Automation of Caenorhabditis elegans lifespan assay using a simplified domain synthetic image-based neural network training strategy.

Performing lifespan assays with Caenorhabditis elegans (C. elegans) nematodes manually is a time consuming and laborious task. Therefore, automation is necessary to increase productivity. In this paper, we propose a method to automate the counting of live C. elegans using deep learning. The survival curves of the experiment are obtained using a sequence formed by an image taken on each day of the assay. Solving this problem would require a very large labeled dataset; thus, to facilitate its generation, we propose a simplified image-based strategy. This simplification consists of transforming the real images of the nematodes in the Petri dish to a synthetic image, in which circular blobs are drawn on a constant background to mark the position of the C. elegans. To apply this simplification method, it is divided into two steps. First, a Faster R-CNN network detects the C. elegans, allowing its transformation into a synthetic image. Second, using the simplified image sequence as input, a regression neural network is in charge of predicting the count of live nematodes on each day of the experiment. In this way, the counting network was trained using a simple simulator, avoiding labeling a very large real dataset or developing a realistic simulator. Results showed that the differences between the curves obtained by the proposed method and the manual curves are not statistically significant for either short-lived N2 (p-value log rank test 0.45) or long-lived daf-2 (p-value log rank test 0.83) strains.

Towards generalization for Caenorhabditis elegans detection.

The nematode Caenorhabditis elegans (C. elegans) is of significant interest for research into neurodegenerative diseases, aging, and drug screening. However, conducting these assays manually is a tedious and time-consuming process. This paper proposes a methodology to achieve a generalist C. elegans detection algorithm, as previous work only focused on dataset-specific detection, tailored exclusively to the characteristics and appearance of the images in a given dataset. The main aim of our study is to achieve a solution that allows for robust detection, regardless of the image-capture system used, with the potential to serve as a basis for the automation of numerous assays. These potential applications include worm counting, worm tracking, motion detection and motion characterization. To train this model, a dataset consisting of a wide variety of appearances adopted by C. elegans has been curated and dataset augmentation methods have been proposed and evaluated, including synthetic image generation. The results show that the model achieves an average precision of 89.5% for a wide variety of C. elegans appearances that were not used during training, thereby validating its generalization capabilities.

Automatic segmentation of Caenorhabditis elegans skeletons in worm aggregations using improved U-Net in low-resolution image sequences.

Pose estimation of C. elegans in image sequences is challenging and even more difficult in low-resolution images. Problems range from occlusions, loss of worm identity, and overlaps to aggregations that are too complex or difficult to resolve, even for the human eye. Neural networks, on the other hand, have shown good results in both low-resolution and high-resolution images. However, training in a neural network model requires a very large and balanced dataset, which is sometimes impossible or too expensive to obtain. In this article, a novel method for predicting C. elegans poses in cases of multi-worm aggregation and aggregation with noise is proposed. To solve this problem we use an improved U-Net model capable of obtaining images of the next aggregated worm posture. This neural network model was trained/validated using a custom-generated dataset with a synthetic image simulator. Subsequently, tested with a dataset of real images. The results obtained were greater than 75% in precision and 0.65 with Intersection over Union (IoU) values.

Analysis of a C. elegans lifespan prediction method based on a bimodal neural network and uncertainty estimation.

In recent decades, assays with the nematode Caenorhabditis elegans (C. elegans) have enabled great advances to be made in research on aging. However, performing these assays manually is a laborious task. To solve this problem, numerous C. elegans assay automation techniques are being developed to increase throughput and accuracy. In this paper, a method for predicting the lifespan of C. elegans nematodes using a bimodal neural network is proposed and analyzed. Specifically, the model uses the sequence of images and the count of live C. elegans up to the current day to predict the lifespan curve termination. This network has been trained using a simulator to avoid the labeling costs of training such a model. In addition, a method for estimating the uncertainty of the model predictions has been proposed. Using this uncertainty, a criterion has been analyzed to decide at what point the assay could be halted and the user could rely on the model's predictions. The method has been analyzed and validated using real experiments. The results show that uncertainty is reduced from the mean lifespan and that most of the predictions obtained do not present statistically significant differences with respect to the curves obtained manually.

Caenorhabditis elegans Multi-Tracker Based on a Modified Skeleton Algorithm.

Automatic tracking of Caenorhabditis elegans (C. egans) in standard Petri dishes is challenging due to high-resolution image requirements when fully monitoring a Petri dish, but mainly due to potential losses of individual worm identity caused by aggregation of worms, overlaps and body contact. To date, trackers only automate tests for individual worm behaviors, canceling data when body contact occurs. However, essays automating contact behaviors still require solutions to this problem. In this work, we propose a solution to this difficulty using computer vision techniques. On the one hand, a skeletonization method is applied to extract skeletons in overlap and contact situations. On the other hand, new optimization methods are proposed to solve the identity problem during these situations. Experiments were performed with 70 tracks and 3779 poses (skeletons) of C. elegans. Several cost functions with different criteria have been evaluated, and the best results gave an accuracy of 99.42% in overlapping with other worms and noise on the plate using the modified skeleton algorithm and 98.73% precision using the classical skeleton algorithm.

Towards Lifespan Automation for Caenorhabditis elegans Based on Deep Learning: Analysing Convolutional and Recurrent Neural Networks for Dead or Live Classification.

The automation of lifespan assays with C. elegans in standard Petri dishes is a challenging problem because there are several problems hindering detection such as occlusions at the plate edges, dirt accumulation, and worm aggregations. Moreover, determining whether a worm is alive or dead can be complex as they barely move during the last few days of their lives. This paper proposes a method combining traditional computer vision techniques with a live/dead C. elegans classifier based on convolutional and recurrent neural networks from low-resolution image sequences. In addition to proposing a new method to automate lifespan, the use of data augmentation techniques is proposed to train the network in the absence of large numbers of samples. The proposed method achieved small error rates (3.54% ± 1.30% per plate) with respect to the manual curve, demonstrating its feasibility.

Improving skeleton algorithm for helping Caenorhabditis elegans trackers.

One of the main problems when monitoring Caenorhabditis elegans nematodes (C. elegans) is tracking their poses by automatic computer vision systems. This is a challenge given the marked flexibility that their bodies present and the different poses that can be performed during their behaviour individually, which become even more complicated when worms aggregate with others while moving. This work proposes a simple solution by combining some computer vision techniques to help to determine certain worm poses and to identify each one during aggregation or in coiled shapes. This new method is based on the distance transformation function to obtain better worm skeletons. Experiments were performed with 205 plates, each with 10, 15, 30, 60 or 100 worms, which totals 100,000 worm poses approximately. A comparison of the proposed method was made to a classic skeletonisation method to find that 2196 problematic poses had improved by between 22% and 1% on average in the pose predictions of each worm.

Reducing Results Variance in Lifespan Machines: An Analysis of the Influence of Vibrotaxis on Wild-Type Caenorhabditis elegans for the Death Criterion.

Nowadays, various artificial vision-based machines automate the lifespan assays of C. elegans. These automated machines present wider variability in results than manual assays because in the latter worms can be poked one by one to determine whether they are alive or not. Lifespan machines normally use a "dead or alive criterion" based on nematode position or pose changes, without poking worms. However, worms barely move on their last days of life, even though they are still alive. Therefore, a long monitoring period is necessary to observe motility in order to guarantee worms are actually dead, or a stimulus to prompt worm movement is required to reduce the lifespan variability measure. Here, a new automated vibrotaxis-based method for lifespan machines is proposed as a solution to prompt a motion response in all worms cultured on standard Petri plates in order to better distinguish between live and dead individuals. This simple automated method allows the stimulation of all animals through the whole plate at the same time and intensity, increasing the experiment throughput. The experimental results exhibited improved live-worm detection using this method, and most live nematodes (>93%) reacted to the vibration stimulus. This method increased machine sensitivity by decreasing results variance by approximately one half (from ±1 individual error per plate to ±0.6) and error in lifespan curve was reduced as well (from 2.6% to 1.2%).