The application of convolution neural network based cell segmentation during cryopreservation

Mbogba, Momoh Karmah; Haider, Zeeshan; Hossain, Safwan; Huang, Daobin; Memon, Kashan; Panhwar, Fazil; Lei, Zeling; Zhao, Gang

doi:10.1016/j.cryobiol.2018.09.003

Cited by 8 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…cell segmentation [20], mechanical structural damage detection [21], and so on. This paper builds a deep convolutional neural network to classify fruits.…”

Section: Research Articlementioning

confidence: 99%

Recognition system for fruit classification based on 8-layer convolutional neural network

Jiaji¹

2022

EAI Endorsed Transactions on e-Learning

View full text Add to dashboard Cite

INTRODUCTION: Automatic fruit classification is a challenging task. The types, shapes, and colors of fruits are all essential factors affecting classification. OBJECTIVES: This paper aimed to use deep learning methods to improve the overall accuracy of fruit classification, thereby improving the sorting efficiency of the fruit factory. METHODS: In this study, our recognition system is based on an 8-layer convolutional neural network(CNN) combined with the RMSProp optimization algorithm to classify fruits. It is verified through 10 times 10-fold crossover validation. CONCLUSION: Our method achieves an accuracy of 91.63%, which is superior to the other four state-of-the-art methods.

show abstract

“…cell segmentation [20], mechanical structural damage detection [21], and so on. This paper builds a deep convolutional neural network to classify fruits.…”

Section: Research Articlementioning

confidence: 99%

Recognition system for fruit classification based on 8-layer convolutional neural network

Jiaji¹

2022

EAI Endorsed Transactions on e-Learning

View full text Add to dashboard Cite

show abstract

“…To precisely and quickly process the experimental data, a neural network method was adopted to analyze these images 39,49,50 . Prior to using the neural network, datasets for training should be made.…”

Section: Modeling and Simulation Of The Microfluidic Chip Channelsmentioning

confidence: 99%

“…Then, the pixel values of the oocyte and other positions in the image were set to 255 and 0, respectively, to make a gray image as the output label of the network. The theory and procedure of this neural network approach are described in detail elsewhere 39,49 . After processing by the neural network, the obtained data were calculated to obtain the oocyte volume value.…”

Section: Modeling and Simulation Of The Microfluidic Chip Channelsmentioning

confidence: 99%

A microfluidic approach for synchronous and nondestructive study of the permeability of multiple oocytes

et al. 2020

Self Cite

View full text Add to dashboard Cite

Investigation of oocyte membrane permeability plays a crucial role in fertility preservation, reproductive medicine, and reproductive pharmacology. However, the commonly used methods have disadvantages such as high time consumption, low efficiency, and cumbersome data processing. In addition, the developmental potential of oocytes after measurement has not been fully validated in previous studies. Moreover, oocytes can only maintain their best status in vitro within a very limited time. To address these limitations, we developed a novel multichannel microfluidic chip with newly designed micropillars that provide feasible and repeatable oocyte capture. The osmotic responses of three oocytes at different or the same cryoprotectant (CPA) concentrations were measured simultaneously, which greatly improved the measurement efficiency. Importantly, the CPA concentration dependence of mouse oocyte membrane permeability was found. Moreover, a neural network algorithm was employed to improve the efficiency and accuracy of data processing. Furthermore, analysis of fertilization and embryo transfer after perfusion indicated that the microfluidic approach does not damage the developmental potential of oocytes. In brief, we report a new method based on a multichannel microfluidic chip that enables synchronous and nondestructive measurement of the permeability of multiple oocytes.

show abstract

“…Alternatively, computational approaches with traditional algorithms or deep learning approaches have been proposed to detect neuronal membrane and for mitosis detection in breast cancer [ 58 ], mitochondria [ 59 , 60 ], synapses [ 61 ] and proteins [ 62 ]. In particular, the segmentation of the plasma membrane of HeLa cells has been attempted either manually [ 63 , 64 , 65 , 66 ] or at a much lower resolution [ 67 ] (e.g., pixel resolutions around 312 nm, whilst in this work, 10 nm), which constitute a completely different problem. An alternative approach to a segmentation can be a plasma membrane simulation based on simulated lipid particles that distribute around the intensity of an image [ 68 ].…”

Section: Introductionmentioning

confidence: 99%

Volumetric Semantic Instance Segmentation of the Plasma Membrane of HeLa Cells

2021

View full text Add to dashboard Cite

In this work, an unsupervised volumetric semantic instance segmentation of the plasma membrane of HeLa cells as observed with serial block face scanning electron microscopy is described. The resin background of the images was segmented at different slices of a 3D stack of 518 slices with 8192 × 8192 pixels each. The background was used to create a distance map, which helped identify and rank the cells by their size at each slice. The centroids of the cells detected at different slices were linked to identify them as a single cell that spanned a number of slices. A subset of these cells, i.e., the largest ones and those not close to the edges were selected for further processing. The selected cells were then automatically cropped to smaller regions of interest of 2000 × 2000 × 300 voxels that were treated as cell instances. Then, for each of these volumes, the nucleus was segmented, and the cell was separated from any neighbouring cells through a series of traditional image processing steps that followed the plasma membrane. The segmentation process was repeated for all the regions of interest previously selected. For one cell for which the ground truth was available, the algorithm provided excellent results in Accuracy (AC) and the Jaccard similarity Index (JI): nucleus: JI =0.9665, AC =0.9975, cell including nucleus JI =0.8711, AC =0.9655, cell excluding nucleus JI =0.8094, AC =0.9629. A limitation of the algorithm for the plasma membrane segmentation was the presence of background. In samples with tightly packed cells, this may not be available. When tested for these conditions, the segmentation of the nuclear envelope was still possible. All the code and data were released openly through GitHub, Zenodo and EMPIAR.

show abstract

The application of convolution neural network based cell segmentation during cryopreservation

Cited by 8 publications

References 28 publications

Recognition system for fruit classification based on 8-layer convolutional neural network

Recognition system for fruit classification based on 8-layer convolutional neural network

A microfluidic approach for synchronous and nondestructive study of the permeability of multiple oocytes

Volumetric Semantic Instance Segmentation of the Plasma Membrane of HeLa Cells

Contact Info

Product

Resources

About