본문 바로가기
KERD
논문KCI 등재

반려동물 피부영상에서의 질환 검출을 위한 딥러닝 기반 털 영역분할 기법: 기존 방법의 적용성 평가

Deep learning approaches to hair segmentation for disease detection in pet skin images: Applicability evaluation of current methods

최재영|유원상|박범진|이영찬|이범식
한국차세대컴퓨팅학회 (KINGComputing)|2022.04|한국차세대컴퓨팅학회 논문지 (The Journal of Korean Institute of Next Generation Computing)|제18권 제2호|pp. 59-74|DOI 10.23019/kingpc.18.2.202204.006

1

조회

0

다운로드

2

인용

0

참고문헌

키워드

딥러닝deep learning털 분할합성영상반려동물 피부영상hair segmentationsynthetic imagepet skin image
주제분류컴퓨터학

초록

인공지능 기반 반려동물 피부영상 진단기술은 전세계적으로 아직 초기단계에 머물러 있다. 특히 풍성한 털로 덮인 반려동물의 피부영상에서 털을 제거하는 것은 해결되지 않은 기술적 난제로 남아 있다. 본 논문은 반려동물 고배율 피부영상에서 털 제거를 위한 필수적인 전처리 단계로서 털 영역을 분할하기 위해 딥러닝 모델인 U-net과 LadderNet의 적용 가능성을 시험하고 기존의 영상처리 기반 털 영역분할 알고리즘과 성능을 비교 분석한다(Ronneberger et al. 2015, Zhuang 2018). 반려동물 피부영상 뿐만 아니라 사람 피부영상, 가짜털을 생성한 합성영상을 이용하여 딥러닝 모델을 훈련한 효과도 분석하였다. 실험 결과, 반려동물 피부영상 데이터셋을 사용하여 훈련된 LadderNet이 반려동물 피부영상에 대하여 기존 영상처리 기반 방법 및 U-net보다 더 높은 F1-score, 정확도 및 AUC 값을 보였다. 반면 합성영상을 사용한 모델 훈련은 실제 피부영상에 대해서는 성능 개선 효과가 없었지만 합성영상에 대해서는 좋은 성능을 보였다.

Abstract

Artificial intelligence technologies for pet skin image diagnosis is still in its infancy. Especially, it remains unsolved to remove abundant hairs from pet skin images. In this paper, we evaluated the applicability of two deep learning models, including U-net and LadderNet, for hair segmentation as an essential preprocessing step for hair removal in pet microscopic skin images, and we compared their performance with an existing method based on image processing. In particular, those models were trained not only with pet and human skin images but also with synthetic skin images of fake hairs. In experimental results, the performance of LadderNet for hair segmentation in pet skin images, measured as F1-score, accuracy and AUC, was superior to U-net as well as the image processing method when it was trained with the pet skin image dataset. On the other hand, training both models with synthetic skin images was effective not in real skin images but in synthetic skin images.

참고문헌 (52)

  1. S. Paterson, "Manual of Skin Diseases of the Dog and Cat" (2009), John Wiley & Sons
  2. A. Esteva, "Dermatologist-level classification of skin cancer with deep neural networks", Nature, 542(115), pp.115~118 (2017)
  3. M. Goyal, "Artificial intelligence-based image classification methods for diagnosis of skin cancer:Challenges and opportunities", Comput. Biol. Med., 127(8), pp.104065~102020 (2020)
  4. S. S. Han, "Augmented Intelligence Dermatology: Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders", J. Invest. Dermatol, 140(9), pp.1753~1761 (2020)
  5. S. Pathan, "Hair detection and lesion segmentation in dermoscopic images using domain knowledge", Med. Biol. Eng. Comput., 56(11), pp.2051~2065 (2018)
  6. K. Zafar, "Skin lesion segmentation from dermoscopic images using convolutional neural network", Sensors, 20(6), pp.1~14 (2020)
  7. H. Salehinejad, "Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks", 2018 IEEE International Conference on Acoustics, pp.990~994 (2018), Speech and Signal Processing (ICASSP)
  8. V. Kovalev, "Examining the Capability of GANs to Replace Real Biomedical Images in Classification Models Training", 2019 International Conference on Pattern Recognition and Information Processing(PRIP):Pattern Recognition and Information Processing, pp.98~107 (2019)
  9. 이영찬, "털 합성 데이터 증강을 통한 피부영상 털 제거 심층학습 기법 : 기존방법의 적용성 평가", 제34회 영상처리 및 이해에 관한워크샵(IPIU 2022) (2022)
  10. S. Minaee, "Image Segmentation Using Deep Learning : A Survey", IEEE Trans. Pattern Anal. Mach. Intell, pp.1~1 (2021)
  11. J. Long, "Fully convolutional networks for semantic segmentation", Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp.3431~3440 (2015)
  12. O. Ronneberger, "U-net:Convolutional networks for biomedical image segmentation", International Conference on Medical image computing and computer-assisted intervention, pp.234~241 (2015), Springer
  13. F. Milletari, "V-net: Fully convolutional neural networks for volumetric medical image segmentation", 2016 Fourth International Conference on 3D Vision (3DV), pp.565~571 (2016), IEEE
  14. L.-C. Chen, "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs", IEEE transactions on pattern analysis and machine intelligence, 40(4), pp.834~848 (2017)
  15. F. Visin, "Reseg: A recurrent neural network-based model for semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 41(48), pp.41~48 (2016)
  16. L. -C. Chen, "Attention to scale : Scale-aware semantic image segmentation", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.3640~3649 (2016)
  17. N. Souly, "Semi supervised semantic segmentation using generative adversarial network", Proceedings of the IEEE International Conference on Computer Vision, pp.5688~5696 (2017)
  18. L. -C. Chen, "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation", Lect. Notes Comput. Sci., 11211, pp.833~851 (2018)
  20. T. Lee, "Dullrazor®: A software approach to hair removal from images", Comput. Biol. Med., 27(6), pp.533~543 (1997)
  21. K. Kiani, "E-shaver: An improved DullRazor® for digitally removing dark and light-colored hairs in dermoscopic images", Comput. Biol. Med., 41(3), pp.139~145 (2011)
  22. S. Schmid-Saugeon, "Towards a Computer-Aided Diagnosis System for Pigmented Skin Lesions", Computerized Medical Imaging and Graphics, 27(1), pp.65~78 (2003)
  23. P. Wighton, "Dermascopic Hair Disocclusion Using Inpainting", Proceedings of the SPIE Medical Imaging 2008 Conference, pp.691427-1~691427-8 (2008)
  24. T. S. Cho, "A reliable skin mole localization scheme", 2007 IEEE 11th International Conference on Computer Vision, pp.1~8 (2007)
  25. N. Razmjooy, "A computer aided diagnosis system for malignant melanomas", Neural Comput. Appl, 23(7-8), pp.2059~2071 (2013)
  26. K. Mollersen, "Unsupervised Segmentation for Digital Dermoscopic Images", Skin Research and Technology, 16(4), pp.401~407 (2010)
  27. F. -Y. Xie, "PDE-based unsupervised repair of hair-occluded information in dermoscopyimages of melanoma", Comput. Med. Imaging Graph, 33(4), pp.275~282 (2009)
  28. M. Fiorese, "VirtualShave: Automated hair removal from digital dermatoscopic images", 2011Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp.5145~5148 (2011)
  29. K. Zafar, "Skin lesion segmentation from dermoscopic images using convolutional neural network", Sensors, 20(6), pp.1~14 (2020)
  30. I. Zaqout, "Computer Methods and Programs in Biomedical Signal and Image Processing", pp.1~15 (2020), IntechOpen
  31. N. H. Nguyen, "Segmentation of Light and Dark Hair in Dermoscopic Images: A Hybrid Approach Using a Universal Kernel", Proceedings of the SPIE Medical Imaging 2010 Conference, pp.1~8 (2010)
  32. A. Huang, "A robust hair segmentation and removal approach for clinical images of skin lesions", 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.3315~3318 (2013)
  33. Q. Abbas, "A Feature-Preserving Hair Removal Algorithm for Dermoscopy Images", Ski. Res. Technol., 19(1), pp.27~36 (2013)
  34. J. Koehoorn, "Automated digital hair removal by threshold decomposition and morphological analysis", Lect. Notes Comput. Sci, 9082, pp.15~26 (2015)
  35. A. Nasonova, "Image Warping in Dermatological Image Hair Removal", Lect. Notes Comput. Sci., 8815, pp.159~166 (2014)
  36. S. Pathan, "Hair detection and lesion segmentation in dermoscopic images using domain knowledge", Med. Biol. Eng. Comput., 56(11), pp.2051~2065 (2018)
  37. P. Das, "Removal of Hair Particles from Skin Disease Images Using Pixel Based Approach", Int. J. Comput. Sci. Inf. Technol., 6(5), pp.4154~4158 (2015)
  38. M. T. B. Toossi, "A. Azimi, An Effective Hair Removal Algorithm for Dermoscopy Images", Skin Research and Technology, 19(3), pp.230~235 (2013)
  39. M. G. Fleming, "Techniques for Structural Analysis of Derma-toscopic Imagery", Computerized Medical Imaging and Graphics, 22(5), pp.375~389 (1998)
  40. H. Zhou, "Feature Preserving Artifact Removal from Dermoscopy Images", Proceedings of the SPIE Medical Imaging 2008 Conference, pp.1~9 (2008)
  41. A. Afonso, "Hair Detection in Dermoscopic Images Using Percolation", Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp.4378~4381 (2012)
  42. P. Wighton, "Generalizing Common Tasks in Automated Skin Lesion Diagnosis", IEEE Transactions on Information Technology in Biomedicine, 15(4), pp.622~629 (2011)
  43. C. Barata, "A System for the Detection of Pigment Network in Dermoscopy Images Using Directional Filters", IEEE Transactions on Biomedical Engineering, 59(10), pp.2744~2754 (2012)
  44. K. Thon, "Bayesian Multiscale Analysis of Images Modeled as Gaussian Markov Random Fields", Computational Statistics and Data Analysis, 56(1), pp.49~61 (2012)
  45. V. Rotemberg, "A patientcentric dataset of images and metadata for identifying melanomas using clinical context", Scientific Data, 8(34) (2021)
  46. P. Pérez, "Poisson image editing", ACM SIGGRAPH 2003, 313(318), pp.313~318 (2003)
  47. D. P. Kingma, "Adam: A Method for Stochastic Optimization", Int. Conf. Learn. Represent, pp.1~15 (2015)
  48. O. Marques, "Practical Image and Video Processing Using MATLAB®", pp.299~334 (2011), John Wiley & Sons
  49. N. Otsu, "A Threshold Selection Method from Gray-Level Histograms", IEEE Trans. Syst. Man. Cybern, 9(1), pp.62~66 (1979)
  50. H. Samet, "Efficient component labeling of images of arbitrary dimension represented by linear bintrees", IEEE Trans. Pattern Anal. Mach. Intell., 10(4), pp.579~586 (1988)
  51. F. Melo, "Encyclopedia of Systems Biology" (2013), Springer
  52. A. Jaiswal, "A Survey on Contrastive Self-Supervised Learning", Tech-nologies, 9(1), pp.2~ (2020)

관련 논문AI추천

피부영상 털 제거를 위한 트랜스포머 기반 인페인팅 기법:기존 방법의 적용성 평가박범진, 유원상, 이영찬한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2022 · 제18권 제6호피부병변 영상 분할의 성능향상을 위한 VmCUnet김홍진, 이태희, 최명렬, 황우성한국전기전자학회 · 전기전자학회논문지2024 · 제28권 제3호피부 병변 분할을 위한 어텐션 기반 딥러닝 프레임워크이범식, Afnan Ghafoor(사)한국스마트미디어학회 · 스마트미디어저널2024 · 제13권 제3호딥 러닝 기반의 악성흑색종 분류를 위한 컴퓨터 보조진단 알고리즘이명숙, 임상헌(사)디지털산업정보학회 · (사)디지털산업정보학회 논문지2018 · 제14권 제4호딥러닝을 이용한 창상 분할 알고리즘강현영, 김지예, 박성빈, 전재준, 정승원, 허연우대한의용생체공학회 · 의공학회지2024 · 제45권 제2호피부 모공 검출을 위한 ConVmUnet 영상 분할 기법김홍진, 이태희, 최명렬, 황우성한국전기전자학회 · 전기전자학회논문지2025 · 제29권 제1호

이 간행물의 다른 논문 (8건)

이더리움 블록체인 환경에서 전력 데이터의 효율적 저장을 위한 데이터 수직 결합 기법의 설계와 구현박재형, 이태영pp. 7-14강화학습과 비례위험모형을 이용한 환자 치료 효과를 높이는 유전자 변이 탐색 알고리즘강민수, 강민구, 김수현, 김동진pp. 15-24비디오 스토리지 시스템에서 복구 읽기 I/O 대역폭 최소화를 위한 적응형 중복 방법 선택 기법송민석, 이다영, 이춘광pp. 25-35기계장비 진동 데이터를 이용한 딥러닝 기반의 고장 분류 모델이수안, 이수형, 고상근pp. 36-46오토인코더 기반 이상 행동 탐지 시스템에서 3D CNN과 초해상화 기법의 적용 및 성능 분석전영훈, 곽정환, 임현석pp. 47-58
원문 보기