scholarly journals DetecDiv, a deep-learning platform for automated cell division tracking and replicative lifespan analysis

2021 ◽  
Author(s):  
Théo Aspert ◽  
Didier Hentsch ◽  
Gilles Charvin
Keyword(s):  
Deep Learning ◽  
Cell Division ◽  
Single Cell ◽  
High Throughput ◽  
Semantic Segmentation ◽  
Temporal Information ◽  
Biological Processes ◽  
Replicative Lifespan ◽  
Learning Platform ◽  
Microscopy Images

AbstractAutomating the extraction of meaningful temporal information from sequences of microscopy images represents a major challenge to characterize dynamical biological processes. Here, we have developed DetecDiv, a microfluidic-based image acquisition platform combined with deep learning-based software for high-throughput single-cell division tracking. DetecDiv can reconstruct cellular replicative lifespans with an outstanding accuracy and provides comprehensive temporal cellular metrics using timeseries classification and image semantic segmentation.

scholarly journals DeepSea: An efficient deep learning model for automated cell segmentation and tracking

2021 ◽  
Author(s):  
Abolfazl Zargari ◽  
Gerrald A. Lodewijk ◽  
Celine W. Neudorf ◽  
Kimiasadat Araghbidikashani ◽  
Najmeh Mashhadi ◽  
...  
Keyword(s):  
Stem Cells ◽  
Deep Learning ◽  
Cell Division ◽  
Embryonic Stem Cells ◽  
Single Cell ◽  
Cell Size ◽  
Phase Contrast ◽  
Embryonic Stem ◽  
Microscopy Images ◽  
Segmentation And Tracking

AbstractTime-lapse microscopy can directly capture the dynamics and heterogeneity of cellular processes at the single-cell level. Successful application of single-cell live microscopy requires automated segmentation and tracking of hundreds of individual cells over several time points. Recently, deep learning models have ushered in a new era in quantitative analysis of microscopy images. This work presents a versatile and trainable deep-learning-based software, termed DeepSea, that allows for both segmentation and tracking of single cells and their nuclei in sequences of phase-contrast live microscopy images. We show that DeepSea can quantify several cell biological features of mouse embryonic stem cells, such as cell division cycle, mitosis, cell morphology, and cell size, with high precision using phase-contrast images. Using DeepSea, we were able to show that despite their ultrafast cell division cycle, mouse embryonic stem cells exhibit cell size control in the G1 phase of the cell cycle.

scholarly journals MICRA-Net: MICRoscopy Analysis Neural Network to solve detection, classification, and segmentation from a single simple auxiliary task

2021 ◽  
Author(s):  
Anthony Bilodeau ◽  
Constantin V.L. Delmas ◽  
Martin Parent ◽  
Paul De Koninck ◽  
Audrey Durand ◽  
...  
Keyword(s):  
Neural Network ◽  
Quantitative Analysis ◽  
High Throughput ◽  
Semantic Segmentation ◽  
Feature Maps ◽  
Expert Annotation ◽  
Microscopy Analysis ◽  
Weakly Supervised ◽  
Segmentation Task ◽  
Microscopy Images

High throughput quantitative analysis of microscopy images presents a challenge due to the complexity of the image content and the difficulty to retrieve precisely annotated datasets. In this paper we introduce a weakly-supervised MICRoscopy Analysis neural network (MICRA-Net) that can be trained on a simple main classification task using image-level annotations to solve multiple the more complex auxiliary semantic segmentation task and other associated tasks such as detection or enumeration. MICRA-Net relies on the latent information embedded within a trained model to achieve performances similar to state-of-the-art fully-supervised learning. This learnt information is extracted from the network using gradient class activation maps, which are combined to generate detailed feature maps of the biological structures of interest. We demonstrate how MICRA-Net significantly alleviates the Expert annotation process on various microscopy datasets and can be used for high-throughput quantitative analysis of microscopy images.

scholarly journals Biological network inference from single-cell multi-omics data using heterogeneous graph transformer

2021 ◽  
Author(s):  
Anjun Ma ◽  
Xiaoying Wang ◽  
Cankun Wang ◽  
Jingxian Li ◽  
Tong Xiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Single Cell ◽  
Gene Networks ◽  
Network Inference ◽  
Lung Tumor ◽  
Superior Performance ◽  
Omics Data ◽  
Learning Platform ◽  
Cell Clustering ◽  
Cell Cell

We present DeepMAPS, a deep learning platform for cell-type-specific biological gene network inference from single-cell multi-omics (scMulti-omics). DeepMAPS includes both cells and genes in a heterogeneous graph to infer cell-cell, cell-gene, and gene-gene relations simultaneously. The graph attention neural network considers a cell and a gene with both local and global information, making DeepMAPS more robust to data noises. We benchmarked DeepMAPS on 18 datasets for cell clustering and network inference, and the results showed that our method outperforms various existing tools. We further applied DeepMAPS on a case study of lung tumor leukocyte CITE-seq data and observed superior performance in cell clustering, and predicted biologically meaningful cell-cell communication pathways based on the inferred gene networks. To improve the feasibility and ensure the reproducibility of analyzing scMulti-omics data, we deployed a webserver with multi-functions and various visualizations. Overall, we valued DeepMAPS as a novel platform of the state-of-the-art deep learning model in the single-cell study and can promote the use of scMulti-omics data in the community.

scholarly journals Test-time augmentation for deep learning-based cell segmentation on microscopy images

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Nikita Moshkov ◽  
Botond Mathe ◽  
Attila Kertesz-Farkas ◽  
Reka Hollandi ◽  
Peter Horvath
Keyword(s):  
Deep Learning ◽  
Prediction Accuracy ◽  
Data Science ◽  
Single Cell Analysis ◽  
Prediction Method ◽  
Semantic Segmentation ◽  
Cell Segmentation ◽  
Test Time ◽  
Scoring Method ◽  
Microscopy Images

AbstractRecent advancements in deep learning have revolutionized the way microscopy images of cells are processed. Deep learning network architectures have a large number of parameters, thus, in order to reach high accuracy, they require a massive amount of annotated data. A common way of improving accuracy builds on the artificial increase of the training set by using different augmentation techniques. A less common way relies on test-time augmentation (TTA) which yields transformed versions of the image for prediction and the results are merged. In this paper we describe how we have incorporated the test-time argumentation prediction method into two major segmentation approaches utilized in the single-cell analysis of microscopy images. These approaches are semantic segmentation based on the U-Net, and instance segmentation based on the Mask R-CNN models. Our findings show that even if only simple test-time augmentations (such as rotation or flipping and proper merging methods) are applied, TTA can significantly improve prediction accuracy. We have utilized images of tissue and cell cultures from the Data Science Bowl (DSB) 2018 nuclei segmentation competition and other sources. Additionally, boosting the highest-scoring method of the DSB with TTA, we could further improve prediction accuracy, and our method has reached an ever-best score at the DSB.

scholarly journals HD Spot: Interpretable Deep Learning Classification of Single Cell Transcript Data

2019 ◽  
Author(s):  
Eric Prince ◽  
Todd C. Hankinson
Keyword(s):  
Deep Learning ◽  
Single Cell ◽  
High Throughput ◽  
Ground Truth ◽  
Sequencing Technologies ◽  
Bioinformatic Tool ◽  
Complex Relationships ◽  
Insight Into ◽  
Generation Sequencing

ABSTRACTHigh throughput data is commonplace in biomedical research as seen with technologies such as single-cell RNA sequencing (scRNA-seq) and other Next Generation Sequencing technologies. As these techniques continue to be increasingly utilized it is critical to have analysis tools that can identify meaningful complex relationships between variables (i.e., in the case of scRNA-seq: genes) in a way such that human bias is absent. Moreover, it is equally paramount that both linear and non-linear (i.e., one-to-many) variable relationships be considered when contrasting datasets. HD Spot is a deep learning-based framework that generates an optimal interpretable classifier a given high-throughput dataset using a simple genetic algorithm as well as an autoencoder to classifier transfer learning approach. Using four unique publicly available scRNA-seq datasets with published ground truth, we demonstrate the robustness of HD Spot and the ability to identify ontologically accurate gene lists for a given data subset. HD Spot serves as a bioinformatic tool to allow novice and advanced analysts to gain complex insight into their respective datasets enabling novel hypotheses development.

scholarly journals CoTECH for single-cell joint detection of transcriptome and chromatin occupancy

2021 ◽  
Author(s):  
Yingjie Luo ◽  
Haiqing Xiong ◽  
Qianhao Wang ◽  
Xianhong Yu ◽  
Aibin He
Keyword(s):  
Gene Regulation ◽  
Single Cell ◽  
High Throughput ◽  
Single Cells ◽  
Cellular Heterogeneity ◽  
Joint Detection ◽  
Biological Processes ◽  
Experimental Procedure ◽  
Higher Dimensional

Abstract Here we present CoTECH, a high-throughput co-aasay that measures chromatin occupancy and transcriptome in single cells. The CoTECH method adopts a combinatorial indexing strategy to enrich chromatin fragments of interest as reported in CoBATCH in combination with a modified Smart-seq2 procedure to simultaneously capture the 3’ mRNA profiles in the same single cells. The whole experimental procedure can be handled within three days.The CoTECH acquires data quality of 1000-9000 unique mapped reads (DNA partition) and 1500-4000 expressed genes (RNA partition) per cell. Experimentally linking chromatin occupancy to transcriptional outputs and inferred molecular association between multimodal omics datasets made possible by CoTECH enables reconstructions of higher dimensional epigenomic landscape, providing new insights into epigenome-centric gene regulation and cellular heterogeneity in many biological processes. This step-by-step protocol is related to the publication “Single-cell joint detection of chromatin occupancy and transcriptome enables higher-dimensional epigenomic reconstructions” in Nature Methods.

Deep learning semantic segmentation of opaque and non-opaque minerals from epoxy resin in reflected light microscopy images

2021 ◽  
Vol 170 ◽  
pp. 107007
Author(s):  
Michel Pedro Filippo ◽  
Otávio da Fonseca Martins Gomes ◽  
Gilson Alexandre Ostwald Pedro da Costa ◽  
Guilherme Lucio Abelha Mota
Keyword(s):  
Deep Learning ◽  
Light Microscopy ◽  
Epoxy Resin ◽  
Semantic Segmentation ◽  
Reflected Light ◽  
Opaque Minerals ◽  
Microscopy Images

scholarly journals A Deep Learning Semantic Segmentation-Based Approach for Field-Level Sorghum Panicle Counting

2019 ◽  
Vol 11 (24) ◽  
pp. 2939 ◽  
Author(s):  
Lonesome Malambo ◽  
Sorin Popescu ◽  
Nian-Wei Ku ◽  
William Rooney ◽  
Tan Zhou ◽  
...  
Keyword(s):  
Image Analysis ◽  
Deep Learning ◽  
High Throughput ◽  
Precision Agriculture ◽  
Crop Improvement ◽  
Image Data ◽  
Semantic Segmentation ◽  
Detection Accuracy ◽  
Phenotypic Data ◽  
Field Level

Small unmanned aerial systems (UAS) have emerged as high-throughput platforms for the collection of high-resolution image data over large crop fields to support precision agriculture and plant breeding research. At the same time, the improved efficiency in image capture is leading to massive datasets, which pose analysis challenges in providing needed phenotypic data. To complement these high-throughput platforms, there is an increasing need in crop improvement to develop robust image analysis methods to analyze large amount of image data. Analysis approaches based on deep learning models are currently the most promising and show unparalleled performance in analyzing large image datasets. This study developed and applied an image analysis approach based on a SegNet deep learning semantic segmentation model to estimate sorghum panicles counts, which are critical phenotypic data in sorghum crop improvement, from UAS images over selected sorghum experimental plots. The SegNet model was trained to semantically segment UAS images into sorghum panicles, foliage and the exposed ground using 462, 250 × 250 labeled images, which was then applied to field orthomosaic to generate a field-level semantic segmentation. Individual panicle locations were obtained after post-processing the segmentation output to remove small objects and split merged panicles. A comparison between model panicle count estimates and manually digitized panicle locations in 60 randomly selected plots showed an overall detection accuracy of 94%. A per-plot panicle count comparison also showed high agreement between estimated and reference panicle counts (Spearman correlation ρ = 0.88, mean bias = 0.65). Misclassifications of panicles during the semantic segmentation step and mosaicking errors in the field orthomosaic contributed mainly to panicle detection errors. Overall, the approach based on deep learning semantic segmentation showed good promise and with a larger labeled dataset and extensive hyper-parameter tuning, should provide even more robust and effective characterization of sorghum panicle counts.

Sign in / Sign up

Export Citation Format

Share Document