Usiigaci: Instance-aware cell tracking in stain-free phase contrast microscopy enabled by machine learning

Tsai, Hsieh-Fu; Gajda, Joanna; Sloan, Tyler F.W.; Rares, A.; Shen, Amy Q.

doi:10.1016/j.softx.2019.02.007

Cited by 117 publications

(63 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The adhesion and electrotaxis of T98G and U-251MG glioblastoma cell lines on various ECMs are tested in a double-layer hybrid multiple electric field chip (HMEFC) based on the hybrid PMMA/PDMS design approach 17 (Supplementary TABLE. S.1). The migration directedness, speed, and morphology of glioblastoma cells (see details in section IV.D) are quantitatively analyzed by a machine learning-based single cell segmentation and tracking software from stain-free phase contrast microscopy 30 While standard poly(D-lysine) (PDL) and various combinations of poly(L-ornithine) (PLO) and laminin have been used for glioblastoma electrotaxis 16,39 , the adhesion and electrotaxis of T98G and U-251MG are not always are not always consistent and reproducible as shown in Supplementary FIG. S.2 and FIG.…”

Section: B Glioblastoma Electrotaxis Requires Optimal Laminin-contaimentioning

confidence: 99%

“…Quantitative single cell migration analysis is carried out by extracting cell migration metrics such as the directedness, orientation, or speed using a robust machine learning-powered cell segmentation/tracking/analysis software with stain-free phase contrast microscopy 30 . Using the hybrid microfluidic platform, the role of voltage-gated calcium channels in calcium signaling pathways of glioblastoma electrotaxis are investigated.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Voltage-gated ion channels mediate the electrotaxis of glioblastoma cells in a hybrid PMMA/PDMS microdevice

Tsai

IJspeert

Shen

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Transformed astrocytes in the most aggressive form cause glioblastoma, the most common cancer in central nervous system with high mortality. The physiological electric field by neuronal local field potentials and tissue polarity may guide the infiltration of glioblastoma cells through the electrotaxis process. However, microenvironments with multiplex gradients are difficult to create. In this work, we have developed a hybrid microfluidic platform to study glioblastoma electrotaxis in controlled microenvironments with high throughput quantitative analysis by a machine learning-powered single cell tracking software. By equalizing the hydrostatic pressure difference between inlets and outlets of the microchannel, uniform single cells can be seeded reliably inside the microdevice. The electrotaxis of two glioblastoma models, T98G and U-251MG, require optimal laminin-containing extracellular matrix and exhibits opposite directional and electro-alignment tendencies. Calcium signaling is a key contributor in glioblastoma pathophysiology but its role in glioblastoma electrotaxis is still an open question. Anodal T98G electrotaxis and cathodal U-251MG electrotaxis require the presence of extracellular calcium cations. U-251MG electrotaxis is dependent on the P/Q-type voltage-gated calcium channel (VGCC) and T98G is dependent on the R-type VGCC. U-251MG and T98G electrotaxis are also mediated by A-type (rapidly inactivating) voltage-gated potassium channels and acidsensing sodium channels. The involvement of multiple ion channels suggests that the glioblastoma electrotaxis is complex and patient-specific ion channel expression can be critical to develop personalized therapeutics to fight against cancer metastasis. The hybrid microfluidic design and machine learning-powered single cell analysis provide a simple and flexible platform for quantitative investigation of complicated biological systems.

show abstract

Section: B Glioblastoma Electrotaxis Requires Optimal Laminin-contaimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Voltage-gated ion channels mediate the electrotaxis of glioblastoma cells in a hybrid PMMA/PDMS microdevice

Tsai

IJspeert

Shen

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, most existing solutions and benchmark datasets for multi-object tracking as well as for posture and activity recognition, are dedicated to human behavior and crowds [22][23][24][25] . In biological image data CNNs have been broadly exploited for cell or particle segmentation [26][27][28][29] . Versatile, supervised CNN-based tools have also been proposed for animal posture quantification 17,18 and have been successfully applied to the study of insect behavior [30][31][32] .…”

Section: Introductionmentioning

confidence: 99%

Markerless tracking of an entire insect colony

Bożek

Hebert

Portugal

et al. 2020

Preprint

View full text Add to dashboard Cite

We present a comprehensive, computational method for tracking an entire colony of the honey bee Apis mellifera using high-resolution video on a natural honeycomb background. We adapt a convolutional neural network (CNN) segmentation architecture to automatically identify bee and brood cell positions, body orientations and within-cell states. We achieve high accuracy (~10% body width error in position, ~10° error in orientation, and true positive rate > 90%) and demonstrate months-long monitoring of sociometric colony fluctuations. We combine extracted positions with rich visual features of organismcentered images to track individuals over time and through challenging occluding events, recovering ~79% of bee trajectories from five observation hives over a span of 5 minutes. The resulting trajectories reveal important behaviors, including fast motion, comb-cell activity, and waggle dances. Our results provide new opportunities for the quantitative study of collective bee behavior and for advancing tracking techniques of crowded systems.

show abstract

“…While deep learning has been successfully applied to single-cell segmentation, a robust deep learning-based cell tracker for mammalian cells has been elusive. Integration of deep learning into live-cell imaging analysis pipelines achieve performance boosts by combining the improved segmentation accuracy of deep learning with conventional object tracking algorithms 13,[25][26][27] . These algorithms include linear programming 28 and the Viterbi algorithm 29 ; both have seen extensive use on live-cell imaging data.…”

Section: Introductionmentioning

confidence: 99%

Caliban: Accurate cell tracking and lineage construction in live-cell imaging experiments with deep learning

Moen

Borba

Miller

et al. 2019

Preprint

View full text Add to dashboard Cite

Live-cell imaging experiments have opened an exciting window into the behavior of living systems. While these experiments can produce rich data, the computational analysis of these datasets is challenging. Single-cell analysis requires that cells be accurately identified in each image and subsequently tracked over time. Increasingly, deep learning is being used to interpret microscopy image with single cell resolution. In this work, we apply deep learning to the problem of tracking single cells in live-cell imaging data. Using crowdsourcing and a human-in-the-loop approach to data annotation, we constructed a dataset of over 11,000 trajectories of cell nuclei that includes lineage information. Using this dataset, we successfully trained a deep learning model to perform cell tracking within a linear programming framework. Benchmarking tests demonstrate that our method achieves state-of-the-art performance on the task of cell tracking with respect to multiple accuracy metrics. Further, we show that our deep learning-based method generalizes to perform cell tracking for both fluorescent and brightfield images of the cell cytoplasm, despite having never been trained on those data types. This enables analysis of live-cell imaging data collected across imaging modalities. A persistent cloud deployment of our cell tracker is available at http://www.deepcell.org.

show abstract

Usiigaci: Instance-aware cell tracking in stain-free phase contrast microscopy enabled by machine learning

Cited by 117 publications

References 33 publications

Voltage-gated ion channels mediate the electrotaxis of glioblastoma cells in a hybrid PMMA/PDMS microdevice

Voltage-gated ion channels mediate the electrotaxis of glioblastoma cells in a hybrid PMMA/PDMS microdevice

Markerless tracking of an entire insect colony

Caliban: Accurate cell tracking and lineage construction in live-cell imaging experiments with deep learning

Contact Info

Product

Resources

About