Name: Automated Analysis of C. elegans Fluorescence Images using SegElegans (Video) | JoVE Journal
Uploaded: 2025-10-10T14:05:00.000+00:00
Duration: 6 min 27 s
Description: Discover SegElegans, a deep learning system for automated C. elegans segmentation in widefield microscopy images. This method reduces analysis time from 245 seconds to under 60 seconds while achieving over 93% accuracy.

ai_agent_IP

ai_agent

maintenance

instantTrialDurationMinutes

isBiopharma

enableNewMyJoveSectionDesign

educationFeatures

seoMetaApi

ai_copilot_institution_blacklist

ai_chat_institution_blacklist

freeAccessWindow

ssoRoleCapture

scheduledMaintenanceBanner

joveLabsFeatures

disable_autoplay_for_bots

extended_trial_duration

5 minutes

Work in the authors&#39; laboratory is funded by the General Secretariat for 
Research and Innovation of the Greek Ministry of Development, the 
European Union - NextGenerationEU (project code: TAEDR-0535850, Acronym: 
BrainPrecision) in the framework of the Action &#34;Flagship Actions in 
Interdisciplinary Scientific Areas with Special Interest in Connection 
to the Productive Fabric,&#34; under the National Recovery and Resilience 
Plan &#34;Greece 2.0&#34;, the European Commission Research Executive Agency 
Excellence Hub &#34;CHAngeing&#34; (GA-101087071) and the Hellenic Foundation 
for Research and Innovation (H.F.R.I.) under the &#34;1st Call for H.F.R.I. 
Research Projects to support Faculty members and Researchers and the 
procurement of high-cost research equipment&#34; (Project Number: 
HFRI-FM17C3- 0869, NeuroMitophagy).

<ol><li>Kaletta, T., Hengartner, M. O. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Finding+function+in+novel+targets%3A+C.+elegans+as+a+model+organism%5BTitle%5D)+AND+%22Nat+Rev+Drug+Discov%22%5BJournal%5D)">Finding function in novel targets: C. elegans as a model organism.</a> Nat Rev Drug Discov. 5 (5), 387-398 (2006).</li>
<li>Markaki, M., Tavernarakis, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Caenorhabditis+elegans+as+a+model+system+for+human+diseases%5BTitle%5D)+AND+%22Curr+Opin+Biotechnol%22%5BJournal%5D)">Caenorhabditis elegans as a model system for human diseases.</a> Curr Opin Biotechnol. 63, 118-125 (2020).</li>
<li>Zuryn, S. C. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((elegans+as+a+model+for+health+and+disease%5BTitle%5D)+AND+%22Semin+Cell+Dev+Biol%22%5BJournal%5D)">elegans as a model for health and disease.</a> Semin Cell Dev Biol. 154 (Pt A), 1-3 (2024).</li>
<li>Corsi, A. K., Wightman, B., Chalfie, M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+transparent+window+into+biology%3A+A+primer+on+Caenorhabditis+elegans%5BTitle%5D)+AND+%22WormBook%22%5BJournal%5D)">A transparent window into biology: A primer on Caenorhabditis elegans.</a> WormBook. , 1-31 (2015).</li>
<li>Kerr, R. A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Imaging+the+activity+of+neurons+and+muscles%5BTitle%5D)+AND+%22WormBook%22%5BJournal%5D)">Imaging the activity of neurons and muscles.</a> WormBook. , 1-13 (2006).</li>
<li>Feinberg, E. H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((GFP+reconstitution+across+synaptic+partners+%28GRASP%29+defines+cell+contacts+and+synapses+in+living+nervous+systems%5BTitle%5D)+AND+%22Neuron%22%5BJournal%5D)">GFP reconstitution across synaptic partners (GRASP) defines cell contacts and synapses in living nervous systems.</a> Neuron. 57 (3), 353-363 (2008).</li>
<li>Hammarlund, M., Jin, Y. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Axon+regeneration+in+C.+elegans%5BTitle%5D)+AND+%22Curr+Opin+Neurobiol%22%5BJournal%5D)">Axon regeneration in C. elegans.</a> Curr Opin Neurobiol. 27, 199-207 (2014).</li>
<li>Daniele, J. R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((UPR%28ER%29+promotes+lipophagy+independent+of+chaperones+to+extend+life+span%5BTitle%5D)+AND+%22Sci+Adv%22%5BJournal%5D)">UPR(ER) promotes lipophagy independent of chaperones to extend life span.</a> Sci Adv. 6 (1), eaaz1441(2020).</li>
<li>Yemini, E., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((NeuroPAL%3A+A+multicolor+atlas+for+whole-brain+neuronal+identification+in+C.+elegans%5BTitle%5D)+AND+%22Cell%22%5BJournal%5D)">NeuroPAL: A multicolor atlas for whole-brain neuronal identification in C. elegans.</a> Cell. 184 (1), 272-288.e11 (2021).</li>
<li>Sinnige, T., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Kinetic+analysis+reveals+that+independent+nucleation+events+determine+the+progression+of+polyglutamine+aggregation+in+C.+elegans%5BTitle%5D)+AND+%22Proc+Natl+Acad+Sci+U+S+A%22%5BJournal%5D)">Kinetic analysis reveals that independent nucleation events determine the progression of polyglutamine aggregation in C. elegans.</a> Proc Natl Acad Sci U S A. 118 (11), e2021888118(2021).</li>
<li>Gkikas, I., Daskalaki, I., Kounakis, K., Tavernarakis, N., Lionaki, E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((MitoSNARE+assembly+and+disassembly+factors+regulate+basal+autophagy+and+aging+in+C.+elegans%5BTitle%5D)+AND+%22Int+J+Mol+Sci%22%5BJournal%5D)">MitoSNARE assembly and disassembly factors regulate basal autophagy and aging in C. elegans.</a> Int J Mol Sci. 24 (4), 4230(2023).</li>
<li>Kutscher, L. M., Shaham, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Forward+and+reverse+mutagenesis+in+C.+elegans%5BTitle%5D)+AND+%22WormBook%22%5BJournal%5D)">Forward and reverse mutagenesis in C. elegans.</a> WormBook. , 1-26 (2014).</li>
<li>Praitis, V., Maduro, M. F. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Transgenesis+in+C.+elegans%5BTitle%5D)+AND+%22Methods+Cell+Biol%22%5BJournal%5D)">Transgenesis in C. elegans.</a> Methods Cell Biol. 106, 161-185 (2011).</li>
<li>Kim, H. M., Colaiacovo, M. P. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((CRISPR-Cas9-guided+genome+engineering+in+Caenorhabditis+elegans%5BTitle%5D)+AND+%22Curr+Protoc+Mol+Biol%22%5BJournal%5D)">CRISPR-Cas9-guided genome engineering in Caenorhabditis elegans.</a> Curr Protoc Mol Biol. 129 (1), e106(2019).</li>
<li>Kamath, R. S., Ahringer, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Genome-wide+RNAi+screening+in+Caenorhabditis+elegans%5BTitle%5D)+AND+%22Methods%22%5BJournal%5D)">Genome-wide RNAi screening in Caenorhabditis elegans.</a> Methods. 30 (4), 313-321 (2003).</li>
<li>Lai, C. H., Chou, C. Y., Ch'ang, L. Y., Liu, C. S., Lin, W. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Identification+of+novel+human+genes+evolutionarily+conserved+in+Caenorhabditis+elegans+by+comparative+proteomics%5BTitle%5D)+AND+%22Genome+Res%22%5BJournal%5D)">Identification of novel human genes evolutionarily conserved in Caenorhabditis elegans by comparative proteomics.</a> Genome Res. 10 (5), 703-713 (2000).</li>
<li>Kuwabara, P. E., O'Neil, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((The+use+of+functional+genomics+in+C.+elegans+for+studying+human+development+and+disease%5BTitle%5D)+AND+%22J+Inherit+Metab+Dis%22%5BJournal%5D)">The use of functional genomics in C. elegans for studying human development and disease.</a> J Inherit Metab Dis. 24 (2), 127-138 (2001).</li>
<li>Ranganathan, R., Sawin, E. R., Trent, C., Horvitz, H. R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Mutations+in+the+Caenorhabditis+elegans+serotonin+reuptake+transporter+MOD-5+reveal+serotonin-dependent+and+-independent+activities+of+fluoxetine%5BTitle%5D)+AND+%22J+Neurosci%22%5BJournal%5D)">Mutations in the Caenorhabditis elegans serotonin reuptake transporter MOD-5 reveal serotonin-dependent and -independent activities of fluoxetine.</a> J Neurosci. 21 (16), 5871-5884 (2001).</li>
<li>Lackner, M. R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Chemical+genetics+identifies+Rab+geranylgeranyl+transferase+as+an+apoptotic+target+of+farnesyl+transferase+inhibitors%5BTitle%5D)+AND+%22Cancer+Cell%22%5BJournal%5D)">Chemical genetics identifies Rab geranylgeranyl transferase as an apoptotic target of farnesyl transferase inhibitors.</a> Cancer Cell. 7 (4), 325-336 (2005).</li>
<li>Yoon, S., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Microfluidics+in+high-throughput+drug+screening%3A+Organ-on-a-chip+and+C.+elegans-based+innovations%5BTitle%5D)+AND+%22Biosensors+%28Basel%29%22%5BJournal%5D)">Microfluidics in high-throughput drug screening: Organ-on-a-chip and C. elegans-based innovations.</a> Biosensors (Basel). 14 (1), 55(2024).</li>
<li>Schindelin, J., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Fiji%3A+An+open-source+platform+for+biological-image+analysis%5BTitle%5D)+AND+%22Nat+Methods%22%5BJournal%5D)">Fiji: An open-source platform for biological-image analysis.</a> Nat Methods. 9 (7), 676-682 (2012).</li>
<li>Schindelin, J., Rueden, C. T., Hiner, M. C., Eliceiri, K. W. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((The+ImageJ+ecosystem%3A+An+open+platform+for+biomedical+image+analysis%5BTitle%5D)+AND+%22Mol+Reprod+Dev%22%5BJournal%5D)">The ImageJ ecosystem: An open platform for biomedical image analysis.</a> Mol Reprod Dev. 82 (7-8), 518-529 (2015).</li>
<li>Rueden, C. T., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((ImageJ2%3A+ImageJ+for+the+next+generation+of+scientific+image+data%5BTitle%5D)+AND+%22BMC+Bioinformatics%22%5BJournal%5D)">ImageJ2: ImageJ for the next generation of scientific image data.</a> BMC Bioinformatics. 18 (1), 529(2017).</li>
<li>Valente, A. J., Maddalena, L. A., Robb, E. L., Moradi, F., Stuart, J. A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+simple+ImageJ+macro+tool+for+analyzing+mitochondrial+network+morphology+in+mammalian+cell+culture%5BTitle%5D)+AND+%22Acta+Histochem%22%5BJournal%5D)">A simple ImageJ macro tool for analyzing mitochondrial network morphology in mammalian cell culture.</a> Acta Histochem. 119 (3), 315-326 (2017).</li>
<li>Ramki, K., Thiruppathi, G., Ramasamy, S. K., Sundararaj, P., Sakthivel, P. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((An+aggregation-induced+emission-based+ratiometric+fluorescent+chemosensor+for+Hg%28II%29+and+its+application+in+Caenorhabditis+elegans+imaging%5BTitle%5D)+AND+%22Methods%22%5BJournal%5D)">An aggregation-induced emission-based ratiometric fluorescent chemosensor for Hg(II) and its application in Caenorhabditis elegans imaging.</a> Methods. 221, 1-11 (2024).</li>
<li>Boulin, T., Etchberger, J. F., Hobert, O. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Reporter+gene+fusions%5BTitle%5D)+AND+%22WormBook%22%5BJournal%5D)">Reporter gene fusions.</a> WormBook. , 1-23 (2006).</li>
<li>Braeckman, B. P., Smolders, A., Back, P., De Henau, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((In+vivo+detection+of+reactive+oxygen+species+and+redox+status+in+Caenorhabditis+elegans%5BTitle%5D)+AND+%22Antioxid+Redox+Signal%22%5BJournal%5D)">In vivo detection of reactive oxygen species and redox status in Caenorhabditis elegans.</a> Antioxid Redox Signal. 25 (10), 577-592 (2016).</li>
<li>He, K., Gkioxari, G., Dollár, P., Girshick, R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Mask+R-CNN%5BTitle%5D)+AND+%22arXiv%22%5BJournal%5D)">Mask R-CNN.</a> arXiv. , (2017).</li>
<li>Ronneberger, O., Fischer, P., Brox, T. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((U-Net%3A+Convolutional+networks+for+biomedical+image+segmentation%5BTitle%5D)+AND+%22arXiv%22%5BJournal%5D)">U-Net: Convolutional networks for biomedical image segmentation.</a> arXiv. , (2015).</li>
<li>Exploring deep learning architectures in NAECON 2018. Proc IEEE NAECON. Alom, M. Z., Yakopcic, C., Taha, T. M., Asari, V. K. IEEE National Aerospace and Electronics Conference, , 228-233 (2018).</li>
<li>Micallef, N., Seychell, D., Bajada, C. J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Exploring+the+U-Net%2B%2B+model+for+automatic+brain+tumor+segmentation%5BTitle%5D)+AND+%22IEEE+Access%22%5BJournal%5D)">Exploring the U-Net++ model for automatic brain tumor segmentation.</a> IEEE Access. 9, 125523-125539 (2021).</li>
<li>Plebani, E., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((High-throughput+segmentation+of+unmyelinated+axons+by+deep+learning%5BTitle%5D)+AND+%22Sci+Rep%22%5BJournal%5D)">High-throughput segmentation of unmyelinated axons by deep learning.</a> Sci Rep. 12 (1), 1198(2022).</li>
<li>Fudickar, S., Nustede, E. J., Dreyer, E., Bornhorst, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Mask+R-CNN+based+C.+elegans+detection+with+a+DIY+microscope%5BTitle%5D)+AND+%22Biosensors+%28Basel%29%22%5BJournal%5D)">Mask R-CNN based C. elegans detection with a DIY microscope.</a> Biosensors (Basel). 11 (8), 257(2021).</li>
<li>Lalit, M., Tomancak, P., Jug, F. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((EmbedSeg%3A+Embedding-based+instance+segmentation+for+biomedical+microscopy+data%5BTitle%5D)+AND+%22Med+Image+Anal%22%5BJournal%5D)">EmbedSeg: Embedding-based instance segmentation for biomedical microscopy data.</a> Med Image Anal. 81, 102523(2022).</li>
<li>Layana Castro, P. E., Garvi, A. G., Sanchez-Salmeron, A. J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Automatic+segmentation+of+Caenorhabditis+elegans+skeletons+in+worm+aggregations+using+improved+U-Net+in+low-resolution+image+sequences%5BTitle%5D)+AND+%22Heliyon%22%5BJournal%5D)">Automatic segmentation of Caenorhabditis elegans skeletons in worm aggregations using improved U-Net in low-resolution image sequences.</a> Heliyon. 9 (4), e14715(2023).</li>
<li>A convolutional neural network model for worm imaging in 2020. Proc IEEE ISBI. Chen, L., et al. IEEE 17th International Symposium on Biomedical Imaging (ISBI), , 508-512 (2020).</li>
<li>Guan, G., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Cell+lineage-resolved+embryonic+morphological+map+reveals+signaling+associated+with+cell+fate+and+size+asymmetry%5BTitle%5D)+AND+%22Nat+Commun%22%5BJournal%5D)">Cell lineage-resolved embryonic morphological map reveals signaling associated with cell fate and size asymmetry.</a> Nat Commun. 16 (1), 3700(2025).</li>
<li>Cao, J., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Establishment+of+a+morphological+atlas+of+the+Caenorhabditis+elegans+embryo+using+deep-learning-based+4D+segmentation%5BTitle%5D)+AND+%22Nat+Commun%22%5BJournal%5D)">Establishment of a morphological atlas of the Caenorhabditis elegans embryo using deep-learning-based 4D segmentation.</a> Nat Commun. 11 (1), 6254(2020).</li>
<li>Zhao, C., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((EmbSAM%3A+Cell+boundary+localization+and+Segment+Anything+Model+for+fast+images+of+developing+embryos%5BTitle%5D)+AND+%22bioRxiv%22%5BJournal%5D)">EmbSAM: Cell boundary localization and Segment Anything Model for fast images of developing embryos.</a> bioRxiv. , (2024).</li>
<li>Castro, P. E. L., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((SegElegans%3A+Instance+segmentation+using+dual+convolutional+recurrent+neural+network+decoder+in+Caenorhabditis+elegans+microscopic+images%5BTitle%5D)+AND+%22Comput+Biol+Med%22%5BJournal%5D)">SegElegans: Instance segmentation using dual convolutional recurrent neural network decoder in Caenorhabditis elegans microscopic images.</a> Comput Biol Med. 190, 110012(2025).</li>
<li>Trebing, K., Stańczyk, T., Mehrkanoon, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((SmaAt-UNet%3A+Precipitation+nowcasting+using+a+small+attention-UNet+architecture%5BTitle%5D)+AND+%22Pattern+Recognit+Lett%22%5BJournal%5D)">SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture.</a> Pattern Recognit Lett. 145, 178-186 (2021).</li>
<li>Woo, S., Park, J., Lee, J. Y., Kweon, I. S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((CBAM%3A+Convolutional+block+attention+module%5BTitle%5D)+AND+%22arXiv%22%5BJournal%5D)">CBAM: Convolutional block attention module.</a> arXiv. , (2018).</li>
<li>Shi, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Convolutional+LSTM+network%3A+A+machine+learning+approach+for+precipitation+nowcasting%5BTitle%5D)+AND+%22arXiv%22%5BJournal%5D)">Convolutional LSTM network: A machine learning approach for precipitation nowcasting.</a> arXiv. , (2015).</li>
<li>Stuhr, N. L., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Rapid+lipid+quantification+in+Caenorhabditis+elegans+by+Oil+Red+O+and+Nile+Red+staining%5BTitle%5D)+AND+%22Bio+Protoc%22%5BJournal%5D)">Rapid lipid quantification in Caenorhabditis elegans by Oil Red O and Nile Red staining.</a> Bio Protoc. 12 (5), e4340(2022).</li>
<li>Kuzmic, M., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((In+situ+visualization+of+carbonylation+and+its+co-localization+with+proteins%2C+lipids%2C+DNA+and+RNA+in+Caenorhabditis+elegans%5BTitle%5D)+AND+%22Free+Radic+Biol+Med%22%5BJournal%5D)">In situ visualization of carbonylation and its co-localization with proteins, lipids, DNA and RNA in Caenorhabditis elegans.</a> Free Radic Biol Med. 101, 465-474 (2016).</li>
<li>Fang, E. F., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((In+vitro+and+in+vivo+detection+of+mitophagy+in+human+cells%2C+C.+elegans%2C+and+mice%5BTitle%5D)+AND+%22J+Vis+Exp%22%5BJournal%5D)">In vitro and in vivo detection of mitophagy in human cells, C. elegans, and mice.</a> J Vis Exp. (129), e56301(2017).</li>
</ol>

The authors have no conflicts of interest to declare.

The methodology presented here should allow users to analyze C. elegans microscopy experiments in a significantly faster timeframe without any loss in accuracy. Since it extracts segmentations from brightfield guide images independently of the actual fluorescence (as discussed in protocol section 1) it can be used with any strain and for any application that requires measuring phenotypes on a per-worm basis. These can include single-channel applications such as the quantification of the formation of abnormal pro...

Caenorhabditis elegans is a eukaryotic model organism with wide use in the fields of cellular and molecular biology1,2,3. It is a small (~1 mm for wild type adults) soil-living nematode worm with a fast life cycle (~three weeks), and a large number of progeny (typically genetically identical to the self-fertilizing hermaphrodite parent). Despite its relative simplicity, the animal is still a complex multicellular organism with defined and distinct tissues and organs, which, thanks to its small size and transparency, can be studied in vivo without any need for fixing or other invasive treatments4. The capacity of the worm for in vivo study through microscopy can be further amplified through the use of fluorescent reporters, that permit the easy distinguishment of individual cells or even the direct visualization of sub-cellular organelles/components such as mitochondria, lipid droplets, or protein aggregates, and of processes such as signal transduction, gene expression, vesicle fusion, autophagy, neuronal and muscle action potentials, etc.5,6,7,8,9,10,11. In addition, the nematode is also highly amenable to genetic manipulation through mutagenesis12, transgenesis via microinjection or microparticle bombardment13, CRISPR editing14, and, most importantly, when it comes to easy and cost-effective genetic screening, RNAi15. This manipulation permits the extensive study of genes and their role in the nematode itself, while simultaneously, thanks to the significant genetic homology that C. elegans exhibits to other model organisms, making foundational discoveries with relevance all the way to humans16,17. Finally, this homology/conservation also makes the worm an ideal initial testing ground for drugs and chemical agents, allowing the elucidation of the mechanisms of drug activity, the identification of potential activity-modifying genetic variations, and the discovery of potential unwanted interactions and off-target effects18,19,20.
All the above-mentioned advantages have rendered C. elegans an attractive model for cellular and molecular biology studies, particularly for scientists interested in the in vivo and often real-time monitoring of processes via microscopy. Such studies typically involve a significant amount of image analysis through special software, with the most widely used option being ImageJ21,22,23. A common characteristic of the analysis through such software is the need for the user/researcher to specify Regions of Interest (ROIs) for analysis through the use of selection tools. Quite frequently, each individual worm in an image will be selected as its own ROI, with the aim to acquire per-worm information about simple morphological features (such as body dimensions) or more &#34;advanced&#34; experimental readouts such as the expression levels of a gene (measured with a fluorescent reporter), the readout of a ratiometric reporter, the number and size of lipid droplets, the formation of protein aggregates, the morphology of individual organelles and their networks etc.5,8,10,24,25,26,27. These per-worm selections are typically made manually, since automatic selection methods that are based on standard image processing algorithms are usually not capable enough to distinguish the shapes and features of the worm, especially in darkfield images where the outlines of the worms are not clearly visible or in brightfield images with significant numbers of animals that touch and overlap. The manual process is, however, slow (20 s to 1 min per worm depending on the precision needed and the experience of the user), laborious, and subject to user bias and error.
An alternative and much more powerful approach for the generation of individual C. elegans ROIs (a task typically referred to as segmentation in the field of computer vision) is to automate it with the help of deep learning/neural network techniques. Convolutional neural networks based primarily on the Mask R-CNN28 and the U-net architectures29 have produced decent results in segmentation tasks on various biological model systems30,31,32 including in C. elegans33,34,35,36,37,38,39, but none have provided a satisfactory solution to the problem of generating full body segmentations that correctly distinguish individual animals (instance segmentation) in high resolution images with large numbers of touching or outright overlapping worms. In order to meet this need, we developed SegElegans, a deep learning model specifically designed and optimized for this task40.
SegElegans is comprised of two major parts (Figure 1). The first part is a two-headed U-net variant convolutional neural network. It is composed of one encoder block and two decoder blocks. The encoder block is based on the SmaAt AT model41 and uses double convolution blocks for each layer feeding into a Convolutional Block Attention Module (CBAM)42. The two decoder blocks are based on the convolutional long short-term memory (LSTM) network43. One decoder is responsible for categorizing each pixel of the images as a part of the main body of a worm, a part of the edge of a worm, a part of the background, or a part of an area where worms overlap (this is typically referred to as semantic segmentation). The other decoder is responsible for drawing a linear &#34;skeleton&#34; along the length of each worm. The second part is a post-processing algorithm that combines the outputs of the two decoders and uses them to generate accurate instance segmentations. It initially identifies the segments of true overlaps by comparing the semantic segmentation output to the skeleton one. Then it outputs the instance segmentation directly for worms without overlaps or by assembling it from segments for overlapping ones40. These segmentations are saved as binary masks as well as ImageJ compatible ROIs.

<table><tbody><tr><td>Computer with internet access (example: Dell Vostro Desktop)</td><td>Several (Dell for example)</td><td>&amp;nbsp;-</td><td>This will allow running SegElegans online via cloud computing as recommended and using image analysis software such as ImageJ.</td></tr><tr><td>CUDA compatible Graphics Processing Unit with at least 6 GB of VRAM (example: MSI Geforce RTX&amp;nbsp; RTX3050 Ventus 2X 6GB) (Optional)</td><td>NVIDIA + several manufacturers (Micro Star International for example)</td><td>https://developer.nvidia.com/cuda-gpus</td><td>This will allow running SegElegans offline on a local machine.&lt;br/&gt; CUDA compatible GPU chipsets can be found here:&lt;br/&gt; https://developer.nvidia.com/cuda-gpus&lt;br/&gt; The VRAM is dependent on the actual implementation of the chipset into a GPU by the manufacturer.&lt;br/&gt; WARNING: You will need an expensive and powerful CUDA card far past the minimum requirements (16+ GB VRAM) to match the performance achieved by the cloud computing version.</td></tr><tr><td>Epifluorescence Microscope (Invitrogen EVOS FL Auto 2)</td><td>ThermoFisher Scientific&amp;nbsp;</td><td>AMAFD2000 for example</td><td>We recommend using a system that can automatically acquire images from both brightfield and one or more fluorescence channels almost simultaneously.</td></tr><tr><td>ImageJ (Optional)</td><td>NIH</td><td>https://imagej.net/software/fiji/downloads</td><td>We recommend the Fiji distribution, available here:&lt;br/&gt; https://imagej.net/software/fiji/downloads</td></tr><tr><td>PC with NVIDIA GPU compatibility (example: Dell Vostro Desktop) (Optional)&amp;nbsp;</td><td>Several (Dell for example)</td><td>&amp;nbsp;-</td><td>This is needed in conjunction with the GPU for running SegElegans offline on a local machine.&lt;br/&gt; A GPU will require Windows compatible hardware with the appropriate PCI slots on the motherboard, room to fit the card and a sufficiently powerful power supply.</td></tr><tr><td>SegElegans</td><td>-</td><td>https://github.com/KonstantinosKounakis/SegElegansOnline/tree/v1.0&amp;nbsp;</td><td>See manuscript for full instructions.&amp;nbsp;</td></tr></tbody></table>

automated analysis of c. elegans fluorescence images using segelegans

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Microscopy, particularly of the fluorescent kind, is a frequently used tool in C. elegans research. The analysis of data from microscopy experiments can, however, be quite tedious and time-consuming. Thus, automation is desirable. We developed SegElegans, a two-headed U-net-based convolutional neural network system that is specifically designed for the automated segmentation of worms, even in images with large numbers of touching or overlapping individuals. The first part of SegElegans consists of one encoder and two decoders. The encoder, based on the SmaAt AT model, applies double convolution layers followed by a Convolutional Block Attention Module (CBAM). Both decoders use convolutional LSTMs: one performs semantic segmentation of worm images (body, edge, background, or overlap), while the other extracts a linear skeleton along each worm. The second part is a post-processing algorithm that combines the outputs of the two decoders and uses them to generate accurate instance segmentations. These segmentations can then be fed to ImageJ or other appropriate image analysis tools. Here we present instructions on how to access and run this system. We provide an online, cloud computing-based implementation as well as two methods to use the SegElegans models offline, on a local machine, should the required hardware be available.

By following this protocol, researchers should be able to extract high-quality worm segmentations, even for the analysis of fluorescence images without visible worm borders. As discussed in section 6 of the protocol, these segmentations can be imported directly to ImageJ and used for the quick measurement of relevant properties such as the intensity of fluorescent reporters (commonly used for expression quantification) or the number, size, and morphology of fluorescently tagged areas (used frequently to study protein agg...

Here we provide instructions on effectively utilizing SegElegans, a deep learning system we developed for the automated segmentation of individual worms in widefield microscopy images, for subsequent use in image analysis software such as ImageJ. We provide ways to use the system both online and offline.

Microscopy, particularly of the fluorescent kind, is a frequently used tool in C. elegans research. The analysis of data from microscopy experiments can, ...

C.elegans research makes routine use of in vivo imaging techniques to monitor processes and answer questions about cell biology. The analysis of the imaging data often requires spending significant time designating regions of interest by making manual selections in the software. Existing options that could automate the process of generating individual worm ROIs are lacking in precision.And often have difficulties distinguishing touching or overlapping worms. To begin, image adult worms using a widefield microscope with a 4x objective lens. If the data is measured in brightfield images, acquire them normally.If the data is measured in dark field fluorescence images, acquire them simultaneously with matching brightfield guide images using the multi-channel acquisition options in the microscope software. Ensure both image sets are saved with identical names, but placed in separate folders. To run the online version of SegElegans, first log into a Google account using a web browser.Enter Google Drive and upload the folder containing brightfield or guide images. Open the GitHub page and click on the SegElegans Body Prediction Interface. ipynb file.Press the open in CoLab button at the top of the opened file. Ensure that CoLab is running a CUDA compatible GPU runtime. Press the play button to execute code block one and grant runtime permissions.Next, execute code block two to load Google Drive into the runtime. Accept all confirmation dialogues, and grant all requested permissions. Then execute code blocks three and four in order, ensuring block three completes fully before running block four.Open the folder tab icon on the left in the CoLab interface, and find the folder with your guide images. Copy the path, then paste it into the test images input form of code block five. Also specify a separate path for the analysis output.Execute code block five. Specify the exact image extension to be analyzed in code block six. Execute code block six, and wait for completion.Now, execute code block seven without changing inputs and less memory issues occur. In a separate tab or window, access Google Drive and open the output folder. Choose one of three options.The first option is to use the ROIs from one all ROIs results, and reject unwanted ROIs in Image J.The second option is to accept the curated good masks from one complete mask without any manual correction, although this will not include the segmentations of overlapping worms. The third and recommended option is to manually adjust the curation. In order to do that, use code block eight.Examine the results of the initial curation from the summary graphs in the zero summary results folder. For each image that needs correction, input the full name of the original input image in the name image change form. And the numbers of the masks to be kept, separated by commas in the index images form.Now, execute code block eight. After completing or skipping the curation correction, execute code block nine to generate the two curated ROIs results folder. The folder includes all the final curated segmentations in the Image J format.To run the pipeline on a new set of images, reset the runtime by navigating to runtime, then choose restart session and repeat the procedure from the beginning. It is also possible to run SegElegans without cloud computing on a local machine using Jupyter or a Python script. To import the segmentations, open one of the actual data images in Image J.Open the corresponding zip file containing the ROIs of that image to load the selections into the Image J ROI manager.If they are from the two curated ROIs results output, proceed with analysis using the desired methods, preferably automated with macros. If the ROIs originate from the one all ROIs results output, remove unwanted segmentations from the ROI manager. Select them and press the delete button on the ROI manager window.Then proceed with analysis normally. If software other than Image J is required, import the segmentations as binary masks instead. In the validation and performance testing experiments, SegElegans significantly reduced the average time required per image compared to manual segmentation.Cutting it from approximately 245 seconds to under 60 seconds. SegElegans achieved a segmentation intersection over union score above 93%outperforming all alternative models listed at the time of publication. SegElegans is a deep learning system that utilizes a special architecture that permits the accurate segmentation of individual worms, even in crowded images.SegElegans is important and versatile tool that can help expedite the analysis of microscopic data without sacrificing accuracy.

automated-analysis-of-c-elegans-fluorescence-images-using-segelegans

Research

JoVE Journal

Biology

We report the development of a system for automated imaging and analysis of zebrafish transgenic embryos in multiwell plates. This demonstrates the ability to measure dose dependent effects of a small molecule, BCI, on Fibroblast Growth Factor reporter gene expression and provide technology for establishing high-throughput zebrafish chemical screens.

Development of automated imaging and analysis for zebrafish chemical screens. 

The C. elegans embryo is a powerful system for studying cell biology and development.  We present a protocol for live imaging of C. elegans embryos utilizing DIC optics or fluorescence using readily available epifluorescent microscopes and open-source software.

Imaging C. elegans Embryos using an Epifluorescent Microscope and Open Source Software

The abundance of neurotransmitter receptors clustered at synapses strongly influences synaptic strength. This method quantifies fluorescently-labeled neurotransmitter receptors in three dimensions with single-synapse resolution in C. elegans, allowing hundreds of synapses to be rapidly characterized within a single sample without distortions introduced by z-plane projection.

Automated Quantification of Synaptic Fluorescence in C. elegans

We have developed a video-rate tracking microscope system that can record and quantify C. elegans behavior at high resolution and high speeds. We have also developed computational methods to reduce the dimensionality of the worm images to a fundamental set of measurements that completely describe the shape of the worm.

C. elegans Tracking and Behavioral Measurement

This video describes the use of video and tracking software to record worm movement in an arena.  The example protocol measures the effect of ethanol exposure on worm locomotion.

C. elegans Movement Tracking: A Method to Assess Locomotion in Worms

An efficient and simple methodology for computer-based analysis of nematode swimming behavior in liquid is described. The method requires little to no investment for C. elegans laboratories. The hardware used is standard, and the computer software for the behavioral analysis (CeleST) is an open source one.

Automated Analysis of C. elegans Swim Behavior Using CeleST Software

Here, we present a framework to relate broad-range dietary restriction to gene expression and lifespan. We describe protocols for broad-range dietary restriction and for quantitative imaging of gene expression under this paradigm. We further outline computational analyses to reveal underlying information processing features of the genetic circuits involved in food-sensing.

Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans

Here, we present a combinatorial approach using high-resolution microscopy, computational tools, and single-cell labeling in living C. elegans embryos to understand single cell dynamics during neurodevelopment.

Isotropic Light-Sheet Microscopy and Automated Cell Lineage Analyses to Catalogue Caenorhabditis elegans Embryogenesis with Subcellular Resolution

This study outlines quantitative measurements of synaptic size and localization, muscle morphology, and mitochondrial shape in C. elegans using freely available image processing tools. This approach allows future studies in C. elegans to quantitatively compare the extent of tissue and organelle structural changes as a result of genetic mutations.

Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans

This work describes a semi-high-throughput protocol that allows simultaneous 3D time-lapse imaging of embryogenesis in 80–100 C. elegans embryos in a single overnight run. Additionally, image processing and visualization tools are included to streamline data analysis. The combination of these methods with custom reporter strains enables detailed monitoring of embryogenesis.

A Semi-high-throughput Imaging Method and Data Visualization Toolkit to Analyze C. elegans Embryonic Development

Worm-align/Worm_CP is a simple FIJI/CellProfiler workflow that can be used to straighten and align Caenorhabditis elegans samples and to score whole-worm image-based assays without the need for prior training steps. We have applied Worm-align/Worm_CP to the quantification of heat-shock induced expression in live animals or lipid droplets in fixed samples.

Worm-align and Worm_CP, Two Open-Source Pipelines for Straightening and Quantification of Fluorescence Image Data Obtained from Caenorhabditis elegans

Discover SegElegans, a deep learning system for automated C. elegans segmentation in widefield microscopy images. This method reduces analysis time from 245 seconds to under 60 seconds while achieving over 93% accuracy.

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Explore More Videos