Viés Racial em Modelos de Inteligência Artificial para Classificação de Melanomas
Resumo
O uso de inteligência artificial (IA) para a detecção de câncer de pele tem sido objeto de muita pesquisa e desenvolvimento nos últimos anos. No entanto, estudos recentes sugerem que alguns algoritmos de classificação de câncer de pele podem ter viés racial, com desempenho pior em pacientes com pele mais escura. Nesse artigo, avaliamos o desempenho de um modelo de IA ao classificar melanomas em 10 diferentes tons de pele, de acordo com a Escala Monk. Como resultado, foi observado que os modelos têm pior desempenho para classificar melanomas em peles mais escuras.Referências
Arora, G., Dubey, A. K., Jaffery, Z. A., and Rocha, A. (2022). Bag of feature and support vector machine based early diagnosis of skin cancer. Neural Computing and Applications, pages 1–8.
Bissoto, A., Fornaciali, M., Valle, E., and Avila, S. (2019). (de) constructing bias on skin lesion datasets. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 0–0.
Brinker, T. J., Hekler, A., Enk, A. H., Berking, C., Haferkamp, S., Hauschild, A., Weichenthal, M., Klode, J., Schadendorf, D., Holland-Letz, T., et al. (2019). Deep neural networks are superior to dermatologists in melanoma image classification. European Journal of Cancer, 119:11–17.
Bruce, A. and Bruce, P. (2019). Estatística prática para cientistas de dados. Alta Books.
Buolamwini, J. A. (2017). Gender shades: intersectional phenotypic and demographic evaluation of face datasets and gender classifiers. PhD thesis, Massachusetts Institute of Technology.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee.
Gupta, A. K., Bharadwaj, M., and Mehrotra, R. (2016). Skin cancer concerns in people of color: risk factors and prevention. Asian Pacific journal of cancer prevention: APJCP, 17(12):5257.
Gutman, D., Codella, N. C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern, A. (2016). Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (isbi) 2016, hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1605.01397.
Hekler, A., Utikal, J. S., Enk, A. H., Hauschild, A., Weichenthal, M., Maron, R. C., Berking, C., Haferkamp, S., Klode, J., Schadendorf, D., et al. (2019). Superior skin cancer classification by the combination of human and artificial intelligence. European Journal of Cancer, 120:114–121.
Jicman, P. A., Smart, H., Ayello, E. A., and Sibbald, R. G. (2023). Early malignant melanoma detection, especially in persons with pigmented skin. Advances in Skin & Wound Care, 36(2):69–77.
Lynn, N. C. and War, N. (2019). Melanoma classification on dermoscopy skin images using bag tree ensemble classifier. In 2019 International Conference on Advanced Information Technologies (ICAIT), pages 120–125. IEEE.
Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R., and Rozeira, J. (2013). Ph 2-a dermoscopic image database for research and benchmarking. In 2013 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pages 5437–5440. IEEE.
Menegola, A., Fornaciali, M., Pires, R., Bittencourt, F. V., Avila, S., and Valle, E. (2017). Knowledge transfer for melanoma screening with deep learning. In 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017), pages 297–300. IEEE.
Nambisan, A. K., Maurya, A., Lama, N., Phan, T., Patel, G., Miller, K., Lama, B., Hagerty, J., Stanley, R., and Stoecker, W. V. (2023). Improving automatic melanoma diagnosis using deep learning-based segmentation of irregular networks. Cancers, 15(4):1259.
Rezk, E., Eltorki, M., El-Dakhakhni, W., et al. (2022). Improving skin color diversity in cancer detection: Deep learning approach. JMIR Dermatology, 5(3):e39143.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
WCRF, W. C. R. F. I. Cancer trends: Skin cancer statistics.
Bissoto, A., Fornaciali, M., Valle, E., and Avila, S. (2019). (de) constructing bias on skin lesion datasets. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 0–0.
Brinker, T. J., Hekler, A., Enk, A. H., Berking, C., Haferkamp, S., Hauschild, A., Weichenthal, M., Klode, J., Schadendorf, D., Holland-Letz, T., et al. (2019). Deep neural networks are superior to dermatologists in melanoma image classification. European Journal of Cancer, 119:11–17.
Bruce, A. and Bruce, P. (2019). Estatística prática para cientistas de dados. Alta Books.
Buolamwini, J. A. (2017). Gender shades: intersectional phenotypic and demographic evaluation of face datasets and gender classifiers. PhD thesis, Massachusetts Institute of Technology.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee.
Gupta, A. K., Bharadwaj, M., and Mehrotra, R. (2016). Skin cancer concerns in people of color: risk factors and prevention. Asian Pacific journal of cancer prevention: APJCP, 17(12):5257.
Gutman, D., Codella, N. C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern, A. (2016). Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (isbi) 2016, hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1605.01397.
Hekler, A., Utikal, J. S., Enk, A. H., Hauschild, A., Weichenthal, M., Maron, R. C., Berking, C., Haferkamp, S., Klode, J., Schadendorf, D., et al. (2019). Superior skin cancer classification by the combination of human and artificial intelligence. European Journal of Cancer, 120:114–121.
Jicman, P. A., Smart, H., Ayello, E. A., and Sibbald, R. G. (2023). Early malignant melanoma detection, especially in persons with pigmented skin. Advances in Skin & Wound Care, 36(2):69–77.
Lynn, N. C. and War, N. (2019). Melanoma classification on dermoscopy skin images using bag tree ensemble classifier. In 2019 International Conference on Advanced Information Technologies (ICAIT), pages 120–125. IEEE.
Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R., and Rozeira, J. (2013). Ph 2-a dermoscopic image database for research and benchmarking. In 2013 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pages 5437–5440. IEEE.
Menegola, A., Fornaciali, M., Pires, R., Bittencourt, F. V., Avila, S., and Valle, E. (2017). Knowledge transfer for melanoma screening with deep learning. In 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017), pages 297–300. IEEE.
Nambisan, A. K., Maurya, A., Lama, N., Phan, T., Patel, G., Miller, K., Lama, B., Hagerty, J., Stanley, R., and Stoecker, W. V. (2023). Improving automatic melanoma diagnosis using deep learning-based segmentation of irregular networks. Cancers, 15(4):1259.
Rezk, E., Eltorki, M., El-Dakhakhni, W., et al. (2022). Improving skin color diversity in cancer detection: Deep learning approach. JMIR Dermatology, 5(3):e39143.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
WCRF, W. C. R. F. I. Cancer trends: Skin cancer statistics.
Publicado
06/08/2023
Como Citar
PAULINO, José Alberto Souza.
Viés Racial em Modelos de Inteligência Artificial para Classificação de Melanomas. In: WORKSHOP SOBRE AS IMPLICAÇÕES DA COMPUTAÇÃO NA SOCIEDADE (WICS), 4. , 2023, João Pessoa/PB.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 107-114.
ISSN 2763-8707.
DOI: https://doi.org/10.5753/wics.2023.229667.
