should be a shared prior across application-specific pipelines. To address both issues, we introduce ForcingDAS, a unified and robust DA framework. Built on Diffusion Forcing with an independent noise level assigned to each frame, ForcingDAS learns a joint-trajectory prior instead of frame-to-frame transitions. This allows it to capture long-horizon temporal dependencies and reduce error accumulation. In addition, the same trained model spans the full filtering to smoothing spectrum at inference time. Specifically, nowcasting, fixed-lag smoothing, and batch reanalysis are selected through the inference schedule alone, without retraining. We evaluate ForcingDAS on 2D Navier-Stokes vorticity, precipitation nowcasting, and global atmospheric state estimation. Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.

eess.IV↗