为计算病理系统配备伪影处理流水线：计算与性能权衡的展示
Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs
AI总结：
本文提出一种专家混合（MoE）方案，用于检测全玻片图像中的五种伪影，通过集成二元深度学习模型并应用概率阈值化，在多个医院和癌症类型的数据集上取得最佳性能（F1 86.15%，灵敏度97.93%），同时权衡计算成本，确保计算病理系统的可靠诊断。
摘要：
组织病理学是显微镜检查下癌症诊断的金标准。然而，组织学组织处理过程会产生伪影，这些伪影最终会转移到玻璃切片的数字化版本中，即全玻片图像（WSI）。伪影是诊断上无关的区域，可能导致深度学习（DL）算法的错误预测。因此，在计算病理（CPATH）系统中检测和排除伪影对于可靠的自动诊断至关重要。本文提出了一种专家混合（MoE）方案，用于检测五种显著的伪影，包括受损组织、模糊、折叠组织、气泡以及组织学上无关的血液，这些均来自WSI。首先，我们训练独立的二元DL模型作为专家，以捕捉特定伪影的形态。然后，我们使用融合机制集成它们的预测。我们对最终概率分布应用概率阈值化，以提高MoE的灵敏度。我们使用两个MoE和两个多类模型（基于最先进的深度卷积神经网络（DCNN）和视觉变换器（ViT））开发了DL流水线。基于DCNN的MoE和基于ViT的MoE方案优于更简单的多类模型，并在来自不同医院和癌症类型的数据集上进行了测试，其中使用DCNN的MoE取得了最佳结果。所提出的MoE在未见数据上取得了86.15%的F1分数和97.93%的灵敏度，且推理计算成本低于使用ViT的MoE。MoE的这种最佳性能伴随着相对高于多类模型的计算权衡。所提出的伪影检测流水线不仅将确保可靠的CPATH预测，还可能提供质量控制。
英文摘要：
Histopathology is a gold standard for cancer diagnosis under a microscopic examination. However, histological tissue processing procedures result in artifacts, which are ultimately transferred to the digitized version of glass slides, known as whole slide images (WSIs). Artifacts are diagnostically irrelevant areas and may result in wrong deep learning (DL) algorithms predictions. Therefore, detecting and excluding artifacts in the computational pathology (CPATH) system is essential for reliable automated diagnosis. In this paper, we propose a mixture of experts (MoE) scheme for detecting five notable artifacts, including damaged tissue, blur, folded tissue, air bubbles, and histologically irrelevant blood from WSIs. First, we train independent binary DL models as experts to capture particular artifact morphology. Then, we ensemble their predictions using a fusion mechanism. We apply probabilistic thresholding over the final probability distribution to improve the sensitivity of the MoE. We developed DL pipelines using two MoEs and two multiclass models of state-of-the-art deep convolutional neural networks (DCNNs) and vision transformers (ViTs). DCNNs-based MoE and ViTs-based MoE schemes outperformed simpler multiclass models and were tested on datasets from different hospitals and cancer types, where MoE using DCNNs yielded the best results. The proposed MoE yields 86.15% F1 and 97.93% sensitivity scores on unseen data, retaining less computational cost for inference than MoE using ViTs. This best performance of MoEs comes with relatively higher computational trade-offs than multiclass models. The proposed artifact detection pipeline will not only ensure reliable CPATH predictions but may also provide quality control.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
