Automated Segmentation of Fluorescence Microscopy Images for 3D Cell Detection in human- derived Cardiospheres
Automated Segmentation of Fluorescence Microscopy Images for 3D Cell Detection in human- derived Cardiospheres
复制标题
DOI：
10.1038/s41598-019-43137-2
复制
发表时间：
2019-04-30
影响因子：
4.6
通讯作者：
Molinari, Filippo
中科院分区：
文献类型：
--
作者：
Salvi, Massimo;Morbiducci, Umberto;Molinari, Filippo
“心脏圈”是心脏祖细胞的 3D 簇，再现了干细胞微环境，具有对衰竭的人类心肌进行疾病和再生建模的潜力。在这种多细胞 3D 背景下，解密细胞标记的空间分布对于通过在共聚焦显微镜中直接量化荧光信号来剖析细胞表型的进化非常重要。在这项研究中，我们提出了一种名为 CARE（“CARdiosphere 评估”）的全自动方法，用于分割人源心脏圈中的膜和细胞核。所提出的方法在 20 个心球 3D 堆栈上进行了测试，总共 1160 个图像。将自动结果与手动注释和两个专为荧光显微镜设计的开源软件进行比较。 CARE 在心球膜分割方面表现出色，在细胞核检测方面，该算法实现了与两名专家操作员相同的性能。据我们所知，CARE 是第一个用于体外 3D 细胞球体（包括心脏球体）内部分割的全自动算法。所提出的方法将在未来提供心脏生态位环境中标记物分布的自动定量分析，从而实现细胞机械应力和动态表型变化之间的预测关联。
The 'cardiosphere' is a 3D cluster of cardiac progenitor cells recapitulating a stem cell niche-like microenvironment with a potential for disease and regeneration modelling of the failing human myocardium. In this multicellular 3D context, it is extremely important to decrypt the spatial distribution of cell markers for dissecting the evolution of cellular phenotypes by direct quantification of fluorescent signals in confocal microscopy. In this study, we present a fully automated method, named CARE ('CARdiosphere Evaluation'), for the segmentation of membranes and cell nuclei in humanderived cardiospheres. The proposed method is tested on twenty 3D-stacks of cardiospheres, for a total of 1160 images. Automatic results are compared with manual annotations and two open-source software designed for fluorescence microscopy. CARE performance was excellent in cardiospheres membrane segmentation and, in cell nuclei detection, the algorithm achieved the same performance as two expert operators. To the best of our knowledge, CARE is the first fully automated algorithm for segmentation inside in vitro 3D cell spheroids, including cardiospheres. The proposed approach will provide, in the future, automated quantitative analysis of markers distribution within the cardiac niche-like environment, enabling predictive associations between cell mechanical stresses and dynamic phenotypic changes.