Two‐Dimensional Light Scattering Anisotropy Cytometry for Label‐Free Classification of Ovarian Cancer Cells via Machine Learning

Su, Xuantao; Yuan, Tao; Wang, Zhiwen; Song, Kun; Li, Rongrong; Yuan, Cunzhong; Kong, Beihua

doi:10.1002/cyto.a.23865

Cited by 26 publications

(20 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the accuracy of this method was more than 90%. Su et al (2020) suggested generating lighting patterns in the cells by single-mode fiber cytometry. Iliyasu and Fatichah (2017) proposed a new method (Qfuzzy) to extract and classify cervical smear cells’ characteristics based on particle swarm optimization and k-nearest neighbors.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED: BCNet: A Novel Network for Blood Cell Classification

Zhu

Wang

et al. 2022

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Aims: Most blood diseases, such as chronic anemia, leukemia (commonly known as blood cancer), and hematopoietic dysfunction, are caused by environmental pollution, substandard decoration materials, radiation exposure, and long-term use certain drugs. Thus, it is imperative to classify the blood cell images. Most cell classification is based on the manual feature, machine learning classifier or the deep convolution network neural model. However, manual feature extraction is a very tedious process, and the results are usually unsatisfactory. On the other hand, the deep convolution neural network is usually composed of massive layers, and each layer has many parameters. Therefore, each deep convolution neural network needs a lot of time to get the results. Another problem is that medical data sets are relatively small, which may lead to overfitting problems.Methods: To address these problems, we propose seven models for the automatic classification of blood cells: BCARENet, BCR5RENet, BCMV2RENet, BCRRNet, BCRENet, BCRSNet, and BCNet. The BCNet model is the best model among the seven proposed models. The backbone model in our method is selected as the ResNet-18, which is pre-trained on the ImageNet set. To improve the performance of the proposed model, we replace the last four layers of the trained transferred ResNet-18 model with the three randomized neural networks (RNNs), which are RVFL, ELM, and SNN. The final outputs of our BCNet are generated by the ensemble of the predictions from the three randomized neural networks by the majority voting. We use four multi-classification indexes for the evaluation of our model.Results: The accuracy, average precision, average F1-score, and average recall are 96.78, 97.07, 96.78, and 96.77%, respectively.Conclusion: We offer the comparison of our model with state-of-the-art methods. The results of the proposed BCNet model are much better than other state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED: BCNet: A Novel Network for Blood Cell Classification

Zhu

Wang

et al. 2022

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

show abstract

“…Later Su et al. [ 256 ] classified cancer cells with the use of the SVM and features obtained from the histograms of oriented gradients applied to a 2D LSP. Recently Ding [ 257 ] demonstrated a potential of convolutional NNs to classify particles shape by a 2D LSP with accuracy above 97%.…”

Section: Characterization Methods and Inverse Problemsmentioning

confidence: 99%

Single‐Particle Characterization by Elastic Light Scattering

Romanov

Yurkin

2021

Laser & Photonics Reviews

View full text Add to dashboard Cite

The field of light‐scattering characterization of single particles has seen a rapid growth over the last 30 years largely due to the progress in measurement and simulation capabilities. In particular, several methods have been developed to reliably characterize various particles, described by a model with several characteristics, with geometric resolution significantly better than the diffraction limit. However, their development has been largely fragmentary, limited to specific experimental set‐ups. To fill this gap, these lines of development are reviewed within a unified framework. While focusing on characterization algorithms themselves, the experimental aspects related to the isolation and measurement of single particles are also discussed. The existing characterization methods are divided into three classes. The widest class is that of model‐driven methods based on solving parametric inverse light‐scattering problems, using a direct inversion of a low‐dimensional mapping, a nonlinear regression, or neural networks. Other classes include model‐free reconstruction methods and data‐driven classification methods. This review is designed to be extensive in including all relevant literature, but the discussion of semi‐quantitative imaging methods, such as tomography or holography‐based reconstruction, is deliberately omitted. Throughout the review the development of various characterization methods is described, they are critically compared, and promising directions of future research are highlighted.

show abstract

“…Recently, 2D light scattering technology has been proven to be an efficient tool for label free discriminating cellular compartments [11][12][13][14][15]. As an improvement of 1D light scattering, 2D light scattering images can expose much more internal structural information, providing a good view for label-free cellular analysis.…”

Section: Introductionmentioning

confidence: 99%

“…As an improvement of 1D light scattering, 2D light scattering images can expose much more internal structural information, providing a good view for label-free cellular analysis. For example, 2D light scattering technology has been utilized to differentiate normal granulocytes with leukemic cells [11] and classify T lymphocytes [12], bacterial species [13], ovarian cancer cells [14], lung cancer cell lines [15], and so on, exhibiting extremely high ability to distinguish different types or status of cells without labeling. However, the applications of 2D light scattering were limited by the challenge of pattern recognition, which is attributed to the absence of clear features for cell discrimination.…”

Section: Introductionmentioning

confidence: 99%

Label‐free classification of dead and live colonic adenocarcinoma cells based on 2D light scattering and deep learning analysis

Yao

et al. 2021

Cytometry Pt A

View full text Add to dashboard Cite

The measurement of cell viability plays an essential role in the area of cell biology. At present, the common methods for cell viability assay mainly on the responses of cells to different dyes. However, the additional steps of cell staining will consequently cause time-consuming and laborious efforts. Furthermore, the process of cell staining is invasive and may cause internal structure damage of cells, restricting their reuse in subsequent experiments. In this work, we proposed a label-free method to classify live and dead colonic adenocarcinoma cells by 2D light scattering combined with the deep learning algorithm. The deep convolutional network of YOLO-v3 was used to identify and classify light scattering images of live and dead HT29 cells. This method achieved an excellent sensitivity (93.6%), specificity (94.4%), and accuracy (94%). The results showed that the combination of 2D light scattering images and deep neural network may provide a new label-free method for cellular analysis.

show abstract

Two‐Dimensional Light Scattering Anisotropy Cytometry for Label‐Free Classification of Ovarian Cancer Cells via Machine Learning

Cited by 26 publications

References 42 publications

RETRACTED: BCNet: A Novel Network for Blood Cell Classification

RETRACTED: BCNet: A Novel Network for Blood Cell Classification

Single‐Particle Characterization by Elastic Light Scattering

Label‐free classification of dead and live colonic adenocarcinoma cells based on 2D light scattering and deep learning analysis

Contact Info

Product

Resources

About