Dataset Information

Learn to segment single cells with deep distance estimator and deep cell detector.

ABSTRACT: Single cell segmentation is a critical and challenging step in cell imaging analysis. Traditional processing methods require time and labor to manually fine-tune parameters and lack parameter transferability between different situations. Recently, deep convolutional neural networks (CNN) treat segmentation as a pixel-wise classification problem and have become a general and efficient method for image segmentation. However, cell imaging data often possesses characteristics that adversely affect segmentation accuracy: absence of established training datasets, few pixels on cell boundaries, and ubiquitous blurry features. We developed a strategy that combines strengths of CNN and traditional watershed algorithm. First, we trained a CNN to learn Euclidean distance transform (EDT) of the mask corresponding to the input images (deep distance estimator). Next, we trained a faster R-CNN (Region with CNN) to detect individual cells in the EDT image (deep cell detector). Then, the watershed algorithm performed the final segmentation using the outputs of previous two steps. Tests on a library of fluorescence, phase contrast and differential interference contrast (DIC) images showed that both the combined method and various forms of the pixel-wise classification algorithm achieved similar pixel-wise accuracy. However, the combined method achieved significantly higher cell count accuracy than the pixel-wise classification algorithm did, with the latter performing poorly when separating connected cells, especially those connected by blurry boundaries. This difference is most obvious when applied to noisy images of densely packed cells. Furthermore, both deep distance estimator and deep cell detector converge fast and are easy to train.

SUBMITTER: Wang W

PROVIDER: S-EPMC6781873 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Learn to segment single cells with deep distance estimator and deep cell detector.

Wang Weikang W Taft David A DA Chen Yi-Jiun YJ Zhang Jingyu J Wallace Callen T CT Xu Min M Watkins Simon C SC Xing Jianhua J

Computers in biology and medicine 20190408

Single cell segmentation is a critical and challenging step in cell imaging analysis. Traditional processing methods require time and labor to manually fine-tune parameters and lack parameter transferability between different situations. Recently, deep convolutional neural networks (CNN) treat segmentation as a pixel-wise classification problem and have become a general and efficient method for image segmentation. However, cell imaging data often possesses characteristics that adversely affect s ...[more]

PMID: 31005005

Similar Datasets

Project description:BackgroundDistance-based methods are popular for reconstructing evolutionary trees thanks to their speed and generality. A number of methods exist for estimating distances from sequence alignments, which often involves some sort of correction for multiple substitutions. The problem is to accurately estimate the number of true substitutions given an observed alignment. So far, the most accurate protein distance estimators have looked for the optimal matrix in a series of transition probability matrices, e.g. the Dayhoff series. The evolutionary distance between two aligned sequences is here estimated as the evolutionary distance of the optimal matrix. The optimal matrix can be found either by an iterative search for the Maximum Likelihood matrix, or by integration to find the Expected Distance. As a consequence, these methods are more complex to implement and computationally heavier than correction-based methods. Another problem is that the result may vary substantially depending on the evolutionary model used for the matrices. An ideal distance estimator should produce consistent and accurate distances independent of the evolutionary model used.ResultsWe propose a correction-based protein sequence estimator called Scoredist. It uses a logarithmic correction of observed divergence based on the alignment score according to the BLOSUM62 score matrix. We evaluated Scoredist and a number of optimal matrix methods using three evolutionary models for both training and testing Dayhoff, Jones-Taylor-Thornton, and Muller-Vingron, as well as Whelan and Goldman solely for testing. Test alignments with known distances between 0.01 and 2 substitutions per position (1-200 PAM) were simulated using ROSE. Scoredist proved as accurate as the optimal matrix methods, yet substantially more robust. When trained on one model but tested on another one, Scoredist was nearly always more accurate. The Jukes-Cantor and Kimura correction methods were also tested, but were substantially less accurate.ConclusionThe Scoredist distance estimator is fast to implement and run, and combines robustness with accuracy. Scoredist has been incorporated into the Belvu alignment viewer, which is available at ftp://ftp.cgb.ki.se/pub/prog/belvu/.

Project description:Encapsulation of cells inside microfluidic droplets is central to several applications involving cellular analysis. Although, theoretically the encapsulation statistics are expected to follow a Poisson distribution, experimentally this may not be achieved due to lack of full control of the experimental variables and conditions. Therefore, there is a need for automatic detection of droplets and cell count enumeration within droplets so a process control feedback to adjust experimental conditions can be implemented. In this study, we use a deep learning object detector called You Only Look Once (YOLO), an influential class of object detectors with several benefits over traditional methods. This paper investigates the application of both YOLOv3 and YOLOv5 object detectors in the development of an automated droplet and cell detector. Experimental data was obtained from a microfluidic flow focusing device with a dispersed phase of cancer cells. The microfluidic device contained an expansion chamber downstream of the droplet generator, allowing for visualization and recording of cell-encapsulated droplet images. In the procedure, a droplet bounding box is predicted, then cropped from the original image for the individual cells to be detected through a separate model for further examination. The system includes a production set for additional performance analysis with Poisson statistics while providing an experimental workflow with both droplet and cell models. The training set is collected and preprocessed before labeling and applying image augmentations, allowing for a generalizable object detector. Precision and recall were utilized as a validation and test set metric, resulting in a high mean average precision (mAP) metric for an accurate droplet detector. To examine model limitations, the predictions were compared to ground truth labels, illustrating that the YOLO predictions closely matched with the droplet and cell labels. Furthermore, it is demonstrated that droplet enumeration from the YOLOv5 model is consistent with hand counted ratios and the Poisson distribution, confirming that the platform can be used in real-time experiments for cell encapsulation optimization.

Dataset Information

Learn to segment single cells with deep distance estimator and deep cell detector.

Publications

Learn to segment single cells with deep distance estimator and deep cell detector.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets