STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Telecommunication, Switching Systems and Networks Original Research

Classification of Skin Disease Images Using EfficientNetTransfer Learning Technique

  1. B.R. Nikhitha Department of Computer Science Engineering, Sai Vidya Institute of Technology, Haddosiddapura, Bengaluru
  2. Shantakumar B. Patil Department of Computer Science Engineering, Sai Vidya Institute of Technology, Haddosiddapura, Bengaluru
  3. Poornima Gowda Department of Computer Science Engineering, Sai Vidya Institute of Technology, Haddosiddapura, Bengaluru
  4. Ananya M.V. Department of Computer Science Engineering, Sai Vidya Institute of Technology, Haddosiddapura, Bengaluru
  5. Apeksha Belavanaki Department of Computer Science Engineering, Sai Vidya Institute of Technology, Haddosiddapura, Bengaluru
  6. Ushashree P. Department of Computer Science Engineering, Sai Vidya Institute of Technology, Haddosiddapura, Bengaluru

Abstract

Melanomous Skin lesions are among the deadliest kinds of cancer. Despite being a very uncommon skin condition, melanoma is responsible for 75% of cancer-related deaths. Dermatologists perform dermoscopy more commonly than any other procedure. Since it aggravates the skin condition, a dermatologist will be the first to identify it during an inspection. Because this strategy depends on the user's visual perception and experience, it can only be used by highly qualified physicians. These difficulties motivate researchers to create novel methods for recognizing and categorizing skin lesions.Skin diseases present a significant public health challenge globally, necessitating efficient and accurate diagnostic methods for timely treatment. With the advent of deep learning techniques, automated classification of skin disease images has emerged as a promising approach to aid dermatologists in diagnosis. In this study, we propose a novel approach utilizing transfer learning with EfficientNet, a state-of-the-art deep learning architecture, for the classification of skin disease images.

Keywords

References (12)

  1. Litjens Geert, et al. A survey on deep learning in medical image analysis. MedImage Anal. 2017; 42: 60–
  2. Russakovsky O, et al. ImageNet large scale visual recognition challenge. Int J Comput 2015 Dec; 115(3): 211–252.
  3. Ker Justin, et al. Deep learning applications in medical image analysis. IEEE Access. 2017; 6: 9375–
  4. LeCun Y, Bottou L, Bengio Y, Haffner Gradient-based learning applied to document recognition. Proc IEEE. 1998 Nov; 86(11): 2278–2324.
  5. Girshick R, Donahue J, Darrell T, Malik Region-based convolutional networks for accurate object detection and semantic segmentation. IEEE Trans Pattern Anal Mach Intell. 2016 Jan; 38(1): 142–158.
  6. Shin Hoo-Chang, et Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imag. 2016; 35(5): 1285–1298.
  7. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. 1989; 1(4): 541–551.
  8. Roth High-order Markov random fields for low-level vision. PhD Thesis. Rhode: Brown University; 2007.
  9. Jain Viren, Sebastian Natural image denoising with convolutional networks. Proceedings of Advances in Neural Information Processing Systems 21. 2008; 769–776.
  10. Enkhsaikhan M, Liu W, Holden E-J, During Auto-labelling entities in low-resource text: A geological case study. Knowl Inf Syst. 2021 Mar; 63(3): 695–715.
  11. Fang W, Luo H, Xu S, Love PED, Lu Z, Ye Automated text classification of near-misses from safety reports: An improved deep learning approach. Adv Eng Informat. 2020 Apr; 44: 101060.
  12. Gautam Transfer learning for COVID-19 cases and deaths forecast using LSTM network. ISA Trans. 2022 May; 124: 41–56.
Support