# Analysis of the Nosema Cells Identification for Microscopic Images

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials: Preparation of The Dataset

- The first strategy is based on an image processing approach, where features were extracted manually.
- The second set of strategies is based on the use of the whole sub-image and the deep learning.

## 3. Methods

#### 3.1. Strategy 1: Nosema Cells Recognition with Image Processing and Machine Learning

#### 3.1.1. Preprocessing for Feature Extraction

#### Geometric Features Extraction

- The size/the perimeter: given that the shape of the Nosema cell is similar to an ellipse form and the other objects have different rounds shapes, perimeter formula of an ellipse adopted have been adopted in this study. This calculation is based on a and b variables where a is the semi-major axis and b is the semi-minor axis. Perimeter P is given by the following equation:$$P=\text{}\mathsf{\pi}\xb7\sqrt{2\xb7{\left({a}^{2}+b\right)}^{2}}$$
- Area A is given by the following formula:$$\mathrm{A}=\text{}\mathsf{\pi}\xb7a\xb7b$$
- Relation R is the dividing quotient of the height (H) and width (W) of the shape.$$\mathrm{R}=\text{}\mathrm{H}/\mathrm{W}\text{}$$
- The equivalent diameter (D), which is the diameter of the circle with the same area of the object,$$\mathrm{D}=\sqrt{4\times \frac{\mathrm{A}}{\mathsf{\pi}}}$$
- The solidity (S): it is the portion of the area of the convex region contained in the object,$$\mathrm{S}=\frac{\mathrm{A}}{\mathrm{convex}\text{}\mathrm{area}}$$
- The eccentricity (E): it is the relation between the distance of the focus of the ellipse and the length of the principal axis. Let $f=1-\frac{a}{b}$ in which a is the semi-major axis and b is the semi-minor axis of the ellipse.$$\mathrm{E}=\sqrt{f\times \left(2-f\right)}$$

#### Statistic Features Extraction

- The standard deviation of these distances have been calculated and which is the feature number 7, the standard deviation is a measure of variability, or what the range of values is, it normalizes the elements of N along the first array dimension whose size does not equal to 1; where P can be a vector or a matrix and in this case is a vector of the radius values of polar coordinates of the studied object, and E is its mean. It is given by Equation (7):$$Std.deviation\left(\sigma \right)=\sqrt{\frac{1}{N}\xb7{\displaystyle \sum}_{j=1}^{N}{\left({P}_{ij}-{E}_{i}\right)}^{2}}$$
- The Variance ${\sigma}^{2}$ is the mean of the squared distances between a value and the mean of those values: it normalizes Y by n − 1 if n > 1, where n is the sample size or pixels shape number. This is an unbiased estimator of the variance of the population from which x is drawn, as long as x consists of independent, distributed distances. For n = 1, Y is normalized by n with μ is the average of all x values. In this case, the variance is calculated as the normalized distances between the centroid and every single pixel in the object shape.$${\sigma}^{2}=\frac{\left({x}_{1}-\mu \right){\text{}}^{2}+{\left({x}_{2}-\mu \right)}^{2}+{\left({x}_{3}-\mu \right)}^{2}+\dots +{\left({x}_{n}-\mu \right)}^{2}}{n}$$
- The Variance derivate is the derivate that calculates the difference and the approximate derivative of the variance (X), for a vector X, is [X(2) − X(1) X(3) − X(2) … X(n) − X(n−1)]. It is given by the following equation:$$f\u2019({\sigma}^{2})=-{n}^{-2}\left[\left({x}_{1}-\mu \right){\text{}}^{2}+{\left({x}_{2}-\mu \right)}^{2}+{\left({x}_{3}-\mu \right)}^{2}+\dots +{\left({x}_{n}-\mu \right)}^{2}\right]$$

#### Features Extraction: Texture and GLCM

_{i}is the set of pixels with the color/channel i of the image and p(x

_{i}) is its probability. The 6 entropy parameters are calculated by the same equation 10 above:

_{d}of size N where, N is the total number of grey levels in the image. The (i, j) th entry of G

_{d}represents the number of times a pixel X with intensity value i is separated from a pixel Y with intensity value j at a particular distance k in a particular direction d. Where the distance k is a non-negative integer and the direction d is specified by d = (d

_{1}, d

_{2}, d

_{3}, … d

_{n}), where d

_{i}∈ {0, k, −k} ∀i = 1, 2, 3, …, n [32]. Four features were extracted from the Haralick GLCM applied to the image of the yellow channel: contrast, correlation, energy, and homogeneity, the most significant features given by the GLCM.

#### Segmentation Diagram Block and Recognition

#### 3.1.2. The Use of Support Vector Machine: SVM

_{1}and X

_{2}, and γ: gamma is used only for RBF kernel. The non-regularization of the values of “γ” and “C” will cause overfitting or an underfitting of the model. The SVM has been configured with C = 3 and γ = 5 × 10

^{−5}as the architecture with the best result. In this case, the SVM model will classify two classes corresponding to Nosema cells and non-Nosema cells (or other objects).

#### 3.2. Strategy 2: Nosema Cells Recognition Using Deep Learning Approaches

#### 3.2.1. Nosema Recognition with the Implemented CNN

#### 3.2.2. The Use of Transfer Learning

#### Nosema Recognition with Alexnet Classifier

#### Nosema Recognition VGG-16 and VGG-19 Classifiers

## 4. Experimental Methodology and Results

## 5. Discussion

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Lewis, C.; Denny, J.B.B.; Jarrad, R.P.; Earle, S.R. Nosema pyrausta: Its biology, history, and potential role in a landscape of transgenic insecticidal crops. Biol. Control
**2009**, 48, 223–231. [Google Scholar] [CrossRef] - Andre, J.B.; Emily, D.J.; Jayre, A.J.; Herman, K.L. North American Propolis Extracts From Upstate New York Decrease Nosema ceranae (Microsporidia) Spore Levels in Honey Bees (Apis mellifera). Front. Microbiol.
**2020**, 11, 1719. [Google Scholar] - Sinpoo, C.; Paxton, R.J.; Disayathanoowat, T.; Krongdang, S.; Chantawannakul, P. Impact of Nosema ceranae and Nosema apis on individual worker bees of the two host species (Apis cerana and Apis mellifera) and regulation of host immune response. J. Insect Physiol.
**2018**, 105, 1–8. [Google Scholar] [CrossRef] - Paneka, J.; Paris, L.; Roriz, D.; Mone, A.; Dubuffet, A.; Delbac, F.; Diogon, M.; El Alaoui, H. Impact of the microsporidian Nosema ceranae on the gut epithelium renewal of the honeybee, Apis mellifera. J. Invertebr. Pathol.
**2018**, 159, 121–128. [Google Scholar] [CrossRef] [PubMed] - Calderón, R.A.; Ramírez, F. Enfermedades de las Abejas Melíferas, con Énfasis en Abejas Africanizadas; CINAT-UNA: Heredia, Costa Rica, 2010; p. 125. [Google Scholar]
- Higes, M.; Hernández, R.M.; Bailón, E.G.; Palencia, P.G.; Meana, A. Detection of infective Nosema ceranae (Microsporidia) spores in corbicular pollen of forager honeybees. J. Invertebr. Pathol.
**2008**, 97, 76–78. [Google Scholar] [CrossRef] - Higes, M.; Martín, R.; Meana, A. Nosema ceranae in Europe: An emergent type C nosemosis. Apidologie
**2010**, 41, 375–392. [Google Scholar] [CrossRef] [Green Version] - Suwannapong, G.; Maksong, S.; Phainchajoen, M.; Benbow, M.E.; Mayack, C. Survival and health improvement of Nosema infected Apis florea (Hymenoptera: Apidae) bees after treatment with propolis extract. J. Asia Pac. Entomol.
**2018**, 21, 437–444. [Google Scholar] [CrossRef] - Mura, A.; Pusceddu, M.; Theodorou, P.; Angioni, A.; Flori, I.; Paxton, R.J.; Satta, A. Propolis Consumption Reduces Nosema ceranae Infection of European Honey Bees (Apis mellifera). Insects
**2020**, 11, 124. [Google Scholar] [CrossRef] [Green Version] - Tu, G.J.; Hansen, M.K.; Kryger, P.; Ahrendt, P. Automatic behaviour analysis system for honeybees using computer vision. Comput. Electron. Agric.
**2016**, 122, 10–18. [Google Scholar] [CrossRef] - Giuffre, C.; Lubkin, S.R.; Tarpy, D.R. Automated assay and differential model of western honey bee (Apis mellifera) autogrooming using digital image processing. Comput. Electron. Agric.
**2017**, 135, 338–344. [Google Scholar] [CrossRef] [Green Version] - Szczurek, A.; Maciejewska, M.; Bąk, B.; Wilde, J.; Siuda, M. Semiconductor gas sensor as a detector of Varroa destructor infestation of honey bee colonies—Statistical evaluation. Comput. Electron. Agric.
**2019**, 162, 405–411. [Google Scholar] [CrossRef] - Alvarez-Ramos, C.M.; Niño, E.; Santos, M. Automatic Classification of Nosema Pathogenic Agents through Machine Vision techniques and Kernel-based Vector Machines. In Proceedings of the 2013 8th Computing Colombian Conference (8CCC), Armenia, Colombia, 21–23 August 2013; [Google Scholar] [CrossRef]
- Dghim, S.; Travieso, C.M.; Dutta, M.K.; Hernández, L.E. Nosema Pathogenic Agent Recognition Based on Geometrical and Texture Features Using Neural Network Classifier. In Proceedings of the International Conference on Contemporary Computing and Applications (IC3A) 2020, Lucknow, India, 5–7 February 2020. [Google Scholar]
- Yadav, S.S.; Jadhav, S.M. Deep convolutional neural network based medical image classification for disease diagnosis. J. Big Data
**2019**, 6, 113. [Google Scholar] [CrossRef] [Green Version] - Khemphila, A.; Boonjing, V. Heart Disease Classification Using Neural Network and Feature Selection. In Proceedings of the 21st International Conference on Systems Engineering 2011, Las Vegas, NV, USA, 16–18 August 2011. [Google Scholar]
- Jain, R.; Jain, N.; Aggarwal, A.; Hemanth, D.J. Convolutional Neural Network Based Alzheimer’s Disease Classification from Magnetic Resonance Brain Images. Cogn. Syst. Res.
**2018**, 57, 147–159. [Google Scholar] [CrossRef] - Guan, Q.; Huang, Y.; Zhong, Z.; Zheng, Z.; Zheng, L.; Yang, Y. Thorax Disease Classification with Attention Guided Convolutional Neural Network. Pattern Recognit. Lett.
**2019**, 131, 38–45. [Google Scholar] [CrossRef] - Chen, L.C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell.
**2018**, 40, 834–848. [Google Scholar] [CrossRef] [PubMed] - Panagiotakis, C.; Argyros, A. Region-Based Fitting of Overlapping Ellipses and Its Application to Cells Segmentation. Image Vis. Comput.
**2020**, 93, 103810. [Google Scholar] [CrossRef] - Zieliński, B.; Sroka-Oleksiak, A.; Rymarczyk, D.; Piekarczyk, A.; Brzychczy-Włoch, M. Deep learning approach to describe and classify fungi microscopic images. PLoS ONE
**2020**, 15, e0234806. [Google Scholar] [CrossRef] - Ge, M.; Su, F.; Zhao, Z.; Su, D. Deedeep learning analysis on microscopic imaging in materials science. Mater. Today Nano
**2020**, 11, 100087. [Google Scholar] [CrossRef] - Zhang, Y.; Jiang, H.; Ye, T.; Juhas, M. Deep Learning for Imaging and Detection of Microorganisms. Trends Microbiol.
**2021**. [Google Scholar] [CrossRef] - Moen, E.; Bannon, D.; Kudo, T.; Graf, W.; Covert, M.; Valen, D.V. Deep learning for cellular image analysis. Nat. Methods
**2019**, 16, 1233–1246. [Google Scholar] [CrossRef] [PubMed] - Miss, H.; Vala, J.; Baxi, A. A Review on Otsu Image Segmentation Algorithm. Intern. J. Adv. Res. Comp. Eng. Tech.
**2013**, 2, 387–389. [Google Scholar] - Gonzales, R.C.; Woods, R.E. Digital Image Processing, 4th ed.; Pearson: Upper Saddle River, NJ, USA, 2017. [Google Scholar]
- Kolkur, S.; Kalbande, D.R. Survey of Texture Based Feature Extraction for Skin Disease Detection. In Proceedings of the International Conference on ICT in Business Industry & Government (ICTBIG) 2016, Indore, India, 18–19 November 2016. [Google Scholar]
- Al-Hiary, H.; Ahmad, S.B.; Reyalat, M.; Braik, M.; ALRahamneh, Z. Fast and Accurate Detection and Classification of Plant Diseases. Inter. J. Comp. Appl.
**2011**, 17, 31–38. [Google Scholar] [CrossRef] - Rundo, L.; Tangherloni, A.; Galimberti, S.; Cazzaniga, P.; Woitek, R.; Sala, E.; Nobile, M.S.; Mauri, G. HaraliCU: GPU-powered Haralick feature extraction on medical images exploiting the full dynamics of gray-scale levels. In Proceedings of the International Conference on Parallel Computing Technologies 2020, Macau, China, 7–10 December 2020. [Google Scholar]
- Rundo, L.; Tangherloni, A.; Cazzaniga, P.; Mistri, M.; Galimberti, S.; Woitek, R.; Sala, E.; Mauri, G.; Nobile, M.S. A CUDA-powered method for the feature extraction and unsupervised analysis of medical images. J. Supercomput.
**2021**. [Google Scholar] [CrossRef] - Mohanaiah, P.; Sathyanarayana, P.; GuruKumar, L. Image Texture Feature Extraction Using GLCM Approach. Int. J. Sci. Res. Pub.
**2013**, 3322, 750–757. [Google Scholar] [CrossRef] - Sebastian, B.; Unnikrishnan, A.; Balakrishnan, K. Grey level co-occurrence matrices: Generalization and some new features. Int. J. Comput. Sci. Eng. Inf. Technol.
**2012**, 8, 1463–1465. [Google Scholar] - Tian, Y.; Shi, Y.; Liu, X. Recent Advances on Support Vector Machines Research. Tech. Econ. Dev. Econ.
**2012**, 18, 5–33. [Google Scholar] [CrossRef] [Green Version] - Weiss, K.; Khoshgoftaar, T.M.; Wang, D. A survey of transfer learning. J. Big Data
**2016**, 3, 9. [Google Scholar] [CrossRef] [Green Version] - Ma, Y.; Gong, W.; Mao, F. Transfer learning used to analyze the dynamic evolution of the dust aerosol. J. Quant. Spectrosc. Radiat. Transf.
**2015**, 153, 119–130. [Google Scholar] [CrossRef] - Xie, M.; Jean, N.; Burke, M.; Lobell, D.; Ermon, S. Transfer learning from deep features for remote sensing and poverty mapping. In Proceedings of the 30th AAAI Conference on Artificial Intelligence 2015, Pheonix, AZ, USA, 12–17 February 2015; pp. 1–10. [Google Scholar]
- Ogoe, H.A.; Visweswaran, S.; Lu, X.; Gopalakrishnan, V. Knowledge transfer via classification rules using functional mapping for integrative modeling of gene expression data. BMC Bioinform.
**2015**, 7, 1–15. [Google Scholar] [CrossRef] [Green Version] - Kan, M.; Wu, J.; Shan, S.; Chen, X. Domain adaptation for face recognition: Targetize source domain bridged by common subspace. Int. J. Comput. Vis.
**2014**, 109, 94–109. [Google Scholar] [CrossRef] - Widmer, C.; Ratsch, G. Multitask learning in computational biology. JMLR
**2012**, 27, 207–216. [Google Scholar]

**Figure 1.**Example of extraction of Nosema cells and other existing objects in a part of one microscopic image.

**Figure 3.**Shape results of two examples before and after preprocessing. The first sample is Nosema and the second is non Nosema object.

**Figure 5.**The Segmentation Diagram Block of the first strategy in Nosema detection: The Training Mode consists of the part of dataset construction, features extraction, and their fusion to be trained with ANN and SVM. The Testing Mode consists of data preparation for testing the model and decision making.

**Figure 8.**The Accuracy (blue curve) and loss (orange curve) results given by VGG-16 simulation: 96.25% of success accuracy with 20 epochs.

Images | Number | Color | Type | Resolution |
---|---|---|---|---|

Nosema sub-images | 1000 | RGB | JPEG | 229 × 161 |

Non-Nosema sub-images | 1000 | RGB | JPEG | 450 × 257 |

Number of Features | Classifier | Accuracy | Observation |
---|---|---|---|

15 Features | ANN | 79.00% | For 1400 neurons in the hidden layer |

SVM | 81.00% | Using kernel RBF | |

19 Features | ANN | 83.20% | For 1400 neurons in the hidden layer |

SVM | 83.50% | Using kernel RBF |

Layer Type | Output Shape | Number of Parameters |
---|---|---|

conv2d (Conv2D) | (None, 80, 80, 32) | 896 |

batch_normalization (BatchNo) | (None, 80, 80, 32) | 128 |

conv2d_1 (Conv2D) | (None, 80, 80, 32) | 9248 |

batch_normalization_1 (Batch) | (None, 80, 80, 32) | 128 |

max_pooling2d (MaxPooling2D) | (None, 80, 80, 32) | 0 |

dropout (Dropout) | (None, 80, 80, 32) | 0 |

conv2d_2 (Conv2D) | (None, 80, 80, 64) | 18,496 |

batch_normalization_2 (Batch) | (None, 40, 40, 64) | 256 |

conv2d_3 (Conv2D) | (None, 40, 40, 64) | 36,928 |

batch_normalization_3 (Batch) | (None, 40, 40, 64) | 256 |

max_pooling2d_1 (MaxPooling2) | (None, 40, 40, 64) | 0 |

dropout_1 (Dropout) | (None, 40, 40, 64) | 0 |

Model | Parameters | Setting Values |
---|---|---|

AlexNet | Learning algorithm | Sgdm |

Initial Learning Rate | 0.001 | |

Mini-batchsize | 64 | |

Maximum epochs | 0 | |

VGG-16 and VGG-19 | Learning algorithm | Adam |

Initial Learning rate | 0.0004 | |

Mini-batch size | 10 | |

Maximum epochs | 25 | |

Validation Frequency | 3 | |

Validation Information | Test-Images |

Experiment (Trained Data, the Rest for Validation) | Accuracy | Epochs Number |
---|---|---|

0.5 | 84.58% | 6 |

0.6 | 83.98% | 6 |

0.7 | 86.98% | 6 |

0.8 | 85.28% | 6 |

Experiments | Epochs | Accuracy | |
---|---|---|---|

VGG-16 | VGG-19 | ||

0.7 | 6 | 76.29% | 71.95% |

08 | 6 | 92.50% | 93.00% |

12 | 94.50% | 82.00% | |

20 | 96.25% | 92.32% | |

25 | 93.00% | 93.50% | |

0.9 | 6 | 88.00% | 77.00% |

ANN | SVM | CNN | AlexNet | VGG-16 | VGG-19 |
---|---|---|---|---|---|

83.20% | 83.50% | 92.5% | 87.48% | 96.25% | 93.00% |

Reference | Data Size | Method | Accuracy |
---|---|---|---|

[14] | 185 images (1655 extracted features) | ANN | 91.10% |

This work | 2000 images | ANN | 83.20% |

This work | 2000 images | SVM | 83.50% |

This work | 2000 images | CNN | 92.50% |

This work | 2000 images | AlexNet | 87.48% |

This work | 2000 images | VGG-16 | 96.25% |

This work | 2000 images | VGG-19 | 93.50% |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Dghim, S.; Travieso-González, C.M.; Burget, R.
Analysis of the Nosema Cells Identification for Microscopic Images. *Sensors* **2021**, *21*, 3068.
https://doi.org/10.3390/s21093068

**AMA Style**

Dghim S, Travieso-González CM, Burget R.
Analysis of the Nosema Cells Identification for Microscopic Images. *Sensors*. 2021; 21(9):3068.
https://doi.org/10.3390/s21093068

**Chicago/Turabian Style**

Dghim, Soumaya, Carlos M. Travieso-González, and Radim Burget.
2021. "Analysis of the Nosema Cells Identification for Microscopic Images" *Sensors* 21, no. 9: 3068.
https://doi.org/10.3390/s21093068