Classification of red blood cell shapes in flow using outlier tolerant machine learning

Kihm, Alexander; Kaestner, Lars; Wagner, Christian; Quint, Stephan

doi:10.1371/journal.pcbi.1006278

Cited by 75 publications

(76 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Convolutional Neural Networks (CNN) have been applied to microscopy images for both phenotype classification 21,22 and image segmentation 23,24 . CNNs trained on these tasks have proven to…”

Section: An Accurate and High Throughput Methods Of Cell Volume Quantimentioning

confidence: 99%

CTRL – a label-free artificial intelligence method for dynamic measurement of single-cell volume

Yao

Rochman

Sun

2020

Journal of Cell Science

View full text Add to dashboard Cite

Measuring the physical size of the cell is valuable in understanding cell growth control. Current singlecell volume measurement methods for mammalian cells are labor-intensive, inflexible, and can cause cell damage. We introduce CTRL: Cell Topography Reconstruction Learner, a label-free technique incorporating the Deep Learning algorithm and the Fluorescence Exclusion method for reconstructing cell topography and estimating mammalian cell volume from DIC microscopy images alone. The method achieves quantitative accuracy, requires minimal sample preparation, and applies to a wide range of biological and experimental conditions. The method can be used to track single-cell volume dynamics over arbitrarily long time periods. Using this method, we observe that bigger newborn cells grow larger (sizer) for HT1080 fibrosarcoma cells and there is a noticeable reduction in cell size fluctuations at 25% completion of the cell cycle in HT1080 fibrosarcoma cells.

show abstract

Section: An Accurate and High Throughput Methods Of Cell Volume Quantimentioning

confidence: 99%

CTRL – a label-free artificial intelligence method for dynamic measurement of single-cell volume

Yao

Rochman

Sun

2020

Journal of Cell Science

View full text Add to dashboard Cite

show abstract

“…21 CNNs are supervised machine learning methods whose utility in different areas of scientific inquiry has grown in popularity at an unprecedented rate. 21,[29][30][31] CNNs are composed of a series of matrix operations involving mathematical filters, which are sequentially used as arranged in a so-called CNN architecture. Feature images, which are generated from input images, emphasize elements in the latter that matches the trainable filters used to convolve with the input images.…”

Section: Introductionmentioning

confidence: 99%

Automatic Identification of the Stress Sources of Protein Aggregates Using Flow Imaging Microscopy Images

Gambe-Gilbuena

Shibano

Krayukhina³

et al. 2020

Journal of Pharmaceutical Sciences

View full text Add to dashboard Cite

A novel approach to identify 5 types of simulated stresses that induce protein aggregation in prefilled syringeetype biopharmaceuticals was developed. Principal components analyses of texture metrics extracted from flow imaging microscopy images were used to define subgroups of particles. Supervised machine learning methods, including convolutional neural networks, were used to train classifiers to identify subgroup membership of constituent particles to generate distribution profiles. The applicability of the stress-specific signatures for distinguishing stress source types was verified. The high classification efficiencies (100%) precipitated the collection of data from more than 20 independent experiments to train support vector machines, k-nearest neighbors, and ensemble classifiers. The performances of the trained classifiers were validated. High classification efficiencies for friability (80%-100%) and heating at 90 C (85%-100%) are indicative of high reliability of these methods for stress-stability assays while extreme variations in freeze-thawing (2%-100%) and heating at 60 C (2.25%-98.25%) indicate the unpredictability of particle composition profiles for these forced degradation conditions. We also developed subvisible particle classifiers using convolutional neural network to automatically identify silicone oil droplets, air bubbles, and protein aggregates. The developed classifiers will contribute to mitigating aggregation in biopharmaceuticals via the identification of stress sources.

show abstract

“…Blood is the most delocalized liquid in the body, delivering oxygenated blood from the respiratory system to the other parts of the body and transporting carbon dioxide back [1]. It also helps in the excretion of wastes through the kidney and carries nutrients from the digestive system to the other tissues of the body [2].…”

Section: Introductionmentioning

confidence: 99%

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Shahzad

Umar

Khan

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Previous works on segmentation of SEM (scanning electron microscope) blood cell image ignore the semantic segmentation approach of whole-slide blood cell segmentation. In the proposed work, we address the problem of whole-slide blood cell segmentation using the semantic segmentation approach. We design a novel convolutional encoder-decoder framework along with VGG-16 as the pixel-level feature extraction model. e proposed framework comprises 3 main steps: First, all the original images along with manually generated ground truth masks of each blood cell type are passed through the preprocessing stage. In the preprocessing stage, pixel-level labeling, RGB to grayscale conversion of masked image and pixel fusing, and unity mask generation are performed. After that, VGG16 is loaded into the system, which acts as a pretrained pixel-level feature extraction model. In the third step, the training process is initiated on the proposed model. We have evaluated our network performance on three evaluation metrics. We obtained outstanding results with respect to classwise, as well as global and mean accuracies. Our system achieved classwise accuracies of 97.45%, 93.34%, and 85.11% for RBCs, WBCs, and platelets, respectively, while global and mean accuracies remain 97.18% and 91.96%, respectively.

show abstract

Classification of red blood cell shapes in flow using outlier tolerant machine learning

Cited by 75 publications

References 32 publications

CTRL – a label-free artificial intelligence method for dynamic measurement of single-cell volume

CTRL – a label-free artificial intelligence method for dynamic measurement of single-cell volume

Automatic Identification of the Stress Sources of Protein Aggregates Using Flow Imaging Microscopy Images

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Contact Info

Product

Resources

About