Advertisement

Transfer Learning Model for Detecting Early Stage of Prurigo Nodularis

  • Dhananjay KalbandeEmail author
  • Rithvika Iyer
  • Tejas Chheda
  • Uday Khopkar
  • Avinash Sharma
Conference paper
  • 27 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1087)

Abstract

Skin diseases are becoming increasingly prevalent all over the world due to a multitude of factors including disparity in income groups, lack of access to primary health care, poor levels of hygiene, varied climate, and different cultural factors.The ratio of dermatologists to the number of people affected is very low, and hence, there is a need for expedited and accurate diagnosis of skin diseases. Prurigo Nodularis can be a bothersome-to-enervating disease and its treatment requires a multifaceted approach depending on the severity and underlying etiology of the disease. Often, once patients are diagnosed with Prurigo Nodularis, they are also advised a complete work-up to rule out any underlying systemic disease. Knowing the advantages of early detection of the disease to facilitate quick and suitable treatment, this paper proposes the use of deep learning for accurate and early detection of Prurigo Nodularis. Different architectures of convolutional neural networks were used on the dataset of diseased skin images and the results were compared to ascertain the best method. Thus, with a combination of transfer learning on the image dataset and applying the extra tree classifier on the symptoms dataset, we were able to correctly predict the occurrence of Prurigo Nodularis with an accuracy of around 96%.

Keywords

Transfer learning Machine learning Feature extraction 

Notes

Acknowledgements

We would like to express our heartfelt gratitude to Department of Skin and V.D of Seth G. S. Medical College and KEM Hospital, Mumbai. The images provided by the hospital were vital in training our models and corroborating our findings. Also, working with data which we know is correct helps us in asserting the accuracy we have achieved. We are grateful to the Institutional Ethics Committee (IEC-II) of Seth G. S. Medical College and KEM Hospital, Mumbai for reviewing our work with reference to ethical standards. We are also thankful to Dr. Nazia Suhail, Dr. Jayati Dave, Department of Skin and V.D of Seth G. S. Medical College and KEM Hospital, Mumbai and Dr. Mithali Jage, Lokmanya Tilak Municipal Medical College. Without their constant support, we would not have been able to test the system so quickly.

References

  1. 1.
    A. Damayanti, A.B. Pratiwi, Miswanto, Epilepsy detection on EEG data using backpropagation, firefly algorithm and simulated annealing, in 2016 2nd International Conference on Science and Technology-Computer (ICST) (2016), pp. 167–171Google Scholar
  2. 2.
    B. Harangi, A. Baran, A. Hajdu, Classification of skin lesions using an ensemble of deep neural networks, in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (2018), pp. 2575–2578Google Scholar
  3. 3.
    P.R. Hegde, M.M. Shenoy, B.H. Shekar, Comparison of machine learning algorithms for skin disease classification using color and texture features, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (2018), pp. 1825–1828Google Scholar
  4. 4.
    N.J. Higham, Computing a nearest symmetric positive semidefinite matrix. Linear Alg. Appl. 103, 103–118 (1988)MathSciNetCrossRefGoogle Scholar
  5. 5.
    K.A. Holbrook, L.T. Smith, S. Elias, Prenatal diagnosis of genetic skin disease using fetal skin biopsysamples. Arch. Dermatol. 129(11), 1437–1454 (1993)CrossRefGoogle Scholar
  6. 6.
    C. Korfitis, S. Gregoriou, C. Antoniou, A.D. Katsambas, D. Rigopoulos, Skin biopsy in the context of dermatological diagnosis: a retrospective cohort study. Dermatol. Res. Pract. 734906 (2014)Google Scholar
  7. 7.
    M.A.E. Muhammed, A.A. Ahmed, T.A. Khalid, Benchmark analysis of popular imagenet classification deep CNN architectures, in 2017 International Conference On Smart Technologies For Smart Nation (SmartTechCon), Aug 2017, pp. 902–907Google Scholar
  8. 8.
    P. Mullangi, S.R. Yarravarapu, P. Kotipalli, in Texture and Clustering-based Skin Disease Classification (2018), pp. 103–110Google Scholar
  9. 9.
    D.H. Murphree, C. Ngufor, Transfer learning for melanoma detection: participation in ISIC 2017 skin lesion classification challenge (2017). arXiv:1703.05235
  10. 10.
    J. Sachdev, S. Shekhar, S. Indu, Melanoma screening using deep neural networks, in 2018 3rd International Conference for Convergence in Technology (I2CT), April 2018, pp. 1–5Google Scholar
  11. 11.
    L. Shao, F. Zhu, X. Li, Transfer learning for visual categorization: a survey. IEEE Trans. Neural Netw. Learn. Syst. 26(5), 1019–1034 (2015)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Dhananjay Kalbande
    • 1
    • 2
    Email author
  • Rithvika Iyer
    • 1
  • Tejas Chheda
    • 1
  • Uday Khopkar
    • 3
  • Avinash Sharma
    • 4
  1. 1.Department of Computer EngineeringSardar Patel Institute of TechnologyMumbaiIndia
  2. 2.Skinzy Software Solutions, SPTBIMumbaiIndia
  3. 3.Department of DermatologySeth GS Medical College & KEM HospitalMumbaiIndia
  4. 4.Maharishi Markandeshwar Engineering CollegeAmbalaIndia

Personalised recommendations