Recognition of Viral Infections in Skin Conditions


Prahlad G Menon, PhD, Opu Labs Inc.


Skin rashes appear during febrile illnesses and may be caused by various infectious diseases, including viral infection.  We hypothesize that the time of onset of symptoms manifesting on the skin surface and the characteristics of the rash itself viz. its morphology, location, distribution, etc. in addition to a given patient’s history of specific underlying diseases could be helpful in expediting a clinical diagnosis of specific viral infections. However, the characterization of the etiology of atypical exanthems remains a complex task. We propose to tackle this task of exanthem classification using a novel image-based classification approach underpinned on novel neural network architectures, preceded by custom image-processing pipelines implementing prior image de-noising and region-of-interest segmentation.   Our first target for classification is the maculopapular rash [1] – the most common type of rash in a viral infection – as well as related Koplik spots, livedoids, cutis marmorata, perniosis/chillblains and residual brown skin, which all may be correlated with the outbreak of Coronavirus Disease 2019 (COVID19).   Per recent reports, we will also attempt to classify the petechiae rash that has been found in some COVID19 patients [2], similar to the viral rash which manifests with dengue fever.

Keywords:  Skin Rashes, Febrile Illness, Infectious Diseases, COVID19, Viral Infection 


  1. Wiwanitkit, V., 2020. COVID-19 can present with a rash and be mistaken for Dengue. Journal of the American Academy of Dermatology.
  2. Behnam M, Dey A, Gambell T, and Talwar V. 2020. COVID-19: Overcoming supply shortages for diagnostic testing. McKinsey & Company, July 15. products/our-insights/covid-19-overcoming-supply-shortages-for-diagnostic-testing
  3. Weaver C, and Balhaus R. 2020. Coronavirus testing hampered by disarray, shortages, backlogs. The Wall Street Journal, April 19. backlogs-11587328441
  4. Slabodkin G. 2020. Labs warn COVID-19 testing demand will soon top capacity as new hotspots emerge. MedTechDive, June 29. capacity-hotspots-new-surge/580690/
  5. Recalcati S. 2020. Cutaneous manifestations in COVID-19: a first perspective. Journal of the European Academy of Dermatology and Venereology: JEADV, 34(5), e212–e213.
  6. Joob B, Wiwanitkit V. 2020. COVID-19 can present with a rash and be mistaken for dengue. Journal of the American Academy of Dermatology, 82(5), e177.
  7. Hay RJ. 2020. A viral rash: the impact of COVID-19 infection on the skin. British Journal of Dermatology, 183(1), 1–2 (July 1).
  8. Galván Casas C, Català A, Carretero Hernández G, et al. 2020. Classification of the cutaneous manifestations of COVID-19: a rapid prospective nationwide consensus study in Spain with 375 cases. British Journal of Dermatology 183, 71-7.
  9. Potekaev NN, Zhukova OV, Protsenko DN, et al. 2020. Clinical characteristics of dermatologic manifestations of COVID-19 infection: case series of 15 patients, review of literature, and proposed etiological classification. International Journal of Dermatology, 59(8), 1000–1009.
  10. Kang JH. 2015. Febrile illness with skin rashes. Infection & Chemotherapy, 47(3),155–166.
  11. Guo J, Menon PG. 2015. Feature based classification of melanoma from skin images. In ASME International Mechanical  Engineering  Congress  and  Exposition  (Vol.  57380,  p.  V003T03A083). American  Society  of Mechanical Engineers.
  12. Albahri OS, Zaidan AA, Albahri AS, et al. 2020. Systematic review of artificial intelligence techniques in the detection and classification of COVID-19 medical images in terms of evaluation and benchmarking: taxonomy analysis, challenges, future solutions and methodological aspects. Journal of Infection and Public Health,
  13. Imran A, Posokhova I, Qureshi HN, et al. AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app. Informatics in Medicine Unlocked, 20, 100378.
  14. Rao ASS, and Vazquez JA. 2020. Identification of COVID-19 can be quicker through artificial intelligence framework using a mobile phone-based survey in the populations when cities/towns are under quarantine. Infection Control & Hospital Epidemiology, 41(7), 826–830 (March).
  15. Liu Y, Jain A, Eng C, et al. 2020. A deep learning system for differential diagnosis of skin diseases. Nature Medicine, 1–9.
  16. Szegedy C, Vanhoucke V, Ioffe S, et al. 2015. Rethinking the inception architecture for computer vision. Open access version: openaccess/content_cvpr_2016/papers/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.pdf
  17. He K, Zhang X, Ren S, et al. 2016. Identity mappings in deep residual networks. Microsoft Research.
  18. Sandler M, Howard A, Zhu M, et  al. 2018. MobileNetV2: Inverted Residuals and Linear Bottleneck.
  19. Kinyanjui NM, Odonga T, Cintas C, et al. 2019. Estimating skin tone and effects on classification performance in dermatology datasets. NeurIPS 2019 Workshop on Fair ML for Health, Vancouver, Canada. datasets


© Opu Labs, Inc, 2018. Privacy Policy | Website Terms of Use

The Opu name, the Opu logo and all related names, logos, product and service names, designs and slogans are trademarks of Opu Labs, Inc. or its affiliates or licensors. The Terms of Use permit you to use this Site for your personal, non-commercial use only.