TUMLS：用于组织学全切片图像的可信完全无监督多级分割
TUMLS: Trustful Fully Unsupervised Multi-Level Segmentation for Whole Slide Images of Histology
AI总结：
针对数字病理学中WSI标注繁琐、AI方法缺乏信任度等问题，提出TUMLS方法，采用AE提取特征并结合不确定性度量实现无监督多级分割，在UPENN-GBM和MoNuSeg数据集上取得优异性能，可无缝集成临床工作流程并提升效率与透明度。
摘要：
人工智能（AI）增强的数字病理学在改善病理学家工作流程方面具有重要前景。然而，全切片图像（WSI）的人工密集型标注、高计算需求以及预测中缺乏不确定性估计引发的信任问题，阻碍了当前AI方法在组织病理学中的实际应用。为解决这些问题，我们提出了一种新颖的可信完全无监督多级分割方法（TUMLS）用于WSI。TUMLS采用自动编码器（AE）作为特征提取器，以识别低分辨率训练数据中的不同组织类型。它基于不确定性度量从每个识别的组中选择代表性补丁，然后在其各自的高分辨率空间中进行无监督细胞核分割，无需使用任何机器学习（ML）算法。至关重要的是，该解决方案无缝集成到临床医生的工作流程中，将整个WSI的检查转变为对简洁、可解释的跨层次见解的审查。这种集成显著增强并加速了工作流程，同时确保了透明度。我们使用UPENN-GBM数据集评估了我们的方法，其中AE实现了0.0016的均方误差（MSE）。此外，在MoNuSeg数据集上评估了细胞核分割，其F1分数为77.46%，Jaccard分数为63.35%，优于所有无监督方法。这些结果证明了TUMLS在推进数字病理学领域的有效性。
英文摘要：
Digital pathology, augmented by artificial intelligence (AI), holds significant promise for improving the workflow of pathologists. However, challenges such as the labor-intensive annotation of whole slide images (WSIs), high computational demands, and trust concerns arising from the absence of uncertainty estimation in predictions hinder the practical application of current AI methodologies in histopathology. To address these issues, we present a novel trustful fully unsupervised multi-level segmentation methodology (TUMLS) for WSIs. TUMLS adopts an autoencoder (AE) as a feature extractor to identify the different tissue types within low-resolution training data. It selects representative patches from each identified group based on an uncertainty measure and then does unsupervised nuclei segmentation in their respective higher-resolution space without using any ML algorithms. Crucially, this solution integrates seamlessly into clinicians workflows, transforming the examination of a whole WSI into a review of concise, interpretable cross-level insights. This integration significantly enhances and accelerates the workflow while ensuring transparency. We evaluated our approach using the UPENN-GBM dataset, where the AE achieved a mean squared error (MSE) of 0.0016. Additionally, nucleus segmentation is assessed on the MoNuSeg dataset, outperforming all unsupervised approaches with an F1 score of 77.46% and a Jaccard score of 63.35%. These results demonstrate the efficacy of TUMLS in advancing the field of digital pathology.
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。
