Smart Media Journal (스마트미디어저널)

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

DOI QR Code

Attention-based deep learning framework for skin lesion segmentation

피부 병변 분할을 위한 어텐션 기반 딥러닝 프레임워크

  • Received : 2024.02.29
  • Accepted : 2024.04.03
  • Published : 2024.03.29
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a novel M-shaped encoder-decoder architecture for skin lesion segmentation, achieving better performance than existing approaches. The proposed architecture utilizes the left and right legs to enable multi-scale feature extraction and is further enhanced by integrating an attention module within the skip connection. The image is partitioned into four distinct patches, facilitating enhanced processing within the encoder-decoder framework. A pivotal aspect of the proposed method is to focus more on critical image features through an attention mechanism, leading to refined segmentation. Experimental results highlight the effectiveness of the proposed approach, demonstrating superior accuracy, precision, and Jaccard Index compared to existing methods

본 논문은 기존 방법보다 우수한 성능을 달성하는 피부 병변 분할을 위한 새로운 M자 모양 인코더-디코더 아키텍처를 제안한다. 제안된 아키텍처는 왼쪽과 오른쪽 다리를 활용하여 다중 스케일 특징 추출을 가능하게 하고, 스킵 연결 내에서 어텐션 메커니즘을 통합하여 피부 병변 분할 성능을 더욱 향상시킨다. 입력 영상은 네 가지 다른 패치로 분할되어 입력되며 인코더-디코더 프레임워크 내에서 피부 병변 분할 성능의 향상된 처리를 가능하게 한다. 제안하는 방법에서 어텐션 메커니즘을 통해 입력 영상의 특징에 더 많은 초점을 맞추어 더욱 정교한 영상 분할 결과를 도출하는 것이다. 실험 결과는 제안된 방법의 효과를 강조하며, 기존 방법과 비교하여 우수한 정확도, 정밀도 및 Jaccard 지수를 보여준다.

Keywords

Acknowledgement

이 논문은 2021년도 조선대학교 학술연구비의 지원을 받아 연구되었음.

References

  1. Statistics on Melanoma skin cancer problem:https://www.cancer.org/research/cancer-factsstatistics/all-cancer-facts-figures/cancer-facts-figures2018.html
  2. O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," arXiv:1505.04597, 2015. [DOI: 10.1007/978-3-319-24574-4_28] 
  3. R. Mehta and J. Sivaswamy, "M-net: A Convolutional Neural Network for Deep Brain Structure Segmentation," 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2017, pp. 437-440. [DOI: 10.1109/ISBI.2017.7950584] 
  4. J. Long, E. Shelhamer, and T. Darrell, "Fully Convolutional Networks for Semantic Segmentation," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431-3440. [DOI: 10.1109/CVPR.2015.7298965] 
  5. H. Chen, Y. Qi, X. Yu, L. Dou, Q. Qin, and P.-A. Heng, "DCAN: Dual-Channel Convolutional Attention Network for Automatic Nucleus Segmentation in H&E Stained Images," IEEE Transactions on Medical Imaging, vol. 38, no. 2, pp. 359-370, Feb. 2019. [DOI: 10.1109/TMI.2018.2856806] 
  6. Z. Zhang, X. Wei, Z. Zhao, and W. Qian, "Skin Lesion Segmentation Using Deep Convolutional Neural Networks and a Novel Segmentation Quality Evaluation Method," Journal of Imaging, vol. 6, no. 10, p. 95, Oct. 2020. [DOI: 10.3390/jimaging6100095 
  7. J. Dai, K. He, and J. Sun, "Instance-aware Semantic Segmentation via Multi-task Network Cascades," in CVPR, 2016, pp. 3150-3158. [DOI: 10.1109/CVPR.2016.340] 
  8. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," in CVPR, 2014, pp. 580 - 587. [DOI: 10.1109/CVPR.2014.81] 
  9. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," in NIPS, 2012, pp. 1097 -1105. [DOI: 10.1145/3065386] 
  10. A. B. Ashrafulla, D. M. Shotton, J. Winn, C. Rother, and A. Criminisi, "Anatomy-specific Classification of Medical Images," in ICCV, 2013, pp. 987 - 994. [DOI: 10.1109/ICCV.2013.129] 
  11. Z. Zhang, X. Wei, Z. Zhao, and W. Qian, "Skin Lesion Segmentation Using Deep Convolutional Neural Networks and a Novel Segmentation Quality Evaluation Method," Journal cf Imaging, vol. 6, no. 10, p. 95, Oct. 2020. [DOI: 10.3390/jimaging6100095] 
  12. P. Vakalopoulou, M. M. Zormpas, N. Giatromanolaki, and D. Visvikis, "Deep Learning for the Segmentation of Head and Neck Organs at Risk: A Review," Medical Physics, vol. 47, no. 5, pp. 2011-2027, May 2020. [DOI: 10.1002/mp.l4078] 
  13. J. Dai, K. He, and J. Sun, "Instance-aware Semantic Segmentation via Multi-task Network Cascades," in CVPR, 2016, pp. 3150-3158. [DOI: 10.1109/CVPR.2016.340] 
  14. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," in CVPR, 2014, pp. 580 - 587. [DOI: 10.1109/CVPR.2014.81] 
  15. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," in NIPS, 2012, pp. 1097 - 1105. 
  16. Hemandez-Orallo, "The Jaccard Index: A Unifying View of Similarity and Diversity Measures," CoRR, vol. abs/1301.3787, 2013 
  17. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, vol. 27, no. 8, pp. 1847-1 
  18. Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, 'UNet++: Redesigning Skip Comections to Exploit Multiscale Features in Image Segmentation', arXiv [eess.IV]. 2020. 
  19. L. da F. Costa, 'Further Generalizations of the Jaccard Index', arXiv [cs.LG]. 2021. 
  20. N. Codella et al., 'Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)', arXiv [cs.CV]. 2019.