EggCountAI: A Convolutional Neural Network Based Software for Counting of Aedes Aegypti Mosquito Eggs

doi:10.21203/rs.3.rs-2963897/v1

Download PDF

Research Article

EggCountAI: A Convolutional Neural Network Based Software for Counting of Aedes Aegypti Mosquito Eggs

https://doi.org/10.21203/rs.3.rs-2963897/v1

This work is licensed under a CC BY 4.0 License

Version 1

posted

You are reading this latest preprint version

1. Mosquito-borne diseases exert a huge impact on both animal and human populations, posing substantial health risks. Established practices, such as long-lasting insecticidal nets (LLINs) and indoor residual spraying (IRS), are proving inadequate for controlling mosquito-borne diseases. The behavioural fitness traits of mosquitoes, such as locomotion and fecundity, are crucial factors that influence the spread of diseases. Technological advancements, including Artificial Intelligence (AI), have provided various methods that can be used to monitor these traits effectively.

2. This study presents EggCountAI, a Mask RCNN (Region-based Convolutional Neural Network) based free automatic egg counting tool for Aedes aegypti mosquitoes, the primary vector of several life-threatening diseases, including dengue fever. EggCountAI takes a folder containing egg strip images as input and counts eggs in all the images without any supervision. EggCountAI also provides flexible filtration, considering the possibility of unwanted impurities of different sizes on images. The performance of the EggCountAI was tested using microscopic and macroscopic images of eggs laid on a paper strip. To validate EggCountAI's capability, the results were also compared with two commonly employed tools, ICount and MECVision, confirmed by manually counting all eggs on strips.

3. The results obtained from EggCountAI highlight its remarkable performance, achieving an overall percentage accuracy of 98.88% for micro images and 96.06% for macro images. EggCountAI also significantly outperformed two currently available tools, ICount and MECVision, in performance. The overall accuracy of ICount was 81.71% for micro images and 82.22% for macro images, while the overall accuracy of MECVision was 68.01% for micro images and 51.71% for macro images. The superior performance of the EggCountAI was most evident when handling overlapping or clustered eggs.

4. The use of such tools can benefit in establishing the role of mosquito fitness changes to improve epidemiological models and implement new mosquito management strategies. Introducing such tools can also help to reduce transmission by vectors quicker, by finding the mosquitoes' preferred sites to lay their eggs. Though the focus of this AI-based tool is to count the number of eggs, this tool can be modified to track other mosquito fitness parameters such as egg sizes.

Entomology

Behavioral Ecology

Infectious Diseases

Artificial Intelligence and Machine Learning

EggCountAI

long-lasting insecticidal nets

residual spraying

Artificial Intelligence

Mosquito-borne diseases

epidemiological models

Mask RCNN

Fecundity

Mosquito-transmitted pathogens are considered deadly due to their worldwide impact on public health [1]. Annually, malaria causes around 230 million cases [2], majorly impacting children under five years [3], while dengue causes an estimated 390 million infections with about 20,000 deaths per year [4]. Regardless, with over a hundred years of research and deployment of long-lasting insecticidal nets (LLINs) and indoor residual spraying (IRS), diseases transmitted by mosquitoes remain a concern worldwide [5]. The impact of mosquito transmitted diseases will also likely become worse in future due to the growth of key factors of pathogen spread, such as rising population, urbanisation, lack of infrastructure in large cities, climate change, insecticide resistance, travel, and trade [6].

Infections with pathogens can modulate different behavioural and fitness traits of mosquitoes such as locomotion, blood-feeding, fecundity and fertility [7]. Mosquito-borne viruses can also significantly impact the mosquito’s nervous system leading to behavioural changes that influence the transmission of mosquito-borne diseases [8–10]. In epidemiological context, it is necessary to assess the mosquitoes' fitness. For example, this may facilitate in understanding how different mosquito populations adapt to environmental conditions [11, 12] and the interactions between vectors and their pathogens [13, 14]. Fecundity, the number of eggs laid by female mosquitoes, is a critical trait in determining a mosquito’s fitness, and has been used as a marker to assess the population fitness of mosquitoes [15]. Fecundity also helps in determining the vector’s density in a specific area by assessing the number of eggs present in the designated area [16].

Aedes aegypti mosquitos are the primary vector of several medically significant viruses, including dengue, Zika, yellow fever, and chikungunya. Female mosquitoes can lay anywhere from 20 to 140 eggs per blood meal depending on factors such as the quantity of blood consumed, the female's body size, and reproductive capacity [17]. Novel vector control strategies involve production of thousands of mosquitoes, possibly over many gonotrophic cycles and generations, requiring the counting of hundreds of thousands of eggs. Counting the number of eggs manually with the aid of a magnifying lens or optical microscope makes the process tedious, slow, and prone to errors.

The automatic counting of mosquito eggs is a subject that has received considerable attention in the last few years, with several automatic egg-counting tools recently developed. Some of these tools use segmentation to acquire pixels containing mosquito eggs [18, 19], while others provide graphical user interfaces through web app [20] or computer software [21, 22]. A recent study also employed a wavelet-based method to count eggs [23]; however, unlike the others listed, it requires knowledge of mathematical techniques to process samples. Some tools also required extensive hardware for successful counting, such as scanners, LED lighting, and mechanical support [24, 25]. In most of the egg counting tools, although some operations work automatically, however, each image must be processed separately by manually adjusting the different parameters, such as intensity threshold value and the minimum and maximum size of a unit egg area. Additionally, the performance/accuracy of these current methods significantly drops when eggs in the image are in clusters or overlap.

Convolutional Neural Networks (CNNs), a class of deep neural networks that have revolutionised computer vision tasks by enabling automatic feature extraction [26]. CNNs are equipped with features like instance segmentation and Non-Maximum Suppression (NMS) to accurately identify and segment objects, even when they are overlapping or close together [27]. In mosquito research CNNs have been used to identify many different characteristics including breeding site detection [28], and eggs identification [29]. However, a CNNs-based tool has not been developed to count the number of eggs laid by mosquitoes. Considering the potential of CNNs, it is hypothesised that the application of CNNs can help in counting the mosquitoes' eggs with higher accuracy compared to current methods.

To overcome limitations such as performance drop when the eggs in the image are in clusters or overlap, and the tedious requirement of processing each image separately, we have developed a CNNs-based free software EggCountAI to count Aedes mosquito eggs. The software can count eggs laid on a paper strip from a folder containing several micro or macro images, and also offers filtration to remove undesired impurities. In order to test the software’s capability, we compared EggCountAI with two widely used tools, ICount [21] and MECVision [20].

Maintenance of the mosquito colony:

Aedes aegypti mosquitoes, were maintained in 30 × 30 × 30 cm Plexiglas cages at 27°C temperature and relative humidity of 65% with a 12-hour light and dark photoperiod daily. Mosquitoes had continuous access to sugar, and female mosquitoes aged 2 to 5 weeks were given a blood meal every week.

Artificial blood feeding and egg collection:

Chicken blood meal was provided using chicken skin and an artificial blood feeding device (Hemotek®, Accrington, UK) once a week, lasting 1 hour each time. Three days post-blood meal, beakers were deployed in the cage for female oviposition. A strip of sandpaper measuring the perimeter of a 100 ml beaker (160 mm) in length was inserted into the container. The container was then filled with 50 ml of water up to a depth of half the width of the sandpaper strip (25 mm). After the completion of mosquito oviposition, which typically occurred within five days of the blood meal, the sandpaper strip was taken out of the colony cage and allowed to dry at room temperature.

Capturing and processing of images:

Once the sandpaper strip containing eggs were collected and dried, images of the strip could be taken at any time. Two distinct types of images were collected, labelled as "micro" or "macro", following a similar pattern as described in other studies [20, 21]. Using a camera (Olympus, TG6), an image of the entire sandpaper strip was captured with the focus on the plane of the eggs. This collection of images will be referred as "macro" in this paper. The second image type was taken utilising a microscope (Nikon SMZ18) set at 8.0× magnification with a 1.0× objective lens with the Nikon NIS-Elements software (Nikon, Japan). These images will be referred to as "micro". Macro images were cropped with the help of the Photos App (Microsoft Windows) to eliminate the area without mosquito eggs. Micro images were ready for analysis without any pre-processing.

Training and Validation:

Two different models were trained based on macro and micro images to improve accuracy in egg detection. In the case of the micro images-based model, 100 images were collected, with 70 used for training purposes, 20 used for validation, and 10 used for testing purposes. The dataset used for training contained images with egg counts ranging from 13 to 167, while the validation set comprised images with egg counts between 24 and 182. In the testing phase, the images had object counts ranging from 104 to 215. The model was trained for 20 epochs with 500 steps per epoch, and the detection threshold was set to 70%, resulting in the exclusion of proposals with a confidence level below 0.7 out of 1.0. Training and validation data annotations were created with the help of the Makesense web tool [30] in the form of .json file.

In the case of the macro image-based model, 100 images were collected from which 70 were used for training purposes, 20 used for validation, and 10 used for testing purposes. The dataset used for training contained images with egg counts ranging from 133 to 624, while the validation set comprised images with egg counts between 76 and 357. In the testing phase, the images had object counts ranging from 1047 to 3658. The macro model was also trained for 20 epochs with 500 steps per epoch, and the detection threshold was 70%.

Programming and computational system:

All software development and data processing were performed under a Windows 11 Pro 64-bit environment using AMD Ryzen 9 5900HX with Radeon Graphics (3.30 GHz) processor and 2x16GB SO-DIMM DDR4-3200 RAM. The graphical user interface of EggCountAI was implemented using Python 3.8, Tensorflow 2.40, and OpenCV 4.6.0.66.

Manual counting:

To validate the accuracy of EggCountAI software, a manual egg count was performed using ImageJ software [31]. The Multi-point tool was selected to insert the multiple points inside the image of the sandpaper strip. The Add [t] feature inside the ROI Manager of ImageJ helped to add all multi points along with the decimal count value (Fig. 1(a)). Decimal count values and Multi-point eliminated the chances of errors in manual counting.

Performance evaluation:

In results and comparative analysis, performance was validated using percentage accuracy and overall percentage accuracy. For percentage accuracy, individual images were considered, while for overall percentage accuracy, the same formula was used; however, all images of the relevant dataset were considered. The formula used for the percentage accuracy is given in Eq. 1.

$$Percentage Accuracy=\left(1-\frac{\left|\text{c}\text{o}\text{u}\text{n}\text{t}\text{e}\text{d} \text{e}\text{g}\text{g}\text{s} \text{b}\text{y} \text{s}\text{o}\text{f}\text{t}\text{w}\text{a}\text{r}\text{e}-\text{g}\text{r}\text{o}\text{u}\text{n}\text{d} \text{t}\text{r}\text{u}\text{t}\text{h} \text{n}\text{u}\text{m}\text{b}\text{e}\text{r} \text{o}\text{f} \text{e}\text{g}\text{g}\text{s}\right|}{\text{g}\text{r}\text{o}\text{u}\text{n}\text{d} \text{t}\text{r}\text{u}\text{t}\text{h} \text{n}\text{u}\text{m}\text{b}\text{e}\text{r} \text{o}\text{f} \text{e}\text{g}\text{g}\text{s}}\right)*100$$

Egg estimation using EggCountAI software:

The type of deep neural network used in EggCountAI is Mask RCNN (Region-based Convolutional Neural Network). Mask RCNN is a deep learning model that excels in detecting objects and segmenting them in computer vision applications [32]. Mask R-CNN employs a two-stage approach to perform both object detection and segmentation tasks. In the first stage, the region proposal network (RPN) processes the input image and generates potential object regions in the form of rectangular bounding boxes. The second stage of Mask R-CNN involves the utilisation of two subnetworks working in parallel, namely the object detection network and the mask prediction network. The object detection network classifies objects in each potential object region and improves the accuracy of their bounding box coordinates. This task is accomplished by utilising convolutional and fully connected layers to analyse the proposed regions, which generate object class probabilities and bounding box coordinates. The Mask prediction network inputs potential object regions and corresponding class probabilities and produces binary masks for each potential object region (Fig. 1(c)).

EggCountAI provides five flexible input parameters; (1) choosing between micro and macro image analysis type, (2) setting vertical divisions, (3) setting horizontal divisions, (4) setting the filtration level, and (5) adjusting the detection confidence threshold. Micro and macro options can be selected considering the input data type. Vertical and horizontal divisions can divide the input image into smaller patches, enabling the processing of larger images that would be otherwise infeasible due to memory limitations or computational constraints (Fig. 1(b)). Both horizontal and vertical divisions accept values from 1 to 40. Setting the value to 1 for both horizontal and vertical divisions means that the input image will not be divided into any number of patches (mainly used for the micro images as they are mostly with enough zoom). Setting the value to 2 for both means that the input image will be divided into a 2x2 grid of equal-sized making 4 patches, and setting the value to 40 for both means that the input image will be divided into a 40x40 grid of equal-sized making 1600 patches. The division is only for processing purposes, and after processing, the patches will be combined, and the output image will be in the form of the entire input image.

Whilst setting the horizontal and vertical divisions is mainly for use with macro images, it can also be useful for the micro images depending on the magnification of the microscope. The value of horizontal and vertical divisions for this study was 2 vertical and 2 horizontal divisions for micro images and 25 vertical and 7 horizontal divisions for macro images as the macro images had larger widths compared to heights, and the sizes of eggs in the images were also very small. Setting the filtration level parameter can be used to eliminate noise and impurities from the input image. It takes the value within the range from 0.1 to 10.0. Setting the value to 0.1 means that it will eliminate all the objects in each patch which are 0.1 times bigger or smaller than the average size of eggs in that patch. Setting the value to 10.0 means that it will eliminate all the objects in each patch which are 10.0 times bigger or smaller than the average size of eggs in that patch. The default value of the filtration level is set at 3.0 and kept the same during this study's analysis. The confidence value shows the minimum confidence level that a detected egg must have to be part of the counted eggs. The confidence value ranges from 0.0 to 1.0. Where 1.0 means that the software is fully confident that the detected object is the mosquito egg. The default value of confidence is set at 0.7.

After setting these parameters the input folder containing the macro or micro images can be selected. EggCountAI will create a new folder inside the input folder named “Results” during processing containing the processed input images with a common prefix Result- in their names. EggCountAI also creates a simple text file in the Results folder containing the processed images' names and the number of eggs detected. For instance, if the name of the input image is Eggimage1, the Results folder will contain the processed image with the name Result-Eggimage1 and the text file will show the name Result-Eggimage1 along with the number of eggs detected. Besides saving the processed images and logs in the Result folder, the software will also show the input images, processed images, and numbers of eggs detected in the user interface. The software also gives the control to the user to stop the process at any time by pressing the stop button and will save the partially processed results. The egg-counting procedure was displayed on the user interface depicted in Fig. 2.

10 macro and 10 micro images were processed through EggCountAI. Both sets of data were processed separately by selecting micro and macro options from the software.

Micro Images:

The performance of the EggCountAI tool for micro images was analysed on a dataset of 10 random micro images containing amounts of eggs ranging between 104 to 215 (Table 1). EggCountAI successfully detected eggs in each image with a high level of accuracy, and was able to identify those that were overlapping, demonstrating the tool's effectiveness with complex datasets. The high level of accuracy of detections across the datasets analysed showcases EggCountAI’s ability to adapt to different egg patterns, with an overall percentage accuracy of the tool was 98.88% across all images.

Table 1

EggCountAI results for micro images
Image	Ground Truth	EggCountAI	Accuracy %
1	189	186	98.41%
2	156	153	98.07%
3	157	157	100%
4	183	180	98.36%
5	158	154	97.46%
6	177	177	100%
7	124	123	99.19%
8	215	212	98.60%
9	104	104	100%
10	150	149	99.33%
Total	1613	1595	98.88%

To further illustrate the performance of EggCountAI, Fig. 3(a-d) showcases a combined image of four out of the ten processed images, with rectangles outlining the detected eggs. This visual representation allows for a comprehensive understanding of EggCountAI’s performance, highlighting the accurate detections.

Macro Images

The performance of the EggCountAI tool for macro images was analysed on a dataset of 10 random macro images containing eggs ranging between 1047 to 3658 (Table 2). The EggCountAI tool exhibited remarkable efficacy in accurately detecting a significant number of eggs in each image, including instances where the eggs were very close to each other, highlighting its effectiveness in assessing samples obtained without a microscope.

Table 2 presents the egg detection results for the macro images. Based on the findings presented in Table 2, it can be observed that EggCountAI achieved above 91% accuracy in all macro images. The overall percentage accuracy was 96.06%, showing that EggCountAI can achieve outstanding results even if macro images are fed with thousands of eggs.

Table 2

EggCountAI results for macro images
Image	Ground Truth	EggCountAI	Accuracy %
1	2377	2185	91.92%
2	1579	1544	97.78%
3	1821	1775	97.47%
4	1416	1391	98.23%
5	1490	1439	96.57%
6	2126	2112	99.34%
7	1748	1724	98.62%
8	1047	1041	99.42%
9	3658	3344	91.41%
10	1611	1575	97.76%
Total	18873	18130	96.06%

Figure 4(a-d) presents a combined image of four macro images out of the ten processed images, where rectangles outline the detected eggs. The figure shows that EggCountAI has successfully detected most of the eggs, including the eggs part of clusters.

Comparative Analysis of Accuracy in EggCountAI, ICount, and MECVision:

To further evaluate the performance of EggCountAI, we conducted a comparative analysis by comparing the results of EggCountAI with the results obtained from ICount and MECVision. The comparison was based on the overall percentage accuracy. The comparative analysis based on micro and macro images is discussed below.

Micro Images:

The previously used 10 micro images were run through the ICount and MECVision and compared to EggCountAI (Table 3). In terms of percentage accuracy, EggCountAI significantly outperformed both ICount and MECVision, with an overall percentage accuracy of 98.88%, compared to 81.71% and 68.01% respectively.

Table 3

Comparative Analysis of EggCountAI, ICount, and MECVision based on micro images
Image	Ground Truth	EggCountAI	ICount	MECVision
1	189	186	149	127
2	156	153	133	121
3	157	157	130	107
4	183	180	159	132
5	158	154	121	99
6	177	177	143	133
7	124	123	110	104
8	215	212	164	98
9	104	104	84	74
10	150	149	125	102
Overall Accuracy %		98.88%	81.71%	68.01%

When analysing micro images, results show that the accuracy of the ICount software decreases where eggs were overlapping or close to the neighbouring eggs (Fig. 5(a)), while the MECVision software missed even some single eggs as well as eggs in clusters (Fig. 5(b)). However, EggCountAI was able to successfully detect most of the eggs irrespective of their closeness and overlapping (Fig. 5(c)).

Macro Images:

For comparison based on macro images, the macro images were processed through ICount and MECVision and compared to EggCountAI results (Table 4). EggCountAI again demonstrated superior performance compared to the other two, with an overall percentage accuracy of 96.06%. The overall percentage accuracy of ICount and MECVision was 82.22% and 51.71%, respectively.

Table 4

Comparative Analysis of EggCountAI, ICount, and MECVision based on macro images
Image	Ground Truth	EggCountAI	ICount	MECVision
1	2377	2185	1693	731
2	1579	1544	1346	1085
3	1821	1775	1489	924
4	1416	1391	1155	543
5	1490	1439	1318	746
6	2126	2112	1829	1259
7	1748	1724	1539	1122
8	1047	1041	932	503
9	3658	3344	2874	1831
10	1611	1575	1344	1016
Overall Accuracy %		96.06%	82.22%	51.71%

ICount analysis of macro images has shown a similar performance as it was in the case of micro images and missed the eggs where they were overlapping or in the form of clusters (Fig. 6(a)). In the case of MECVision, along with missing a few single eggs and clusters of eggs MECVision also cropped the macro input image in a small part (Fig. 6(b)), demonstrating that it might have some size limitation for the input image. If that is the case, it is tedious to crop the egg strip image in small chunks and then process it. Also, it was not confirmed whether it considers the whole input image for the counting or only the small part that it shows during processing. In contrast, regardless of eggs’ proximity and overlapping, EggCountAI has demonstrated a high success rate in detecting most of the eggs (Fig. 6(c)).

Vector control remains a vital strategy in the battle against mosquito-borne diseases. Information about fecundity is integral to effective mosquito management strategies. It can provide valuable data for surveillance and monitoring programs [33], identifying areas with high mosquito populations [34], potential breeding sites [35], and assess the effectiveness of vector control interventions [36]. Fecundity information can also be used to assess physical measurements and fitness, as it has shown a strong correlation with pupal mass and wing size [37].

Manual counting of mosquito eggs is a laborious and time-consuming task. Using automatic tools for egg counting offers numerous benefits, including reduced counting time, enhanced capacity to process more images, and avoiding human errors. We have developed EggCountAI that can count thousands of eggs easily, and with a high accuracy of 98.88% in the case of micro images and 96.06% in the case of macro images.

Alternative egg counting software such as ICount and MECVision require manual processing to upload individual images and for the adjustment of input parameters for each image separately as the size of the eggs and size of the clusters of eggs can vary in each image. Hence, they need separate adjustments of minimum egg size, maximum egg size, and maximum cluster size. The advantage of EggCountAI is that it does not need the adjustment of input parameters for each image separately, as it intelligently performs egg detection based on a convolutional neural network. Additionally, image uploading is very simple and does not require feeding each image separately, enabling the processing of a large number of images within a folder in a single operation without any supervision.

While EggCountAI can accurately count eggs within an image, it does have a limitation; it may cut off eggs located at the boundary of patches when creating a grid of rows and columns to analyse the image, which could result in eggs not being counted or counted multiple times during processing. A possible solution to this problem is to overlap across the boundary of patches. However, the inclusion of an overlap resulted in poor performance and was therefore excluded. Alternatively, the ability to use filtration parameter settings is helpful in reducing the impact of this problem. For instance, if the filtration parameter value is set to 3.0 and the grid patch cuts small parts of an egg across neighbouring patches that are three or more than three times smaller than the average size of the eggs, that would be filtered out during processing. In the case of multiple times counting of a single egg, it can only be counted multiple times if it cuts the significant portions of the egg across neighbouring patches that fall out of the adjusted filtration value.

Here we have presented EggCountAI, a free automatic AI based Aedes mosquito egg counting tool. Compared to currently available software, EggCountAI performed remarkably well, with significantly increased accuracy, and the ability to discern more complex samples, when processing either micro or macro images. EggCountAI surpassed both ICount and MECVision in performance, achieving an overall percentage accuracy of 98.88% for micro images and am impressive 96.06% accuracy for macro images. The overall accuracy of ICount was 81.71% for micro images and 82.22% for macro images, while the overall accuracy of MECVision was 68.01% for micro images and 51.71% for macro images. In addition to its superior performance, EggCountAI offers additional advantages, including eliminating the need to adjust input parameters for each image individually, batch processing of images, and effectively filtration of undesired impurities.

This deep neural network-based egg counting tool is the one step towards employing AI in studying mosquitoes' behavioural and fitness traits. Developing next generational egg counting tools can be useful in improving vector-borne disease modelling and understanding pathogen transmission.

Animal Ethics Statement.

The experiments for chicken blood collection were conducted under animal ethics guidelines with approval from ACDP Animal Ethics Committee (#ACDP22010).

Acknowledgement:

The authors acknowledge the capabilities of the Australian Centre for Disease Preparedness (grid.413322.5) in undertaking this research, including infrastructure by the National Collaborative Research Infrastructure Strategy (NCRIS).

Availability of data and material:

EggCountAI exe file, installation instructions, and test images are available for free download at below link:

https://drive.google.com/drive/folders/1SdICI1nNeVPuJtdgSUfOol46zoq4LYIj?usp=share_link

Competing interests:

The authors declare no competing interests.

World Health Organization. Global technical strategy for malaria 2016–2030: World Health Organization; 2015.
World Health Organization. The "World malaria report 2019" at a glance 2019 [Available from: https://www.who.int/news-room/feature-stories/detail/world-malaria-report-2019.
World Health Organization. Malaria in children under five 2018 [Available from: https://www.who.int/malaria/areas/high_risk_groups/children/en/.
Brady OJ, Gething PW, Bhatt S, Messina JP, Brownstein JS, Hoen AG, et al. Refining the global spatial limits of dengue virus transmission by evidence-based consensus. 2012.
Grillet ME, Hernández-Villena JV, Llewellyn MS, Paniz-Mondolfi AE, Tami A, Vincenti-Gonzalez MF, et al. Venezuela's humanitarian crisis, resurgence of vector-borne diseases, and implications for spillover in the region. The Lancet Infectious Diseases. 2019;19(5):e149-e61.
Franklinos LH, Jones KE, Redding DW, Abubakar I. The effect of global change on mosquito-borne disease. The Lancet Infectious Diseases. 2019;19(9):e302-e12.
Javed N, Bhatti A, Paradkar PN. Advances in Understanding Vector Behavioural Traits after Infection. Pathogens. 2021;10(11):1376.
Bhatti A, Lee KH, Garmestani H, Lim CP. Emerging Trends in Neuro Engineering and Neural Computation: Springer; 2017.
Gaburro J, Bhatti A, Sundaramoorthy V, Dearnley M, Green D, Nahavandi S, et al. Zika virus-induced hyper excitation precedes death of mouse primary neuron. Virology journal. 2018;15(1):1–13.
Gaburro J, Nahavandi S, Bhatti A. Insects Neural Model: Potential Alternate to Mammals for Electrophysiological Studies. Emerging Trends in Neuro Engineering and Neural Computation: Springer; 2017. p. 119–30.
Sharma A, Parasher H, Singh O, Adak T. Species B of Anopheles culicifacies (Diptera: Culicidae) is reproductively less fit than species A and C of the complex. Acta Tropica. 2009;112(3):316–9.
Hogg J, Thomson M, Hurd H. Comparative fecundity and associated factors for two sibling species of the Anopheles gambiaecomplex occurring sympatrically in The Gambia. Medical and Veterinary Entomology. 1996;10(4):385–91.
Lyimo I, Keegan S, Ranford-Cartwright L, Ferguson H. The impact of uniform and mixed species blood meals on the fitness of the mosquito vector Anopheles gambiae ss: does a specialist pay for diversifying its host species diet? Journal of Evolutionary Biology. 2012;25(3):452–60.
Hall RA, Bielefeldt-Ohmann H, McLean BJ, O'Brien CA, Colmant AM, Piyasena TB, et al. Commensal viruses of mosquitoes: host restriction, transmission, and interaction with arboviral pathogens. Evolutionary Bioinformatics. 2016;12:EBO. S40740.
Livdahl TP, Sugihara G. Non-linear interactions of populations and the importance of estimating per capita rates of change. The Journal of animal ecology. 1984:573–80.
Okogun GR, Anosike JC, Okere A, Nwoke B, Esekhegbe A. Epidemiological implications of preferences of breeding sites of mosquito speciesin Midwestern Nigeria. Annals of Agricultural and Environmental Medicine. 2003;10(2):217–22.
Briegel H. Metabolic relationship between female body size, reserves, and fecundity of Aedes aegypti. Journal of insect physiology. 1990;36(3):165–72.
Gusmão G, Machado SC, Rodrigues MA, editors. A new algorithm for segmenting and counting Aedes aegypti eggs in ovitraps. 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2009: IEEE.
Mello CA, Candeias ALB, Gusmao CM, Rodrigues MA, Portela NM, dos Santos WP. Automatic counting of Aedes aegypti eggs in images of ovitraps: INTECH Open Access Publisher; 2009.
Krieshok G, Torres Gutierrez C. Using computer vision to identify and count mosquito eggs 2020 [Available from: https://abtassociates.github.io/mecvision/.
Gaburro J, Duchemin J-B, Paradkar PN, Nahavandi S, Bhatti A. Assessment of ICount software, a precise and fast egg counting tool for the mosquito vector Aedes aegypti. Parasites & vectors. 2016;9(1):1–9.
Mollahosseini A, Rossignol M, Pennetier C, Cohuet A, Anjos Ad, Chandre F, et al. A user-friendly software to easily count Anopheles egg batches. Parasites & vectors. 2012;5:1–7.
Wan Yussof WNJH, Man M, Hitam MS, Hamid AAKA, Awalludin EA, Bakar WAWA, editors. Wavelet-based auto-counting tool of aedes eggs. Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing; 2018.
Mains JW, Mercer DR, Dobson SL. Digital image analysis to estimate numbers of Aedes eggs oviposited in containers. J Am Mosq Control Assoc. 2008;24(4):496.
da Silva MGNM, Rodrigues MAB, De Araujo R, editors. Aedes aegypti egg counting system. 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2011: IEEE.
Patel R, Patel S. A comprehensive study of applying convolutional neural network for computer vision. International Journal of Advanced Science and Technology. 2020;6(6):2161–74.
Hosang J, Benenson R, Schiele B, editors. Learning non-maximum suppression. Proceedings of the IEEE conference on computer vision and pattern recognition; 2017.
Bravo DT, Lima GA, Alves WAL, Colombo VP, Djogbenou L, Pamboukian SVD, et al. Automatic detection of potential mosquito breeding sites from aerial images acquired by unmanned aerial vehicles. Computers, Environment and Urban Systems. 2021;90:101692.
Garcia PSC, Martins R, Coelho GLLM, Cámara-Chávez G, editors. Acquisition of digital images and identification of Aedes Aegypti mosquito eggs using classification and deep learning. 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI); 2019: IEEE.
Piotr Skalski. Make Sense 2019 [Available from: https://www.makesense.ai.
Schneider CA, Rasband WS, Eliceiri KW. NIH Image to ImageJ: 25 years of image analysis. Nature methods. 2012;9(7):671–5.
He K, Gkioxari G, Dollár P, Girshick R, editors. Mask r-cnn. Proceedings of the IEEE international conference on computer vision; 2017.
Mwingira V, Mboera LE, Dicke M, Takken W. Exploiting the chemical ecology of mosquito oviposition behavior in mosquito surveillance and control: a review. Journal of Vector Ecology. 2020;45(2):155–79.
Fillinger U, Sombroek H, Majambere S, van Loon E, Takken W, Lindsay SW. Identifying the most productive breeding sites for malaria mosquitoes in The Gambia. Malar J. 2009;8:1–14.
Wong J, Stoddard ST, Astete H, Morrison AC, Scott TW. Oviposition site selection by the dengue vector Aedes aegypti and its implications for dengue control. PLoS Negl Trop Dis. 2011;5(4):e1015.
Cailly P, Tran A, Balenghien T, L’Ambert G, Toty C, Ezanno P. A climate-driven abundance model to assess mosquito control strategies. Ecological Modelling. 2012;227:7–17.
Armbruster P, Hutchinson RA. Pupal mass and wing length as indicators of fecundity in Aedes albopictus and Aedes geniculatus (Diptera: Culicidae). Journal of medical entomology. 2002;39(4):699–704.

Download PDF

Version 1

posted

You are reading this latest preprint version

EggCountAI: A Convolutional Neural Network Based Software for Counting of Aedes Aegypti Mosquito Eggs

Status:

Version 1

Abstract

Figures

Introduction

Materials and Methods

Maintenance of the mosquito colony:

Artificial blood feeding and egg collection:

Capturing and processing of images:

Training and Validation:

Programming and computational system:

Manual counting:

Performance evaluation:

Egg estimation using EggCountAI software:

Results

Micro Images:

Macro Images

Comparative Analysis of Accuracy in EggCountAI, ICount, and MECVision:

Micro Images:

Macro Images:

Discussion

Conclusion

Declarations

References

Status:

Version 1