Learning to segment clustered amoeboid cells from brightfield microscopy via multi-task learning with adaptive weight selection
Learning to segment clustered amoeboid cells from brightfield microscopy via multi-task learning with adaptive weight selection
复制标题
通过具有自适应权重选择的多任务学习，学习从明场显微镜中分割聚集的变形虫细胞
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Jean
中科院分区：
文献类型：
--
作者：
Rituparna Sarkar;Suvadip Mukherjee;E. Labruyère;Jean
从显微图像中检测和分割单个细胞对于各种生命科学应用至关重要。由于对比度和强度异质性较差，传统的细胞分割工具通常不适合在明场显微镜中应用，并且只有一小部分适用于分割簇中的细胞。在这方面，我们在多任务学习范式中引入了一种用于细胞分割的新型监督技术。采用基于区域和单元边界检测的多任务损失的组合来提高网络的预测效率。学习问题是在一种新颖的最小-最大框架中提出的，该框架能够以自动方式自适应估计超参数。通过形态学操作和活动轮廓模型组合区域和细胞边界预测来分割单个细胞。所提出的方法特别适合从明场显微镜图像中分割接触细胞，无需手动干预。从数量上看，我们观察到验证集上的总体 Dice 得分为 0.93，比最近的无监督方法提高了 15.9% 以上，平均比流行的有监督 U-net 算法至少高出 5.8%。
Detecting and segmenting individual cells from microscopy images is critical to various life science applications. Traditional cell segmentation tools are often ill-suited for applications in brightfield microscopy due to poor contrast and intensity heterogeneity, and only a small subset are applicable to segment cells in a cluster. In this regard, we introduce a novel supervised technique for cell segmentation in a multitask learning paradigm. A combination of a multi-task loss, based on the region and cell boundary detection, is employed for an improved prediction efficiency of the network. The learning problem is posed in a novel min-max framework which enables adaptive estimation of the hyper-parameters in an automatic fashion. The region and cell boundary predictions are combined via morphological operations and active contour model to segment individual cells. The proposed methodology is particularly suited to segment touching cells from brightfield microscopy images without manual interventions. Quantitatively, we observe an overall Dice score of 0.93 on the validation set, which is an improvement of over 15.9% on a recent unsupervised method, and outperforms the popular supervised U-net algorithm by at least 5.8% on average.