Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Skin Disease Classification Technique Based on Convolutional Neural Network Using Deep Metric Learning

Deep Metric Learning을 활용한 합성곱 신경망 기반의 피부질환 분류 기술

  • 김강민 (조선대학교 컴퓨터공학과) ;
  • 김판구 (조선대학교 컴퓨터공학과) ;
  • 전찬준 (조선대학교 컴퓨터공학과)
  • Received : 2021.08.24
  • Accepted : 2021.12.28
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The skin is the body's first line of defense against external infection. When a skin disease strikes, the skin's protective role is compromised, necessitating quick diagnosis and treatment. Recently, as artificial intelligence has advanced, research for technical applications has been done in a variety of sectors, including dermatology, to reduce the rate of misdiagnosis and obtain quick treatment using artificial intelligence. Although previous studies have diagnosed skin diseases with low incidence, this paper proposes a method to classify common illnesses such as warts and corns using a convolutional neural network. The data set used consists of 3 classes and 2,515 images, but there is a problem of lack of training data and class imbalance. We analyzed the performance using a deep metric loss function and a cross-entropy loss function to train the model. When comparing that in terms of accuracy, recall, F1 score, and accuracy, the former performed better.

피부는 외부 오염으로부터 일차적으로 몸을 보호하는 역할을 한다. 피부병이 발생하게 되면 피부의 보호 기능이 저하되므로 신속한 진단과 처치가 필요하다. 최근 인공지능의 발달로 인해 여러 분야에 기술적용을 위한 연구가 이루어지고 있으며, 피부과에서도 인공지능을 활용해 오진율을 줄여 신속한 치료를 받을 수 있는 환경을 만들기 위한 연구가 진행되고 있다. 종래 연구들의 주된 흐름은 발생 빈도가 낮은 피부질환의 진단이었지만, 본 논문에서는 사람들에게 흔히 발생할 수 있고, 개인이 명확히 판별하기 힘든 티눈과 사마귀를 합성곱 신경망을 통해 분류하는 방법을 제안한다. 사용한 데이터셋은 3개의 클래스로 이루어져 있으며, 총 2,515장의 이미지를 가지고 있다, 학습 데이터 부족과 클래스 불균형 문제가 존재한다. 모델의 학습에는 deep metric 손실 함수와 교차 손실 함수를 이용해 각각 성능을 분석하였으며, 정밀도, 재현율, F1 점수, 정확도의 측면에서 비교한 결과 deep metric 손실 함수에서 더 우수한 성능을 보였다.

Keywords

Acknowledgement

본 연구는 2021년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (NRF-2019R1C1C1011597).

References

  1. M. A. M. Almeida, and I. A. X. Santos, "Classification models for skin tumor detection using texture analysis in medical images," Journal of Imaging, vol. 6, no. 6, Jun., 2020.
  2. V. Ki, and C. Rotstein, "Bacterial skin and soft tissue infections in adults: A review of their epidemiology, pathogenesis, diagnosis, treatment and site of care," Canadian Journal of Infectious Diseases and Medical Microbiology, vol. 19, no. 2, pp. 173-184, Mar., 2008. https://doi.org/10.1155/2008/846453
  3. Z. Cao, T. Simon, S. Wei, and Y. Sheikh, "Realtime multi-person 2D pose estimation using part affinity fields," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291-7299, Jul., 2017.
  4. D. Castelvecchi, "Deep learning boosts google translate tool," Nature News, Sep., 2016.
  5. M. Blaauw, and J. Bonada, "A neural parametric singing synthesizer modeling timbre and expression from natural songs," Applied Sciences, vol. 7, no. 12, Dec., 2017.
  6. L. A. Gatys, A. S. Ecker, and M. Bethge, "Image style transfer using convolutional neural networks," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414-2423, Jul., 2016.
  7. J. Cheng, D. Ni, Y. Chou, J. Qin, C. Tiu, Y. Chang, C. Huang, D. Shen, and C. Chen, "Computer-aided diagnosis with deep learning architecture: Applications to breast lesions in us images and pulmonary nodules in CT scans," Scientific Reports, Apr., 2016.
  8. S. Pereira, A. Pinto, V. Alves, and C. A. Silva, "Brain tumor segmentation using convolutional neural networks in mri images," IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1240-1251, May, 2016. https://doi.org/10.1109/TMI.2016.2538465
  9. M. N. Alam, T. T. K. Munia, K. Tavakolian, F. Vasefi, N. MacKinnon, and R. Fazel-Rezai, "Automatic detection and severity measurement of eczema using image processing," Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1365-1368, Aug., 2016.
  10. R. Sumithra, M. Suhil, and D. S. Guru, "Segmentation and classification of skin lesions for disease diagnosis," Procedia Computer Science, vol. 45 pp. 76-85, Mar., 2015. https://doi.org/10.1016/j.procs.2015.03.090
  11. J. L. Seixas, and R. G. Mantovani, "Decision trees for the detection of skin lesion patterns in lower limbs ulcers," Proceedings of the International Conference on Computational Science and Computational Intelligence (CSCI), pp. 677-681, Dec., 2016.
  12. X. Zhang, S. Wang, J. Liu, and C. Tao, "Towards improving diagnosis of skin diseases by combining deep neural network and human knowledge," BMC Medical Informatics and Decision Making, vol. 18, pp. 69-76, Jul., 2018. https://doi.org/10.1186/s12911-018-0615-9
  13. E. N. Wilmer, C. J. Gustafson, C. S. Ahn, S. A. Davis, S. R. Feldman, and W. W. Huang, "Most common dermatologic conditions encountered by dermatologists and nondermatologists," Cutis, vol. 94, no. 6, pp. 285-292, Dec., 2014.
  14. Y. Liu, A. Jain, C. Eng, D. H. Way, K. Lee, P. Bui, K. Kanada, G. de O. Marinho, J. Gallegos, S. Gabriele, V. Gupta, N. Singh, V. Natarajan, R. H. Wellenhof, G. S. Corrado, L. H. Peng, D. R. Webster, D. Ai, S. J. Huang, R. C. Dunn, and D. Coz, "A deep learning system for differential diagnosis of skin diseases," Nature Medicine vol. 26, pp. 900-908, May, 2020. https://doi.org/10.1038/s41591-020-0842-3
  15. M. Caron, P. Bojanowski, A. Joulin, and M. Douze, "Deep clustering for unsupervised learning of visual features," Proceedings of the European Conference on Computer Vision (ECCV), pp. 132-149, Sep., 2018.
  16. J. E. Engelen, and H. H. Hoos, "A survey on semi-supervised learning", Machine Learning, vol. 15, pp. 373-440, Nov., 2019.
  17. R. C. Prati, G. E. A. P. A. Batista, and M. C. Monard, "Data mining with imbalanced class distributions: concepts and methods," Proceedings of the 4th Indian International Conference on Artificial Intelligence(IICAI-09), pp. 359-376, Dec., 2009.
  18. E. Rendin, R. Alejo, C. Castorena, E. J. Isidro-Ortega, and E. E. Granda-Gutierrez, "Data sampling methods to deal with the big data multi-class imbalance problem," Applied science, vol. 10, Feb., 2020.
  19. N. Japkowicz, and S. Stephen, "The class imbalance problem: A systematic study," Intelligent Data Analysis, vol. 6, no. 5, pp. 429-449, Nov., 2002. https://doi.org/10.3233/ida-2002-6504
  20. I. Tomek, "Two modifications of CNN," IEEE Transactions on Systems, Man, and Cybernetics, vol. 6, no. 11, pp. 769-772, 1976. https://doi.org/10.1109/TSMC.1976.4309452
  21. P. Hart, "The condensed nearest neighbour rule," IEEE Transactions on Information Theory, pp. 515-516, 1968.
  22. D. Wilson, "Asymptotic properties of nearest neighbor rules using edited data," IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-2, pp. 408-420, Jul., 1972. https://doi.org/10.1109/TSMC.1972.4309137
  23. H. He, Y. Bai, E. A. Garcia, and S. Li, "ADASYN: Adaptive synthetic sampling approach for imbalanced learning," IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 1322-1328, Jun., 2008.
  24. N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic minority over-sampling technique," Journal of Artificial Intelligence Research, vol. 16, pp. 321-357, Jun., 2002. https://doi.org/10.1613/jair.953
  25. C. Chang, M. Hsu, E. X. Esposito, and Y. J. Tseng, "Oversampling to overcome overfitting: Exploring the relationship between data set composition, molecular descriptors, and predictive modeling methods," Journal of Chemical Information and Modeling, vol. 53, no. 4, pp. 958-971, Mar., 2013. https://doi.org/10.1021/ci4000536
  26. S. J. Pan, and Q. Yang, "A survey on transfer learning," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct., 2010. https://doi.org/10.1109/TKDE.2009.191
  27. J. Kim, T. Kim, S. Kim, and C. D. Yoo "Edge-labeling graph neural network for few-shot learning," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11-20, Jun., 2019.
  28. W. Jiang, K. Huang, J. Geng and X. Deng, "Multi-Scale Metric Learning for Few-Shot Learning," IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 3, pp. 1091-1102, Mar., 2021. https://doi.org/10.1109/TCSVT.2020.2995754
  29. M. Kaya, and H. S. bilge, "Deep metric learning: A survey," Symmetry, vol. 11, no. 9, Aug., 2019.
  30. F. Schroff, D. Kalenichenko, and J. Philbin. "Facenet: A unified embedding for face recognition and clustering," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815-823, Jun., 2015.
  31. A. Hermans, L. Beyer, and B. Leibe, "In defense of the triplet loss for person re-identification," arXiv Preprint arXiv:1703.07737, 2017.
  32. J. HU, J. Lu, and Y-P. Tan, "Deep metric learning for visual tracking," IEEE Transactions on Circuits and Systems for Video Technology, vol. 26, no. 11, pp. 2056-2068, Nov., 2016. https://doi.org/10.1109/TCSVT.2015.2477936
  33. J. Xie, G. Dai, F. Zhu, L. Shao and Y. Fang, "Deep Nonlinear Metric Learning for 3-D Shape Retrieval," IEEE Transactions on Cybernetics, vol. 48, no. 2, pp. 412-422, Jan., 2018. https://doi.org/10.1109/TCYB.2016.2638924
  34. M. Annarumma and G. Montana, "Deep metric learning for multi-labelled radiographs," Proceedings of the 33rd Annual ACM Symposium on Applied Computing, pp. 34-37, Apr., 2018.
  35. A. Zhong, X. Li, D. Wu, H. Ren, K. Kim, Y. Kim, V. Buch, N. Neumark, B. Bizzo, W. Y. Tak, S. Y. Park, Y. R. Lee, M. K. Kang, J. G. Park, B. S. Kim, W. J. Chung, N. Guo, I. Dayan, M. K. Kalra and Q. Li, "Deep metric learning-based image retrieval system for chest radiograph and its clinical applications in COVID-19," Medical Image Analysis, vol. 70, May, 2021.
  36. R. Hadsell, S. Chopra, and Y. LeCun, "Dimensionality reduction by learning an invariant mapping," Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2006.
  37. H. O. Song, Y. Xiang, S. Jegelka, and S. Savarese "Deep metric learning via lifted structured feature embedding," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4004-4012, Jul., 2016.
  38. 이정덕, "물리적 인자에 의한 피부손상," Journal of Korean Medical Association. vol. 62, pp. 197-201, Apr., 2019. https://doi.org/10.5124/jkma.2019.62.4.197
  39. N. Hameed, A M. Shabut, and M. A. Hossain, "Multi-class skin diseases classification using deep convolutional neural network and support vector machine," Proceedings of the International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA), pp. 1-7, Dec., 2018.
  40. J. Velasco, C. Pascion, J. W. Alberio, J. Apuang, J. Cruz, M. A. Gomez, B. Molina, L. Tuala, A. Thio-ac, R. and J. Jorda, "A smartphone-based skin disease classification using mobilenet CNN," International Journal of Advanced Trends in Computer Science and Engineering, vol. 8, pp. 2632-2637, Oct., 2019.
  41. A. Esteva, B. Kuprel, R. A. Novoa, J. Ko, S. M. Swetter, H. M. Blau, and S. Thrun, "Dermatologist-level classification of skin cancer with deep neural networks," Nature, vol. 542, pp. 115-118, Jan., 2017. https://doi.org/10.1038/nature21056
  42. A. Budhiman, S. Suyanto, and A. Arifianto, "Melanoma cancer classification using resnet with data augmentation," International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), pp. 17-20, Dec., 2019.
  43. L. V. D. Maaten, and G. Hinton, "Visualizing data using t-sne," Journal of Machine Learning Research, vol. 9, no. 11, pp. 2579-2605, Nov., 2008