Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

SCLC-Edge Detection Algorithm for Skin Cancer Classification

피부암 병변 분류를 위한 SCLC-Edge 검출 알고리즘

  • June-Young Park (Department of Convergence Healthcare Medicine, Graduate School of Ajou University) ;
  • Chang-Min Kim (Department of Information Communication Software Engineering, Sangji University) ;
  • Roy C. Park (Department of Information Communication Software Engineering, Sangji University)
  • 박준영 (아주대학교 의과대학 대학원 융합의과학과대학교) ;
  • 김창민 (상지대학교 정보통신소프트웨어공학과) ;
  • 박찬홍 (상지대학교 정보통신소프트웨어공학과)
  • Received : 2022.11.08
  • Accepted : 2022.12.13
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Skin cancer is one of the most common diseases in the world, and the incidence rate in Korea has increased by about 100% over the past five years. In the United States, more than 5 million people are diagnosed with skin cancer every year. Skin cancer mainly occurs when skin tissue is damaged for a long time due to exposure to ultraviolet rays. Melanoma, a malignant tumor of skin cancer, is similar in appearance to Atypical melanocytic nevus occurring on the skin, making it difficult for the general public to be aware of it unless secondary signs occur. In this paper, we propose a skin cancer lesion edge detection algorithm and a deep learning model, CRNN, which performs skin cancer lesion classification for early detection and classification of these skin cancers. As a result of the experiment, when using the contour detection algorithm proposed in this paper, the classification accuracy was the highest at 97%. For the Canny algorithm, 78% was shown, 55% for Sobel, and 46% for Laplacian.

피부암은 세계에서 가장 흔한 질병 중 하나로 국내에선 발병률이 지난 5년 동안 약 100%가 증가했고 미국에선 매년 500만여 명이 피부암을 진단받는다. 피부암은 주로 자외선의 노출로 피부 조직이 오랜 시간 손상되면서 발생하게 된다. 피부암의 악성종양인 흑색종은 피부 위에서 발생하는 멜라닌 세포 모반과 생김새가 유사해 2차 징후가 발생하지 않는 한 일반인이 자각하기 어려운 점이 있다. 본 논문에서는 이러한 피부암의 조기 발견과 분류를 위해 피부암 병변 윤곽선 검출 알고리즘과 피부암 병변 분류를 수행하는 딥러닝 모델인 CRNN을 제안한다. 실험 결과 본 논문에서 제안하는 윤곽선 검출 알고리즘을 이용할 시 분류 정확도가 97%로 가장 높은 정확도를 보였고 Canny 알고리즘의 경우 78%를 보였고 Sobel의 경우 55%, Laplacian의 경우 46%를 보였다.

Keywords

Acknowledgement

This research was funded by a National Research Foundation of Korea (NRF) grant funded by the Korea government (2022R1F1A1064231).

References

  1. D. H. Shin, K. Chung, and R. C. Park, "Detection of Emotion Using Multi-Block Deep Learning in a Self-Management Interview App," Appli. Sci., vol. 9, no. 22, pp. 4830-4845, Nov. 2019. https://doi.org/10.3390/app9224830
  2. C. M. Kim, E. Hong, K. Chung, R. Park, "Health Risk Detection and Classification Model Using Multi-Model-Based Image Channel Expansion and Visual Pattern Standardization,"Appli. Sci., Vol. 11, No. 8, pp. 8621-8620, Sep. 2021.
  3. C. M. Kim, K. Chung, R. Park, "Anomaly detection model of mammography using YOLOv4-based histogram,"Pers. Ubiquitous Comput., July 2021, Doi: https://doi.org/10.1007/s00779-021-01598-1.
  4. C. M. Kim, E. Hong, R. Park, "Chest X-Ray Outlier Detection Model Using Dimension Reduction and Edge Detection,"IEEE Access, Vol. 9, pp. 86096-86106, Jun., 2021. https://doi.org/10.1109/ACCESS.2021.3086103
  5. C. M. Kim, E. Hong, R. Park, "Breast Mass Classification using the eLFA Algorithm based on CRNN Deep Learning Model,"IEEE Access, Vol. 197312-197323, Oct., 2020.
  6. C. M. Kim, E. Hong, K. Chung, R. Park,"Line-Segment Feature Analysis Algorithm Using Input Dimensionality Reduction for Handwritten Text Recognition,"Appli. Sci., Vol. 10, No. 19, pp. 6904-6921. Oct. 2020. https://doi.org/10.3390/app10196904
  7. H. Yoo, S. Y. Han, K. Y. Chung, "A Frequency Pattern Mining Model Based on Deep Neural Network for Real-Time Classification of Heart Conditions," Healthcare, vol. 8, Issue 3, pp.234-252, July, 2020. https://doi.org/10.3390/healthcare8030234
  8. J. W. Baek, K. Chung, "Context Deep Neural Network Model for Predicting Depression Risk Using Multiple Regression," IEEE Access, vol. 8, pp. 18171-18181, Jan. 2020. https://doi.org/10.1109/ACCESS.2020.2968393
  9. J. C. Kim, K. Chung, "Multi-Modal Stacked Denoising Autoencoder for Handling Missing Data in Healthcare Big Data," IEEE Access, vol. 8, pp.104933-104943, May, 2020. https://doi.org/10.1109/ACCESS.2020.2997255
  10. C. M. Kim, E. Hong, K. Chung, R. Park, "Driver Facial Expression Analysis Using LFA-CRNN-Based Feature Extraction for Health-Risk Decisions," Appl. Sci., vol. 10, pp. 2956-2974, Apr. 2020. https://doi.org/10.3390/app10082956
  11. J. C. Kim, K. Chung, "Hybrid Multi-Modal Deep Learning using Collaborative Concat Layer in Health Bigdata," IEEE Access, vol. 8, pp.192469-192480, Oct. 2020. https://doi.org/10.1109/ACCESS.2020.3031762