NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer.
NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer.
复制标题
NuCLS：用于乳腺癌细胞核分类和分割的可扩展众包方法和数据集。
DOI：
10.1093/gigascience/giac037
复制
发表时间：
2022-05-17
期刊：
影响因子：
9.2
通讯作者：
中科院分区：
文献类型：
--
作者：
深度学习能够对细胞和组织结构进行准确的高分辨率映射，这可以作为计算病理学的可解释机器学习模型的基础。然而，考虑到病理学家所需的时间和精力，为这些结构生成足够的标记是一个关键障碍。这篇文章描述了一种新的协作框架，用于吸引医学生和病理学家群体来为细胞核制作质量标签。我们使用这种方法生成了NuCLS数据集，其中包含乳腺癌细胞核的220,000个注释。这建立在标记组织区域以产生用于训练的综合组织区域和细胞级别注释数据集的基础上，该数据集是用于乳腺癌组织学多尺度分析的最大此类资源。本文介绍了来自非专家和病理学家的单个和多个评分者注释的数据和分析结果。我们提出了一种新的工作流程，它使用算法建议来收集准确的分割数据，而不需要费力的人工追踪细胞核。我们的结果表明，即使是嘈杂的算法建议也不会对病理学家的准确性产生负面影响，并且可以帮助非专家提高注释质量。我们还提出了一种从多个评分者那里推断真理的新方法，并展示了非专家可以为视觉上不同的类别产生准确的注释。这项研究是大规模使用群体智慧方法为计算病理学应用生成数据的最广泛的系统探索。
Deep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists. This article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes. This study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.
登录
查看更多内容
影响因子：
4.6
作者：
Cooper, Lee A. D.;Kong, Jun;Saltz, Joel H.
通讯作者：
Saltz, Joel H.
影响因子：
3.3
作者：
Alexander, C. Bruce
通讯作者：
Alexander, C. Bruce
影响因子：
--
作者：
Dudgeon SN;Wen S;Hanna MG;Gupta R;Amgad M;Sheth M;Marble H;Huang R;Herrmann MD;Szu CH;Tong D;Werness B;Szu E;Larsimont D;Madabhushi A;Hytopoulos E;Chen W;Singh R;Hart SN;Sharma A;Saltz J;Salgado R;Gallas BD
通讯作者：
Gallas BD
影响因子：
5.8
作者：
Amgad, Mohamed;Elfandy, Habiba;Cooper, Lee A. D.
通讯作者：
Cooper, Lee A. D.
影响因子：
2.7
作者：
COHEN, J
通讯作者：
COHEN, J