Improving Skin Lesion Analysis with Generative Adversarial Networks
ResumoMelanoma is the most lethal type of skin cancer. Early diagnosis is crucial to increase the survival rate of those patients due to the possibility of metastasis. Automated skin lesion analysis can play an essential role by reaching people that do not have access to a specialist. However, since deep learning became the state-of-the-art for skin lesion analysis, data became a decisive factor in pushing the solutions further. The core objective of this M.Sc. dissertation is to tackle the problems that arise by having limited datasets. In the first part, we use generative adversarial networks to generate synthetic data to augment our classification model’s training datasets to boost performance. Our method generates high-resolution clinically-meaningful skin lesion images, that when compound our classification model’s training dataset, consistently improved the performance in different scenarios, for distinct datasets. We also investigate how our classification models perceived the synthetic samples and how they can aid the model’s generalization. Finally, we investigate a problem that usually arises by having few, relatively small datasets that are thoroughly re-used in the literature: bias. For this, we designed experiments to study how our models’ use data, verifying how it exploits correct (based on medical algorithms), and spurious (based on artifacts introduced during image acquisition) correlations. Disturbingly, even in the absence of any clinical information regarding the lesion being diagnosed, our classification models presented much better performance than chance (even competing with specialists benchmarks), highly suggesting inflated performances.
A. Bissoto, F. Perez, E. Valle, and S. Avila, "Skin lesion synthesis with generative adversarial networks," in ISIC Skin Image Analysis Workshop, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2018.
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in Advances in Neural Information Processing Systems, 2014, pp. 2672– 2680.
G. Argenziano, G. Fabbrocini, P. Carli, V. De Giorgi, E. Sammarco, and M. Delﬁno, "Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions: comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis," Archives of Dermatology, vol. 134, no. 12, pp. 1563–1570, 1998.
S. W. Menzies, I. C., C. K. A., and M. W. H., "Frequency and mor- phologic characteristics of invasive melanomas lacking speciﬁc surface microscopic features," Archives of Dermatology, pp. 1178–1182, 1996.
F. Nachbar, W. Stolz, T. Merkle, A. B. Cognetta, T. Vogt et al., "The ABCD rule of dermatoscopy: high prospective value in the diagnosis of doubtful melanocytic skin lesions," Journal of the American Academy of Dermatology, vol. 30, no. 4, pp. 551–559, 1994.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
J. Susskind, A. Anderson, and G. Hinton, "The toronto face dataset," University of Toronto, Tech. Rep., 2010.
A. Radford, L. Metz, and S. Chintala, "Unsupervised representation learning with deep convolutional generative adversarial networks," in International Conference on Learning Representations, 2016.
T. Miyato, T. Kataoka, M. Koyama, and Y. Yoshida, "Spectral normal- ization for generative adversarial networks," in International Conference on Learning Representations, 2018.
T. Karras, T. Aila, S. Laine, and J. Lehtinen, "Progressive growing of GANs for improved quality, stability, and variation," in International Conference on Learning Representations, 2018.
T. Miyato and M. Koyama, "cGANs with projection discriminator," in International Conference on Learning Representations, 2018.
D. Yoo, N. Kim, S. Park, A. Paek, and I. Kweon, "Pixel-level do- main transfer," in European Conference on Computer Vision (ECCV). Springer, 2016, pp. 517–532.
P. Isola, J. Zhu, T. Zhou, and A. Efros, "Image-to-image translation with conditional adversarial networks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1125–1134.
O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," in International Conference on Medical Image Computing and Computer-Assisted Intervention (MIC- CAI). Springer, 2015, pp. 234–241.
T. Wang, M. Liu, J. Zhu, A. Tao, J. Kautz, and B. Catanzaro, "High- resolution image synthesis and semantic manipulation with conditional gans," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8798–8807.
J. Johnson, A. Alahi, and L. Fei-Fei, "Perceptual losses for real- time style transfer and super-resolution," in European Conference on Computer Vision (ECCV). Springer, 2016, pp. 694–711.
G. Argenziano, H. P. Soyer, V. De Giorgi, D. Piccolo, P. Carli, M. Delﬁno et al., "Dermoscopy: a tutorial," EDRA, Medical Publishing & New Media, p. 16, 2002.
"International Skin Imaging Collaboration: Melanoma Project," https: //isic-archive.com.
M. E. Celebi, Q. Wen, H. Iyatomi, K. Shimizu, H. Zhou, and G. Schae- fer, "A state-of-the-art survey on lesion border detection in dermoscopy images," Dermoscopy Image Analysis, pp. 97–129, 2015.
T. J. Brinker, A. Hekler, A. Hauschild, C. Berking, B. Schilling, A. H. Enk, S. Haferkamp, A. Karoglan, C. von Kalle, M. Weichenthal et al., "Comparing artiﬁcial intelligence algorithms to 157 german dermatol- ogists: the melanoma classiﬁcation benchmark," European Journal of Cancer, vol. 111, pp. 30–37, 2019.
R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-cam: Visual explanations from deep networks via gradient-based localization," in IEEE International Conference on Computer Vision, 2017, pp. 618–626.
R. Fong and A. Vedaldi, "Interpretable explanations of black boxes by meaningful perturbation," in IEEE International Conference on Computer Vision, 2017, pp. 3429–3437.
A. Torralba and A. A. Efros, "Unbiased look at dataset bias," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, pp. 1521–1528.
O. Russakovsky, J. Deng, H. S., J. Krause, S. Satheesh, S. Ma et al., "ImageNet Large Scale Visual Recognition Challenge," International Journal of Computer Vision, vol. 115, no. 3, pp. 211–252, 2015.
A. Bissoto, E. Valle, and S. Avila, "Debiasing skin lesion datasets and models? not so fast," in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020.
A. Bissoto, M. Fornaciali, E. Valle, and S. Avila, "(De)Constructing bias on skin lesion datasets," in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019.
A. Bissoto, E. Valle, and S. Avila, "The six fronts of the generative adversarial networks," arXiv preprint arXiv:1910.13076, 2019.
A. Bissoto, M. Fornaciali, E. Valle, and S. Avila, "Generating high quality synthetic skin lesions for boosting automated screening," International Educational Symposium of the Melanoma World Society, pp. 43–43, 2018.
A. Bissoto, F. Perez, V. Ribeiro, M. Fornaciali, S. Avila, and E. Valle, "Deep-learning ensembles for skin-lesion segmentation, analysis, classification: RECOD Titans at ISIC Challenge 2018," arXiv preprint arXiv:1808.08480, 2018.