Using Deep Learning in Lyme Disease Diagnosis


  • Tejaswi Koduru Thomas Jefferson High School for Science and Technology
  • Edward Zhang Mentor, Thomas Jefferson High School



Lyme, erythema migrans (EM)


Untreated lyme disease can lead to neurological, cardiac, and dermatological complications. Rapid diagnosis of the erythema migrans (EM) rash, a characteristic symptom of Lyme disease, is therefore crucial to early diagnosis and treatment. In this study, we aim to utilize deep learning frameworks including Tensorflow and Keras to create deep convolutional neural networks (DCNN) to detect images of acute Lyme Disease from images of erythema migrans. This study uses a custom database of erythema migrans images of varying quality to train a DCNN capable of classifying images of EM rashes vs non-EM rashes. Images from publicly available sources were mined to create an initial database. Machine based removal of duplicate images was then performed, followed by a thorough examination of all images by a clinician. The resulting database was combined with images of confounding rashes and regular skin, resulting in a total of 683 images. This database was then used to create a DCNN with an accuracy of 93% when classifying images of rashes as EM vs non EM. Finally, this model was converted into a web and mobile application to allow for rapid diagnosis of EM rashes by both patients and clinicians. This tool could be used for patient prescreening prior to treatment and lead to a lower mortality rate from Lyme disease.


Download data is not yet available.

References or Bibliography

Lyme Disease. (n.d.). Center for Disease Control. Retrieved December 26, 2020, from

Lyme Disease Data and Surveillance. (n.d.). Center for Disease Control. Retrieved December 26, 2020, from

Steere, A. C., & Sikland, V. K. (2003, June 12). The Presenting Manifestations of Lyme Disease and the Outcomes of Treatment. The New England Journal of Medicine. Retrieved December 26, 2020, from

Robert B. Nadelman, John Nowakowski, Gilda Forseter, Neil S. Goldberg, Susan Bittker, Denise Cooper, Maria Aguero-Rosenfeld, Gary P. Wormser,The clinical spectrum of early lyme borreliosis in patients with culture-confirmed erythema migrans, The American Journal of Medicine,Volume 100, Issue 5,1996, Pages 502-508, ISSN 0002-9343,

Martin E. Schriefer,Lyme Disease Diagnosis: Serology,Clinics in Laboratory Medicine,Volume 35, Issue 4,2015,Pages 797-814,ISSN 0272-2712,ISBN 9780323402545,

Shapiro, E. D. (2014, May 1). Lyme Disease. The New England Journal of Medicine. Retrieved December 26, 2020, from

Biesiada, G., Czepiel, J., Leśniak, M. R., Garlicki, A., & Mach, T. (2012). Lyme disease: review. Archives of medical science : AMS, 8(6), 978–982.

Chinmoy Bhate, Robert A. Schwartz,Lyme disease: Part I. Advances and perspectives,Journal of the American Academy of Dermatology,Volume 64, Issue 4,2011,Pages 619-636,ISSN 0190-9622,

Lyme Disease Rashes and Look-alikes. (n.d.). Center for Disease Control. Retrieved December 26, 2020, from

Lipsker D, Lieber-Mbomeyo A, Hedelin G. How Accurate Is a Clinical Diagnosis of Erythema Chronicum Migrans? Prospective Study Comparing the Diagnostic Accuracy of General Practitioners and Dermatologists in an Area Where Lyme Borreliosis Is Endemic. Arch Dermatol. 2004;140(5):620–621. doi:10.1001/archderm.140.5.620

Draelos, R., Ph.D. (2019, April 13). The History of Convolutional Neural Networks. Glassboxmedicine. Retrieved December 26, 2020, from

Čuk, E., Gams, M., Možek, M., Strle, F., Čarman, V. M., & Tasič, J. F. (2014). Supervised visual system for recognition of erythema migrans, an early skin manifestation of lyme borreliosis. Strojniški vestnik-Journal of Mechanical Engineering, 60(2), 115-123.

Philippe M. Burlina, Neil J. Joshi, Elise Ng, Seth D. Billings, Alison W. Rebman, John N. Aucott,Automated detection of erythema migrans and other confounding skin lesions via deep learning,Computers in Biology and Medicine, Volume 105, 2019, Pages 151-156, ISSN 0010-4825,

Treatment for erythema migrans. (n.d.). Centers for Disease Control and Prevention. Retrieved November 3, 2020, from

Treatment for Ringworm. (n.d.). Centers for Disease Control and Prevention. Retrieved November 13, 2020, from

Pityriasis rosea. (2020, August 5). Mayo Clinic.]

Yamashita, R., Nishio, M., Do, R.K.G. et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging 9, 611–629 (2018).

S. Albawi, T. A. Mohammed and S. Al-Zawi, "Understanding of a convolutional neural network," 2017 International Conference on Engineering and Technology (ICET), Antalya, 2017, pp. 1-6, doi: 10.1109/ICEngTechnol.2017.8308186.

Progressive Web App for Offline Image Classification with TensorFlow.js [Video]. (2019, October 4). Youtube.

Train and deploy on-device image classification model with AutoML Vision in ML Kit.(n.d.). codelabs.

Zoph, B., Vasudevan, V., & Le, Q. V. (2018). Learning Transferable Architectures for Scalable Image Recognition (J. Shlens, Ed.). Cornell University.

Wolfram neural net repository. (2019, July 17).,between%20the%20thin%20bottleneck%20layers

He, K., hang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR 2016.

About ImageNet. (n.d.). ImageNet.

M. I. Ul Haque and D. Valles, "Facial Expression Recognition Using DCNN and Development of an iOS App for Children with ASD to Enhance Communication Abilities," 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York City, NY, USA, 2019, pp. 0476-0482, doi: 10.1109/UEMCON47517.2019.8993051.

Jayawant N. Mandrekar, Receiver Operating Characteristic Curve in Diagnostic Test Assessment,

Journal of Thoracic Oncology, Volume 5, Issue 9, 2010, Pages 1315-1316, ISSN 1556-0864,



How to Cite

Koduru, T., & Zhang, E. (2021). Using Deep Learning in Lyme Disease Diagnosis. Journal of Student Research, 10(4).



HS Research Projects