OpenLB
Open Library of Bioscience
Advanced Search
Scientific reports
10 13, 2023;13 (1): 17331.

Psoriasis severity classification based on adaptive multi-scale features for multi-severity disease.

Cho-I Moon, Jiwon Lee, Yoo Sang Baek, Onesok Lee
Author Information
  1. Cho-I Moon: Department of Software Convergence, Graduate School, Soonchunhyang University, 22, Soonchunhyang-ro, Asan, Chungnam-do, 31538, Republic of Korea.
  2. Jiwon Lee: Department of Software Convergence, Graduate School, Soonchunhyang University, 22, Soonchunhyang-ro, Asan, Chungnam-do, 31538, Republic of Korea.
  3. Yoo Sang Baek: Department of Dermatology, Guro Hospital, Korea University College of Medicine, Seoul, 08308, Republic of Korea.
  4. Onesok Lee: Department of Software Convergence, Graduate School, Soonchunhyang University, 22, Soonchunhyang-ro, Asan, Chungnam-do, 31538, Republic of Korea. leeos@sch.ac.kr.
PMID: 37833444 DOI: 10.1038/s41598-023-44478-9

Abstract

Psoriasis is a skin disease that causes lesions of various sizes across the body and can persist for years with cyclic deterioration and improvement. During treatment, and a multiple-severity disease, with irregular severity within the observation area may be found. The current psoriasis evaluation is based on the subjective evaluation criteria of the clinician using the psoriasis area and severity index (PASI). We proposed a novel psoriasis evaluation method that detects representative regions as evaluation criteria, and extracts severity features to improve the evaluation performance of various types of psoriasis, including multiple-severity diseases. We generated multiple-severity disease images using CutMix and proposed a hierarchical multi-scale deformable attention module (MS-DAM) that can adaptively detect representative regions of irregular and complex patterns in multiple-severity disease analyses. EfficientNet B1 with MS-DAM exhibited the best classification performance with an F1-score of 0.93. Compared with the performance of the six existing self-attention methods, the proposed MS-DAM showed more than 5% higher accuracy than that of multiscale channel attention module (MS-CAM). Using the gradient-weighted activation mapping method, we confirmed that the proposed method works at par with human visual perception. We performed a more objective, effective, and accurate analysis of psoriasis severity using the proposed method.

References

  1. Goon, P., Farooqui, U., Koopmans, I., Skellett, A. & Levell, N. Assessment of a 3-dimensional computerised PASI tool for calculating and documenting psoriasis area and severity index scores. J. Eur. Acad. Dermatol. Venereol. 31, e352–e353 (2017). [DOI: 10.1111/jdv.14154]
  2. Fink, C., Uhlmann, L., Klose, C. & Haenssle, H. A. Automated, computer-guided PASI measurements by digital image analysis versus conventional physicians’ PASI calculations: Study protocol for a comparative, single-centre, observational study. BMJ Open 8, e018461 (2018). [DOI: 10.1136/bmjopen-2017-018461]
  3. Li, Y. et al. PSENet: Psoriasis Severity Evaluation Network. Proc. AAAI Conf. Artif. Intell. 34, 800–807 (2020).
  4. Salgado-Boquete, L. et al. A new classification of the severity of psoriasis: What’s moderate psoriasis?. Life 11, 627 (2021). [DOI: 10.3390/life11070627]
  5. Lu, J., Manton, J. H., Kazmierczak, E. & Sinclair, R. Erythema detection in digital skin images. In: 2010 IEEE International Conference on Image Processing 2545–2548 (2010).
  6. Hägg, D., Sundström, A., Eriksson, M. & Schmitt-Egenolf, M. Severity of psoriasis differs between men and women: A study of the clinical outcome measure psoriasis area and severity index (PASI) in 5438 Swedish register patients. Am. J. Clin. Dermatol. 18, 583–590 (2017). [DOI: 10.1007/s40257-017-0274-0]
  7. Hsu, C.-K., Cheng, N.-Y., Yang, C.-C., Yen, Y.-Y. & Tseng, S.-H. Investigating the clinical implication of corneometer and mexameter readings towards objective, efficient evaluation of psoriasis vulgaris severity. Sci. Rep. 12, 1–8 (2022). [DOI: 10.1038/s41598-022-11573-2]
  8. Sumithra, R., Suhil, M. & Guru, D. Segmentation and classification of skin lesions for disease diagnosis. Proc. Comput. Sci. 45, 76–85 (2015). [DOI: 10.1016/j.procs.2015.03.090]
  9. Son, H. M. et al. AI-based localization and classification of skin disease with erythema. Sci. Rep. 11, 1–14 (2021). [DOI: 10.1038/s41598-021-84593-z]
  10. Kye, S. & Lee, O. Skin color classification of Koreans using clustering. Skin Res. Technol. 28, 796–803 (2022). [DOI: 10.1111/srt.13201]
  11. Roy, A., Pal, A. & Garain, U. JCLMM: A finite mixture model for clustering of circular-linear data and its application to psoriatic plaque segmentation. Pattern Recognit. 66, 160–173 (2017). [DOI: 10.1016/j.patcog.2016.12.016]
  12. Ahmad Fadzil, M., Ihtatho, D., Mohd Affandi, A. & Hussein, S. Objective assessment of psoriasis erythema for PASI scoring. J. Med. Eng. Technol. 33, 516–524 (2009). [DOI: 10.1080/07434610902744074]
  13. Mirzaalian, H., Lee, T. K. & Hamarneh, G. Skin lesion tracking using structured graphical models. Med. Image Anal. 27, 84–92 (2016). [DOI: 10.1016/j.media.2015.03.001]
  14. Zhang, J., Xie, Y., Wu, Q. & Xia, Y. Medical image classification using synergic deep learning. Med. Image Anal. 54, 10–19 (2019). [DOI: 10.1016/j.media.2019.02.010]
  15. Moon, C.-I. & Lee, O. Skin microstructure segmentation and aging classification using CNN-based models. IEEE Access 10, 4948–4956 (2021). [DOI: 10.1109/ACCESS.2021.3140031]
  16. Syu, J.-M., Lai, C.-H., Lin, G.-S. & Chai, S.-K. Psoriasis detection based on deep neural network. In: 2018 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW) 1–2 (2018).
  17. Dash, M., Londhe, N. D., Ghosh, S., Raj, R. & Sonawane, R. S. A cascaded deep convolution neural network based CADx system for psoriasis lesion segmentation and severity assessment. Appl. Soft Comput. 91, 106240 (2020). [DOI: 10.1016/j.asoc.2020.106240]
  18. Moon, C.-I., Lee, J., Yoo, H., Baek, Y. & Lee, O. Optimization of psoriasis assessment system based on patch images. Sci. Rep. 11, 1–13 (2021). [DOI: 10.1038/s41598-021-97211-9]
  19. Schaap, M. et al. Image-based automated psoriasis area severity index scoring by convolutional neural networks. J. Eur. Acad. Dermatol. Venereol. 36, 68–75 (2022). [DOI: 10.1111/jdv.17711]
  20. Li, Y. et al. in Proceedings of the AAAI Conference on Artificial Intelligence 800–807.
  21. Aijaz, S. F., Khan, S. J., Azim, F., Shakeel, C. S. & Hassan, U. Deep learning application for effective classification of different types of psoriasis. J. Healthc. Eng. 2022 (2022).
  22. Rezaee, K., Khosravi, M. R., Qi, L. & Abbasi, M. in 2022 International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS) 1–6 (IEEE).
  23. Okamoto, T., Kawai, M., Ogawa, Y., Shimada, S. & Kawamura, T. Artificial intelligence for the automated single-shot assessment of psoriasis severity. J. Eur. Acad. Dermatol. Venereol. 36, 2512–2515 (2022). [DOI: 10.1111/jdv.18354]
  24. Moon, C.-I., Baek, Y.-S., Choi, M.-H. & Lee, O. Robust psoriasis severity classification by using data augmentation. Trans. Korean Inst. Electric. Eng. 71, 1841–1847 (2022). [DOI: 10.5370/KIEE.2022.71.12.1841]
  25. DeVries, T. & Taylor, G. W. Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552 (2017).
  26. Zhang, H., Cisse, M., Dauphin, Y. N. & Lopez-Paz, D. mixup: Beyond empirical risk minimization. arXiv:1710.09412 (2017).
  27. Yun, S. et al. Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision 6023–6032 (2019).
  28. Dai, J. et al. Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision 764–773 (2017).
  29. Thomas, S. M., Lefevre, J. G., Baxter, G. & Hamilton, N. A. Interpretable deep learning systems for multi-class segmentation and classification of non-melanoma skin cancer. Med. Image Anal. 68, 101915 (2021). [DOI: 10.1016/j.media.2020.101915]
  30. Hu, J., Shen, L. & Sun, G. Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 7132–7141 (2018).
  31. Woo, S., Park, J., Lee, J.-Y. & Kweon, I. S. Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV) 3–19 (2018).
  32. Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y. & Barnard, K. Attentional feature fusion. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 3560–3569 (2021).
  33. Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning 6105–6114 (2019).
  34. Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K. & Dollár, P. Designing network design spaces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 10428–10436 (2020).
  35. Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision 618–626 (2017).
  36. Park, J., Woo, S., Lee, J.-Y. & Kweon, I. S. Bam: Bottleneck attention module. arXiv:1807.06514 (2018).
  37. Liu, T. et al. Spatial channel attention for deep convolutional neural networks. Mathematics 10, 1750 (2022). [DOI: 10.3390/math10101750]
  38. Schlemper, J. et al. Attention gated networks: Learning to leverage salient regions in medical images. Med. Image Anal. 53, 197–207 (2019). [DOI: 10.1016/j.media.2019.01.012]
  39. Jiang, G., Lu, Z., Tu, X., Guan, Y. & Wang, Q. Image super-resolution using multi-scale space feature and deformable convolutional network. IEEE Access 9, 74614–74621 (2021). [DOI: 10.1109/ACCESS.2021.3079519]
  40. Mustafa, H. T., Yang, J. & Zareapoor, M. Multi-scale convolutional neural network for multi-focus image fusion. Image Vis. Comput. 85, 26–35 (2019). [DOI: 10.1016/j.imavis.2019.03.001]
  41. Yao, P. et al. Single model deep learning on imbalanced small datasets for skin lesion classification. arXiv:2102.01284 (2021).
  42. Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Dollár, P. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision 2980–2988 (2017).
  43. Liu, L. et al. On the variance of the adaptive learning rate and beyond. arXiv:1908.03265 (2019).

MeSH Term

Humans
Severity of Illness Index
Psoriasis
Journal Article Research Support, Non-U.S. Gov't
Article has an altmetric score of 1

Word Cloud

Similar Articles

Cited By