Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China.
Department of Systems Biology, Harvard Medical School, Boston, MA, USA.
Sci Rep. 2022 Jan 10;12(1):342. doi: 10.1038/s41598-021-04048-3.
Cell segmentation plays a crucial role in understanding, diagnosing, and treating diseases. Despite the recent success of deep learning-based cell segmentation methods, it remains challenging to accurately segment densely packed cells in 3D cell membrane images. Existing approaches also require fine-tuning multiple manually selected hyperparameters on the new datasets. We develop a deep learning-based 3D cell segmentation pipeline, 3DCellSeg, to address these challenges. Compared to the existing methods, our approach carries the following novelties: (1) a robust two-stage pipeline, requiring only one hyperparameter; (2) a light-weight deep convolutional neural network (3DCellSegNet) to efficiently output voxel-wise masks; (3) a custom loss function (3DCellSeg Loss) to tackle the clumped cell problem; and (4) an efficient touching area-based clustering algorithm (TASCAN) to separate 3D cells from the foreground masks. Cell segmentation experiments conducted on four different cell datasets show that 3DCellSeg outperforms the baseline models on the ATAS (plant), HMS (animal), and LRP (plant) datasets with an overall accuracy of 95.6%, 76.4%, and 74.7%, respectively, while achieving an accuracy comparable to the baselines on the Ovules (plant) dataset with an overall accuracy of 82.2%. Ablation studies show that the individual improvements in accuracy is attributable to 3DCellSegNet, 3DCellSeg Loss, and TASCAN, with the 3DCellSeg demonstrating robustness across different datasets and cell shapes. Our results suggest that 3DCellSeg can serve a powerful biomedical and clinical tool, such as histo-pathological image analysis, for cancer diagnosis and grading.
细胞分割在理解、诊断和治疗疾病方面起着至关重要的作用。尽管基于深度学习的细胞分割方法最近取得了成功，但在 3D 细胞膜图像中准确分割密集排列的细胞仍然具有挑战性。现有的方法还需要在新数据集上微调多个手动选择的超参数。我们开发了一种基于深度学习的 3D 细胞分割管道 3DCellSeg，以解决这些挑战。与现有的方法相比，我们的方法具有以下新颖性：（1）一个强大的两阶段管道，仅需要一个超参数；（2）一个轻量级的深度卷积神经网络（3DCellSegNet），以有效地输出体素级别的掩模；（3）一个自定义损失函数（3DCellSeg Loss），以解决细胞聚集问题；（4）一个高效的基于触面的聚类算法（TASCAN），以将 3D 细胞从前景掩模中分离出来。在四个不同的细胞数据集上进行的细胞分割实验表明，3DCellSeg 在 ATAS（植物）、HMS（动物）和 LRP（植物）数据集上的表现优于基线模型，总体准确率分别为 95.6%、76.4%和 74.7%，而在 Ovules（植物）数据集上的准确率与基线模型相当，总体准确率为 82.2%。消融研究表明，精度的个别提高归因于 3DCellSegNet、3DCellSeg Loss 和 TASCAN，而 3DCellSeg 在不同数据集和细胞形状上表现出稳健性。我们的结果表明，3DCellSeg 可以作为一种强大的生物医学和临床工具，如组织病理学图像分析，用于癌症诊断和分级。
