Massachusetts Institute of Technology (MIT), Department of Mechanical Engineering and Department of Biological Engineering, Cambridge, Massachusetts, United States.
J Biomed Opt. 2024 Jun;29(Suppl 2):S22710. doi: 10.1117/1.JBO.29.S2.S22710. Epub 2024 Aug 24.
Accurate cell segmentation and classification in three-dimensional (3D) images are vital for studying live cell behavior and drug responses in 3D tissue culture. Evaluating diverse cell populations in 3D cell culture over time necessitates non-toxic staining methods, as specific fluorescent tags may not be suitable, and immunofluorescence staining can be cytotoxic for prolonged live cell cultures.
We aim to perform machine learning-based cell classification within a live heterogeneous cell culture population grown in a 3D tissue culture relying only on reflectance, transmittance, and nuclei counterstained images obtained by confocal microscopy.
In this study, we employed a supervised convolutional neural network (CNN) to classify tumor cells and fibroblasts within 3D-grown spheroids. These cells are first segmented using the marker-controlled watershed image processing method. Training data included nuclei counterstaining, reflectance, and transmitted light images, with stained fibroblast and tumor cells as ground-truth labels.
Our results demonstrate the successful marker-controlled watershed segmentation of 84% of spheroid cells into single cells. We achieved a median accuracy of 67% (95% confidence interval of the median is 65-71%) in identifying cell types. We also recapitulate the original 3D images using the CNN-classified cells to visualize the original 3D-stained image's cell distribution.
This study introduces a non-invasive toxicity-free approach to 3D cell culture evaluation, combining machine learning with confocal microscopy, opening avenues for advanced cell studies.
在三维（3D）图像中准确地分割和分类细胞对于研究活细胞行为和 3D 组织培养中的药物反应至关重要。评估 3D 细胞培养中随时间变化的不同细胞群体需要非毒性染色方法，因为特定的荧光标记物可能不合适，而免疫荧光染色可能对长时间的活细胞培养具有细胞毒性。
我们旨在仅依靠共聚焦显微镜获得的反射率、透射率和核染色图像，在 3D 组织培养中生长的异质活细胞培养群体中进行基于机器学习的细胞分类。
在这项研究中，我们采用了有监督的卷积神经网络（CNN）来对 3D 培养的球体中的肿瘤细胞和成纤维细胞进行分类。这些细胞首先使用标记控制分水岭图像处理方法进行分割。训练数据包括核染色、反射率和透射光图像，用染色的成纤维细胞和肿瘤细胞作为真实标签。
我们的结果表明，成功地对 84%的球体细胞进行了标记控制分水岭分割，将其分割为单个细胞。我们在识别细胞类型方面取得了中位数准确率为 67%（中位数的 95%置信区间为 65-71%）的结果。我们还使用 CNN 分类的细胞重新生成原始的 3D 图像，以可视化原始 3D 染色图像的细胞分布。
本研究提出了一种非侵入性、无毒的 3D 细胞培养评估方法，将机器学习与共聚焦显微镜相结合，为先进的细胞研究开辟了道路。
