arXiv 2407.061162024-05-15eess.IVcs.CVcs.LG

基于风格迁移数字病理的结肠H&E图像数据驱动细胞核亚分类

Data-driven Nucleus Subclassification on Colon H&E using Style-transferred Digital Pathology

Vanderbilt University（范德堡大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；National Institutes of Health（美国国立卫生研究院）；Vanderbilt University Medical Center（范德堡大学医学中心）；Vanderbilt University School of Medicine（范德堡大学医学院）；Veterans Affairs Tennessee Valley Healthcare System（田纳西河谷退伍军人事务医疗系统）

Lucas W. Remedios, Shunxing Bao, Samuel W. Remedios, Ho Hin Lee, Leon Y. Cai, Thomas Li, Ruining Deng, Nancy R. Newlin, Adam M. Saunders, Can Cui, Jia Li, Qi Li… 展开作者

Lucas W. Remedios, Shunxing Bao, Samuel W. Remedios, Ho Hin Lee, Leon Y. Cai, Thomas Li, Ruining Deng, Nancy R. Newlin, Adam M. Saunders, Can Cui, Jia Li, Qi Liu, Ken S. Lau, Joseph T. Roland, Mary K Washington, Lori A. Coburn, Keith T. Wilson, Yuankai Huo, Bennett A. Landman

备注：: arXiv admin note: text overlap with arXiv:2401.05602

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对H&E染色难以标注细胞亚类的问题，本研究结合MxIF标注与风格迁移生成带标签的虚拟H&E图像，训练监督学习模型，首次实现H&E图像上辅助性T细胞和上皮祖细胞的细胞核分类。

摘要：

理解细胞的通讯、共定位及相互关联方式对深化我们对机体功能的认知至关重要。H&E染色应用十分广泛，但细胞亚型分型通常需要专业知识以及特殊染色技术的辅助。为减轻标注负担，已有研究提出用AI对H&E图像中的细胞进行分类，例如近期的结肠细胞核识别与分类挑战赛（Colon Nucleus Identification and Classification, CoNIC）便聚焦于结肠H&E图像上6种细胞类型的标注。然而CoNIC挑战赛无法对上皮细胞亚型（祖细胞、肠内分泌细胞、杯状细胞）、淋巴细胞亚型（B细胞、辅助性T细胞、细胞毒性T细胞）以及结缔组织亚型（成纤维细胞）进行分类。\n我们采用跨模态学习方法，对H&E图像上此前无法标注的细胞类型进行标注。我们利用多重免疫荧光（multiplexed immunofluorescence, MxIF）组织学技术标注了14种细胞亚类。我们对相同的MxIF组织样本执行风格迁移，合成出逼真的虚拟H&E图像，并将其与源自MxIF的细胞亚分类标签配对。我们评估了一种监督学习方案的效果：该方案的输入为高逼真度虚拟H&E图像，标签为源自MxIF的细胞亚类。我们分别在私有虚拟H&E数据集和公开真实H&E数据集上评估了模型性能。\n在使用真实质心信息的情况下，模型在虚拟H&E图像上对辅助性T细胞和上皮祖细胞的阳性预测值分别为$0.34 \pm 0.15$（流行度$0.03 \pm 0.01$）和$0.47 \pm 0.1$（流行度$0.07 \pm 0.02$）；在真实H&E图像上，二者的阳性预测值上限分别为$0.43 \pm 0.03$（父类流行度0.21）和$0.94 \pm 0.02$（父类流行度0.49）。本研究是首个实现H&E图像上辅助性T细胞与上皮祖细胞核分类的工作。

英文摘要：

Understanding the way cells communicate, co-locate, and interrelate is essential to furthering our understanding of how the body functions. H&E is widely available, however, cell subtyping often requires expert knowledge and the use of specialized stains. To reduce the annotation burden, AI has been proposed for the classification of cells on H&E. For example, the recent Colon Nucleus Identification and Classification (CoNIC) Challenge focused on labeling 6 cell types on H&E of the colon. However, the CoNIC Challenge was unable to classify epithelial subtypes (progenitor, enteroendocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), and connective subtypes (fibroblasts). We use inter-modality learning to label previously un-labelable cell types on H&E. We take advantage of multiplexed immunofluorescence (MxIF) histology to label 14 cell subclasses. We performed style transfer on the same MxIF tissues to synthesize realistic virtual H&E which we paired with the MxIF-derived cell subclassification labels. We evaluated the efficacy of using a supervised learning scheme where the input was realistic-quality virtual H&E and the labels were MxIF-derived cell subclasses. We assessed our model on private virtual H&E and public real H&E. On virtual H&E, we were able to classify helper T cells and epithelial progenitors with positive predictive values of $0.34 \pm 0.15$ (prevalence $0.03 \pm 0.01$) and $0.47 \pm 0.1$ (prevalence $0.07 \pm 0.02$) respectively, when using ground truth centroid information. On real H&E we could classify helper T cells and epithelial progenitors with upper bound positive predictive values of $0.43 \pm 0.03$ (parent class prevalence 0.21) and $0.94 \pm 0.02$ (parent class prevalence 0.49) when using ground truth centroid information. This is the first work to provide cell type classification for helper T and epithelial progenitor nuclei on H&E.

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。