Skip to main content

Using convolutional neural networks for tick image recognition – a preliminary exploration

Abstract

Smartphone cameras and digital devices are increasingly used in the capture of tick images by the public as citizen scientists, and rapid advances in deep learning and computer vision has enabled brand new image recognition models to be trained. However, there is currently no web-based or mobile application that supports automated classification of tick images. The purpose of this study was to compare the accuracy of a deep learning model pre-trained with millions of annotated images in Imagenet, against a shallow custom-build convolutional neural network (CNN) model for the classification of common hard ticks present in anthropic areas from northeastern USA. We created a dataset of approximately 2000 images of four tick species (Ixodes scapularis, Dermacentor variabilis, Amblyomma americanum and Haemaphysalis sp.), two sexes (male, female) and two life stages (adult, nymph). We used these tick images to train two separate CNN models – ResNet-50 and a simple shallow custom-built. We evaluated our models’ performance on an independent subset of tick images not seen during training. Compared to the ResNet-50 model, the small shallow custom-built model had higher training (99.7%) and validation (99.1%) accuracies. When tested with new tick image data, the shallow custom-built model yielded higher mean prediction accuracy (80%), greater confidence of true detection (88.7%) and lower mean response time (3.64 s). These results demonstrate that, with limited data size for model training, a simple shallow custom-built CNN model has great prospects for use in the classification of common hard ticks present in anthropic areas from northeastern USA.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3

References

  • Adrion Emily R, Aucott John, Lemke Klaus W, Weiner Jonathan P (2015) Health care costs, utilization and patterns of care following Lyme disease. PloS One 10:e0116767

    Article  Google Scholar 

  • Aik LE, Hong TW, Junoh AK (2006) A new formula to determine the optimal dataset size for training neural networks. ARPN J Eng Appl Sci 14:52–61

    Google Scholar 

  • Hadley A (2020) CombineZP 1.0 Processes stacks of digital image files. https://combinezp.software.informer.com/. Accessed 22 July

  • AppAdvice LLC (2020) TickID by NC State University. https://appadvice.com/game/app/tickid/531348104. Accessed 13 April

  • Bhatt S (2019) Understanding the basics of CNN with image classification. https://becominghuman.ai/understanding-the-basics-of-cnn-with-image-classification-7f3a9ddea8f9. Accessed 17 Aug

  • Staake J (Birds & Blooms) (2020) 5 Birding apps to give your skills a boost. https://www.birdsandblooms.com/birding/birding-basics/5-birding-apps/. Accessed 22 June

  • Bron GM, Fenelon H, Paskewitz SM (2021a) Assessing recognition of the vector of lyme disease using resin-embedded specimens in a lyme endemic area. J Med Entomol 58:866–872

    Article  Google Scholar 

  • Bron Gebbiena M, del Pilaernandez Maria, Bartholomay Lyric C, Diuasser Maria A, Paskewitz Susan M, Jean Tsao I (2021) Comment on Eisen and Eisen (2020) benefits and drawbacks of citizen science to complement traditional data gathering approaches for medically important hard ticks (acari: ixodidae) in the United States’ regarding the tick app and research-based citizen science. J Med Entomol 58:991–993

    Article  Google Scholar 

  • Clifford CM, Anastos G (1960) The use of chaetotaxy in the identification of larval ticks (Acarina: Ixodidae). J Parasitol 46:567–578

    CAS  Article  Google Scholar 

  • Columbia University, University of Maryland, and Smithsonian Institution (2011) Leafsnap: an electronic field guide. http://leafsnap.com/about/. Accessed 22 June

  • Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248–255. Ieee.

  • Deng Li, Yu D (2014) Deep learning: methods and applications. FNT Signal Proc 7:197–387

    Article  Google Scholar 

  • Dergousoff SJ, Chilton NB (2007) Differentiation of three species of ixodid tick, Dermacentor andersoni, D. variabilis and D. albipictus, by PCR-based approaches using markers in ribosomal DNA. Mol Cell Probes 21:343–348

    CAS  Article  Google Scholar 

  • Diuk-Wasser MA, Gatewood AG, Roberto Cortinas M, Yaremych-Hamer S, Tsao J, Uriel Kitron G, Hickling JSB, Walker E, Piesman J (2014) Spatiotemporal patterns of host-seeking Ixodes scapularis nymphs (Acari: Ixodidae) in the United States. J Med Entomol 43:166–176

    Article  Google Scholar 

  • Dreiseitl S, Binder M, Hable K, Kittler H (2009) Computer versus human diagnosis of melanoma: evaluation of the feasibility of an automated diagnostic system in a prospective clinical trial. Melanoma Res 19:180–184

    Article  Google Scholar 

  • Dwivedi P (2019) Understanding and coding a ResNet in Keras. https://towardsdatascience.com/understanding-and-coding-a-resnet-in-keras-446d7ff84d33. Accessed 17 Aug

  • Eisen Lars, Eisen Rebecca J (2020) Benefits and drawbacks of citizen science to complement traditional data gathering approaches for medically important hard ticks (acari: ixodidae) in the United States. J Med Entomol. https://doi.org/10.1093/jme/tjaa165

    Article  PubMed  Google Scholar 

  • Fernandez Maria P, Bron Gebbiena M, Kache Pallavi A, Larson Scott R, Maus Adam, Gustafson Jr David, Tsao Jean I, Bartholomay Lyric C, Paskewitz Susan M, Diuk-Wasser Maria A (2019) Usability and feasibility of a smartphone app to assess human behavioral factors associated with tick exposure (the tick app): quantitative and qualitative study. JMIR mHealth and uHealth 7:769

    Article  Google Scholar 

  • Frid-Adar M, Klang E, Amitai M, Goldberger J, Greenspan H (2018) Synthetic data augmentation using GAN for improved liver lesion classification. In 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), 289–293. IEEE.

  • Ginsberg HS, Stafford III KC (2005) Management of ticks and tick‐borne diseases. Tick‐Borne Diseases of Humans,65–86.

  • Google (2020) Google play – apps. https://play.google.com/store. Accessed 24 June

  • Hagberg A, Swart P, Chult DS (2008) Exploring network structure, dynamics, and function using NetworkX. In: Los Alamos National Lab.(LANL), Los Alamos, NM (United States).

  • He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, 1026–1034.

  • He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.

  • Hoogstraal H (1979) The epidemiology of tick-borne Crimean-Congo hemorrhagic fever in Asia Europe, and Africa. J Med Entomol 15:307–417

    CAS  Article  Google Scholar 

  • Huh M, Agrawal P, Efros AA (2016) What makes ImageNet good for transfer learning?, arXiv preprint arXiv:1608.08614.

  • Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167.

  • Justus D, Brennan J, Bonner S, McGough AS (2018) Predicting the computational cost of deep learning models. In: 2018 IEEE international conference on big data (Big Data), 3873–3882. IEEE.

  • Keirans JE, Durden LA (1998) Illustrated key to nymphs of the tick genus Amblyomma (Acari: Ixodidae) found in the United States. J Med Entomol 35:489–495

    CAS  Article  Google Scholar 

  • Keirans JE, Litwak TR (1989) Pictorial key to the adults of hard ticks, family Ixodidae (Ixodida: Ixodoidea), east of the Mississippi River. J Med Entomol 26:435–448

    CAS  Article  Google Scholar 

  • Kopsco HL, Duhaime RJ, Mather TN (2021) Assessing public tick identification ability and tick bite riskiness using passive photograph-based crowdsourced tick surveillance. J Med Entomol 58:837–846

    Article  Google Scholar 

  • Kopsco HL, Xu G, Luo C-Y, Rich SM, Mather TN (2019) Crowdsourced photographs as an effective tool for large-scale passive tick surveillance. In: Entomology 2019. ESA.

  • Kopsco HL, Guang Xu, Luo C-Y, Rich SM, Mather TN (2020) Crowdsourced photographs as an effective method for large-scale passive tick surveillance. J Med Entomol 57:1955–1963

    Article  Google Scholar 

  • Krizhevsky A, Sutskever I, and Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, 1097–1105.

  • Lawrence S, Lee Giles C, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Networks 8:98–113

    CAS  Article  Google Scholar 

  • LivLyme Foundation (n.d.) TickTracker.. https://ticktracker.com/. Accessed 11 June

  • Madison-Antenucci S, Kramer LD, Gebhardt LL, Kauffman E (2020) Emerging tick-borne diseases. Clin Microbiol Rev 33:e00083-e118

    CAS  Article  Google Scholar 

  • Malvehy J, Hauschild A, Curiel-Lewandrowski C, Mohr P, Hofmann-Wellenhof R, Motley R, Berking C, Grossman D, Paoli J, Loquai C (2014) Clinical performance of the Nevisense system in cutaneous melanoma detection: an international, multicentre, prospective and blinded clinical trial on efficacy and safety. Br J Dermatol 171:1099–1107

    CAS  Article  Google Scholar 

  • Marcel S, Rodriguez Y (2010) Torchvision the machine-vision package of torch. In: Proceedings of the 18th ACM international conference on Multimedia, 1485–1488.

  • Mead PS (2015) Epidemiology of Lyme disease. Infect Dis Clin 29:187–210

    Article  Google Scholar 

  • Mediannikov O, Fenollar F (2014) Looking in ticks for human bacterial pathogens. Microb Pathog 77:142–148

    CAS  Article  Google Scholar 

  • Monheit G, Cognetta AB, Ferris L, Rabinovitz H, Gross K, Martini M, Grichnik JM, Mihm M, Prieto VG, Googe P (2011) The performance of MelaFind: a prospective multicenter study. Arch Dermatol 147:188–194

    Article  Google Scholar 

  • Nicholson WL, Sonenshine DE, Noden BH, Brown RN (2019) Ticks (Ixodida). In: Medical and veterinary entomology (Elsevier), pp 603–672

  • Nieto NC, Porter WT, Wachara JC, Lowrey TJ, Martin L, Motyka PJ, Salkeld DJ (2018) Using citizen science to describe the prevalence and distribution of tick bite and exposure to tick-borne diseases in the United States. PloS One 13:e0199644

    Article  Google Scholar 

  • Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, 8026–8037.

  • Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning, arXiv preprint arXiv:1712.04621.

  • Porter WT, Motyka PJ, Wachara J, Barrand ZA, Hmood Z, McLaughlin M, Pemberton K, Nieto NC (2019) Citizen science informs human-tick exposure in the Northeastern United States. Int J Health Geogr 18:9

    Article  Google Scholar 

  • Rahman MK, Azad A (2019) Evaluating the Community Structures from Network Images Using Neural Networks. In: International conference on complex networks and their applications, 866–878. Springer.

  • Ray SF (2002) Applied Photographic Optics, 3rd edn. Focal Press, Oxford, UK

    Book  Google Scholar 

  • Robitaille TP, Tollerud EJ, Greenfield P, Droettboom M, Bray E, Aldcroft T, Davis M, Ginsburg A, Price-Whelan AM, Kerzendorf WE (2013) Astropy: a community python package for astronomy. Astron Astrophys 558:A33

    Article  Google Scholar 

  • Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, 234–241. Springer.

  • Saha S (2018) A comprehensive guide to convolutional neural networks — the ELI5 way. https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53. Accessed 17 Aug

  • Sonenshine DE, Roe RM (eds) (2014) External and internal anatomy of ticks. In: Biology of ticks, vol 1, 2nd edn. Oxford University Press, Oxford, UK, pp 74–98

    Google Scholar 

  • Stafford KC, Cartter ML, Magnarelli LA, Ertel S-H, Mshar PA (1998) Temporal correlations between tick abundance and prevalence of ticks infected with Borrelia burgdorferi and increasing incidence of Lyme disease. J Clin Microbiol 36:1240–1244

    Article  Google Scholar 

  • Statista (2019) Number of smartphone users in the United States from 2018 to 2024 (in millions). https://www.statista.com/statistics/201182/forecast-of-smartphone-users-in-the-us/#:~:text=Smartphone%20users%20in%20the%20United%20States%202018%2D2024&text=This%20statistic%20shows%20the%20number,estimated%20to%20reach%20275.66%20million.&text=Advances%20in%20telecommunication%20technology%20have%20been%20significant%20in%20recent%20years. Accessed 8 Dec

  • Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 1–9.

  • Szegedy C, Vanhoucke V, Ioffe S, Shlens J, and Wojna Z ( 2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2818–2826.

  • Taigman Y, Yang M, Ranzato M, Wolf L (2014) Deepface: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 1701–1708.

  • The University of Georgia-Center for Invasive Species and Ecosystem. 2020. Early detection & distribution mapping system (EDDMapS). https://www.eddmaps.org/alberta/. Accessed 15 Sept

  • TickCheck.com (2021) TickCheck Tick ID - free tick identification & information. https://www.tickcheck.com/info/app. Accessed 11 June

  • Tschandl P, Codella N, Akay BN, Argenziano G, Braun RP, Cabo H, Gutman D, Halpern A, Helba B, Hofmann-Wellenhof R (2019) Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. Lancet Oncol 20:938–947

    Article  Google Scholar 

  • US CDC (United States Centers for Disease Control and Prevention) (2019) Tickborne Diseases of the United States. https://www.cdc.gov/ticks/tickbornediseases/. Accessed 11 June

  • US CDC (United States Centers for Disease Control and Prevention) (2020) Guide to the Surveillance of Metastriate Ticks (Acari: Ixodidae) and their Pathogens in the United States. https://www.cdc.gov/ticks/pdfs/Tick_surveillance-P.pdf. Accessed 4 Oct

  • Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, Burovski E, Peterson P, Weckesser W, Bright J (2020) SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 17:261–272

    CAS  Article  Google Scholar 

  • Wang H-H, Grant WE, Teel PD, Lohmeyer KH, Adalberto A, de León P (2020) Enhanced biosurveillance of high-consequence invasive pests: southern cattle fever ticks, Rhipicephalus (Boophilus) microplus, on livestock and wildlife. Parasit Vectors 13:1–13

    Article  Google Scholar 

  • Wilson JG, Kinzer DR, Sauer JR, Hair JA (1972) Chemo-attraction in the lone star tick (Acarina: Ixodidae): i response of different developmental stages to carbon dioxide administered via traps. J Med Entomol 9:245–252

    CAS  Article  Google Scholar 

  • Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network, arXiv preprint arXiv:1505.00853.

  • Zhang X, Chen X, Yao L, Ge C, Dong M (2019) Deep neural network hyperparameter optimization with orthogonal array tuning. In: International conference on neural information processing, 287–295. Springer.

  • Zhang X, Zhao J, LeCun Y (2015) Character-level convolutional networks for text classification. In: Advances in neural information processing systems, 649–657.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Oghenekaro Omodior.

Ethics declarations

Conflict of interest

The authors declare no real or perceived conflict of interest. No human subjects were used in this study. This project was supported by the Environmental Resilience Institute (ERI), funded by Indiana University’s Prepared for Environmental Change (PfEC) Grand Challenge initiative.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Omodior, O., Saeedpour-Parizi, M.R., Rahman, M.K. et al. Using convolutional neural networks for tick image recognition – a preliminary exploration. Exp Appl Acarol 84, 607–622 (2021). https://doi.org/10.1007/s10493-021-00639-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10493-021-00639-x

Keywords

  • Convolutional neural network
  • Tick-borne diseases
  • Ixodes scapularis
  • Amblyomma americanum
  • Northeastern United States