Table 6 Summary of previous studies on artificial intelligence (AI)-based label-free identification of biological cells using digital in-line holographic microscopy
Year | Object | Content | AI algorithm | References |
|---|---|---|---|---|
2018 | Erythrocyte | Classification of discocytes, echinocytes, and spherocytes | Decision tree | [197] |
2018 | Erythrocyte | Classification of healthy and malaria-infected erythrocytes | Support vector machine (SVM) | [198] |
2018 | Leukocyte | Classification of lymphocytes, granulocytes, and monocytes | SVM with a linear kernel | [199] |
2017 | Tumor cell | Screening and enumeration of erythrocytes, peripheral blood mononuclear cells, and breast cancer cells | Decision tree | [200] |
2021 | Tumor cell | Classification of human mammary gland epithelial cells, breast cancer cells, and esophageal cancer cells | Convolutional neural network (CNN) | [201] |
2023 | Tumor cell | Enumeration of breast cancer cells and ovarian cancer cells | Custom-built shallow network | [202] |
2016 | Yeast cell | Evaluation of viability and concentration of yeast cells | SVM | [203] |
2023 | Yeast cell | Evaluation of viability of yeast cells | You Only Look Once version 5 | [204] |
2018 | Diatoms and algae | Automatic identification of various biological cells | Random forest | [205] |
2021 | Prorocentrum lima (P. lima) | Evaluation of death rate of algae P. lima | SVM | [206] |
2022 | Phaeodactylum tricornutum (P. tricornutum) | Enumeration of clustered algae P. tricornutum | Three-dimensional CNN | [207] |