The deep paradox
from kernels to social makeup
Keywords:
Algorithms, Deep Learning, Artificial Intelligence, Public Health, Information SocietyAbstract
The aim of this study is to analyze the available scientific production on Deep Learning models for skin disease diagnosis, with a focus on ethnoracial diversity in image collections. Methodologically, the study is characterized as an exploratory narrative literature review. Articles that did not use deep learning algorithms or that did not address the diagnosis of skin diseases were excluded. Thirty-seven articles and seven collections of skin lesion images were analyzed. The results show that three articles mentioned the population origin of the images used in the training of Deep Learning models. Only one collection indicated the predominant population of the images represented, but none of these repositories provided detailed statistics on the participating population. It is concluded that the effectiveness of algorithms in contexts of racial diversity lacks evidence, and the analyzed research did not present solutions for this gap. In this context, this study highlights the deep paradox between technological advancement and the perpetuation of social inequalities, emphasizing the need for social adjustments in artificial intelligence systems to promote equity in access to health and avoid algorithmic bias in diagnostic technologies.
Downloads
References
Abhishek, K.; Kawahara, J.; Hamarneh, G. Predicting the clinical management of skin lesions using deep learning. Scientific Reports, v. 11, n. 1, p. 1-14, 2021. Doi: https://doi.org/10.1038/s41598-021-87064-7.
Almaraz-Damian, J-A. et al. Melanoma and nevus skin lesion classification using handcraft and deep learning feature fusion via mutual information measures. Entropy, v. 22, n. 4, p. 484, 2020. Doi: https://doi.org/10.3390/e22040484.
Ameri, A. A Deep learning approach to skin cancer detection in dermoscopy images. Journal of Biomedical Physics and Engineering, v. 10, n. 6, p. 801-806, 2020. Doi: https://doi.org/10.31661/jbpe.v0i0.2004-1107.
Anaba, E. L. Comparative study of cutaneous melanoma and its associated issues between people of African decent and Caucasians. Dermatologic Therapy, v. 34, n. 2, e14790, 2021.
Bezerra, A. C.; Da Costa, C. M. Pele negra, algoritmos brancos: informação e racismo nas redes sociotécnicas. Liinc em Revista, v. 18, n. 2, e6043, 2022.
Bhavani, R. et al. Vision-based skin disease identification using deep learning. International Journal of Engineering and Advanced Technology, v. 8, n. 6, p. 3784-3788, 2019. Doi: https://doi.org/10.35940/ijeat.F9391.088619.
Burlina, P. M. et al. Automated detection of erythema migrans and other confounding skin lesions via deep learning. Computers in Biology and Medicine, v. 105, p. 151-156, 2019. Doi: https://doi.org/10.1016/j.compbiomed.2018.12.007.
Carrera, F. Racismo e sexismo em bancos de imagens digitais: análise de resultados de busca e atribuição de relevância na dimensão financeira/profissional. Comunidades, Algoritmos e Ativismos Digitais, v. 139, n. 1, p. 138-155, 2020.
Casarin, S. et al. Tipos de revisão de literatura: considerações das editoras do Journal of Nursing and Health. Journal of Nursing and Health, v. 10, n. 5, e20104031, 2020. Doi: https://doi.org/10.15210/jonah.v10i5.19924.
Chen, H.; Sung, J. J. Potentials of AI in medical image analysis in gastroenterology and hepatology. Journal of Gastroenterology and Hepatology, v. 36, n. 1, p. 31-38, 2021.
Cullell-Dalmau, M.; Otero-Viñas, M.; Manzo, C. Research techniques made simple: deep learning for the classification of dermatological images. Journal of Investigative Dermatology, v. 140, n. 3, p. 507-514, 2020.
Dascalu, A.; David, E. O. Skin cancer detection by deep learning and sound analysis algorithms: A prospective clinical study of an elementary dermoscope. EBioMedicine, v. 43, p. 107-113, 2019. Doi: https://doi.org/10.1016/j.ebiom.2019.04.055.
De Oliveira, F. W. P.; De Souza, D. A.; Tonieto, M. T. Detecção de doenças dermatológicas baseada em aprendizagem de máquina. Revista de Tecnologia da Informação da Faculdade Lourenço Filho, v. 3, n. 2, p. 1-5, 2022.
Delazeri, A. V.; Stevani, E. S. Classificação de câncer de pele usando redes neurais convolucionais: uma análise do desempenho de classificação em um conjunto de dados desbalanceado. 2021. Trabalho de Conclusão de Curso (Bacharelado em Sistemas de Informação) – Universidade Tecnológica Federal do Paraná, Curitiba, 2021.
Do Nascimento Neto, C. D. et al. Inteligência artificial e novas tecnologias em saúde: desafios e perspectivas. Brazilian Journal of Development, v. 6, n. 2, p. 9431-9445, 2020.
El-Khatib, H.; Popescu, D.; Ichim, L. Deep learning–based methods for automatic diagnosis of skin lesions. Sensors, v. 20, n. 6, p. 1753, 2020. Doi: https://doi.org/10.3390/s20061753.
Faes, L. et al. Automated deep learning design for medical image classification by health-care professionals with no coding experience: A feasibility study. The Lancet Digital Health, v. 1, n. 5, e232-e242, 2019. Doi: https://doi.org/10.1016/S2589-7500(19)30108-6.
Gajera, H. K.; Nayak, D. R.; Zaveri, M. A. A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features. Biomedical Signal Processing and Control, v. 79, n. 2, p. 104186, 2023. Doi:10.1016/j.bspc.2022.104186.
Gómez, D. A. C.; González, G. A. P. Desarrollo de una interfaz de clasificación de enfermedades dermatológicas basadas en procesamiento de señales e inteligencia artificial. Semilleros de Investigación, v. 3, n. 2, p. 1-7, 2021.
Goyal, M. et al. Skin lesion segmentation in dermoscopic images with ensemble deep learning methods. IEEE. Access, v. 8, p. 4171-4181, 2020.
Guarizi, D. D.; Oliveira, E. V. Estudo da Inteligência Artificial aplicada na área da saúde. Colloquium Exactarum, v. 6, p. 26-37, 2014.
Han, B. C. Infocracia: digitalização e a crise da democracia. Petrópolis: Vozes, 2022.
Harangi, B.; Baran, A.; Hajdu, A. Assisted deep learning framework for multi-class skin lesion classification considering a binary classification support. Biomedical Signal Processing and Control, v. 62, n. 102041, 2020. Doi: https://doi.org/10.1016/j.bspc.2020.102041.
Hekler, A. et al. Effects of label noise on deep learning-based skin cancer classification. Frontiers in Medicine, v. 7, p. 177, 2020. Doi: https://doi.org/10.3389/fmed.2020.00177.
Higgins, S. et al. Clinical presentations of melanoma in African Americans, Hispanics, and Asians. Dermatologic Surgery, v. 45, n. 6, p. 791-801, 2019. Doi: https://doi.org/10.1097/dss.0000000000001759.
Jackson, B. A. Skin cancer in skin of color. In: MacFarlane, D. F. (ed.). Skin Cancer Management: A practical approach. New York: Springer, 2010. p. 217-223. Doi: https://doi.org/10.1007/978-0-387-88495-0_16.
Jafari, M. et al. Extraction of skin lesions from non-dermoscopic images using deep learning. ArXiv.Org, v. 12, n. 6, 2016. Doi: https://doi.org/10.48550/arXiv.1609.02374.
Jiang, S.; Li, H.; Jin, Z. A Visually interpretable deep learning framework for histopatho-logical image-based skin cancer diagnosis. IEEE Journal of Biomedical and Health Informatics, v. 25, n. 5, p. 1483-1494, 2021.
Jinnai, S. et al. The development of a skin cancer classification system for pigmented skin lesions using deep learning. Biomolecules, v. 10, n. 8, p. 1123, 2020. Doi: https://doi.org/10.3390/biom10081123.
Kadampur, M. A.; Al Riyaee, S. Skin cancer detection: Applying a deep learning based model driven architecture in the cloud for classifying dermal cell images. Informatics in Medicine Unlocked, v. 18, n. 12, 2020. Doi: https://doi.org/10.1016/j.imu.2019.100282.
Kanani, P.; Padole, M. Deep learning to detect skin cancer using google colab. International Journal of Engineering and Advanced Technology, v. 8, n. 6, p. 2176-2183, 2019. Doi: https://doi.org/10.35940/ijeat.F8587.088619.
Khan, M. A. et al. Skin lesion segmentation and multiclass classification using deep learning features and improved moth flame optimization. Diagnostics, v. 11, n. 5, p. 811, 2021. Doi: https://doi.org/10.3390/diagnostics11050811.
Kora, P. et al. Transfer learning techniques for medical image analysis: A review. Biocybernetics and Biomedical Engineering, v. 42, n. 1, p. 79-107, 2022.
Li, Y.; Shen, L. Skin lesion analysis towards melanoma detection using deep learning network. Sensors, v. 18, n. 2, p. 556, 2018. Doi: https://doi.org/10.3390/s18020556.
Lima, G. L. S. Identificação da psoríase através de dispositivos móveis usando redes neurais convolucionais profundas. 2019. 111 f. Dissertação (Mestrado em Sistemas de Informação) - Instituto Politécnico de Bragança, Bragança, Portugal, 2019.
Liu, Y. et al. A deep learning system for differential diagnosis of skin diseases. ArXiv.Org, v. 26, n. 6, p. 900-908, 2019. Doi: https://doi.org/10.1038/s41591-020-0842-3.
Lobo, L. C. Inteligência artificial e medicina. Revista Brasileira de Educação Médica, v. 41, p. 185-193, 2017. Machado, F. C. L. Application of deep learning methods to detect global patterns in dermoscopic images and aid the skin cancer diagnosis. 2021. 30 f. Monografia (Graduação em Ciência da Computação) − Universidade Federal de Ouro Preto, Ouro Preto, 2021.
Mamoshina, P. et al. A. Applications of deep learning in biomedicine: Molecular pharmaceutics. American Chemical Society, v. 13, n. 5, p. 1445-1454, 2016. Doi: https://doi.org/10.1021/acs.molpharmaceut.5b00982
Maqsood, S.; Damaševičius, R. Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare. Neural Networks, v. 160, p. 238-258, 2023.
Minagawa, A. et al. Dermoscopic diagnostic performance of Japanese dermatologists for skin tumors differs by patient origin: A deep learning convolutional neural network closes the gap. Journal of Dermatology, v. 8, n. 2, p. 232-236. 2020. Doi: https://doi.org/10.1111/1346-8138.15640.
Mohamed, A.; Mohamed, W.; Zekry, A. H. Deep learning can improve early skin cancer detection. International Journal of Electronics and Telecommunications, v. 65, n. 3, p. 507-513, 2019.
Molina-Molina, E. O.; Solorza-Calderón, S.; Álvarez-Borrego, J. Classification of Dermos-copy Skin Lesion Color-Images Using Fractal-Deep Learning Features. Applied Sciences, v. 10, n. 17, p. 5954, 2020. Doi: https://doi.org/10.3390/app10175954.
Moreno, J.; Caicedo, J.; González, F. A kernel-based multi-feature image representation for histopathology image classification. Acta Biológica Colombiana, v. 15, n. 3, p. 251-260, 2010.
Morid, M. A.; Borjali, A.; Del Fiol, G. A scoping review of transfer learning research on medical image analysis using ImageNet. Computers in Biology and Medicine, v. 128, 104115, 2021. Doi: https://doi.org/10.1016/j.compbiomed.2020.104115.
Nascimento, E. L. L.; Viera, A. F. G. Contributions and limitations about the use of deep learning for skin diagnosis: A review. Switzerland: Springer Nature, 2022. p. 133-149.
Neves, L. A. P.; Vieira Neto, H.; Gonzaga, A. Avanços em visão computacional. Curitiba: Omnipax, 2012.
Olsen, T. et al. Diagnostic performance of deep learning algorithms applied to three common diagnoses in dermatopathology. Journal of Pathology Informatics, v. 9, n. 1, p. 32, 2018.
Olveres, J. et al. What is new in computer vision and artificial intelligence in medical image analysis applications. Quantitative Imaging in Medicine and Surgery, v. 11, n. 8, p. 3830, 2021.
Pacheco, A. G. C.; Krohling, R. An attention-based mechanism to combine images and metadata in deep learning models applied to skin cancer classification. IEEE Journal of Biomedical and Health Informatics, v. 25, n. 9, p. 1, 2021.
Padovese, V. et al. Skin cancer risk assessment in dark skinned immigrants: The role of social determinants and ethnicity. Ethnicity and Health, v. 23, n. 6, p. 649-658, 2018. Doi: https://doi.org/10.1080/13557858.2017.1294657.
Passos, R. P.; Junior, G. D. B. V. Inteligência artificial nas ciências da saúde. Revista CPAQV, v. 10, n. 1, p. 2, 2018.
Penacci, F. A. Perfil das adolescentes privadas de liberdade no interior do Estado de São Paulo. 2017. Tese (Doutorado em Medicina) – Universidade Estadual Paulista, São Paulo, 2017.
Premaladha, J.; Ravichandran, K. Novel approaches for diagnosing melanoma skin lesions through supervised and deep learning algorithms. Journal of Medical Systems, v. 40, n. 4, p. 1-12, 2016. Doi: https://doi.org/10.1007/s10916-016-0460-2.
Ravikumar, N.; Maier, A. SkinNet: A deep learning framework for skin lesion segmentation. [S. l.]: IEEE, 2018. Doi: https://doi.org/10.13140/RG.2.2.26648.75521.
Ribeiro, A. L. L. Discriminação em algoritmos de inteligência artificial: uma análise acerca da LGPD como instrumento normativo mitigador de vieses discriminatórios. 2021. Trabalho de Conclusão de Curso (Bacharel em Direito) – Universidade Federal do Ceará, Fortaleza, 2021.
Rocha, C. J.; Porto, L. V.; Abaurre, H. E. Discriminação algorítmica no trabalho digital. Revista de Direitos Humanos e Desenvolvimento Social, v.1, e205201, 2020.
Rodrigues, D. A. et al. A new approach for classification skin lesion based on transfer learning, deep learning, and IoT system. Pattern Recognition Letters, v. 136, p. 8-15, 2020. Doi: https://doi.org/10.1016/j.patrec.2020.05.019.
Rong, G. et al. Artificial intelligence in healthcare: Review and prediction case studies. Engineering, v, 6, n. 3, p. 291-301, 2020. Doi: https://doi.org/10.1016/j.eng.2019.08.015.
Rother, E. T. Revisão sistemática X revisão narrativa. Acta Paulista de Enfermagem, v. 20, n. 2, p. vii-viii, 2007. [Editorial]. https://doi.org/10.1590/S0103-21002007000200001.
Seeja, R. D.; Suresh, A. Deep learning based skin lesion segmentation and classification of melanoma using Support Vector Machine (SVM). Asian Pacific Journal of Cancer Prevention, v. 20, n. 5, p. 1555-1561, 2019.
Serte, S.; Demirel, H. Gabor wavelet-based deep learning for skin lesion classification. Computers in Biology and Medicine, v. 113, p. 103423, 2019. Doi: https://doi.org/10.1016/j.compbiomed.2019.103423.
Serte, S.; Demirel, H. Wavelet-based deep learning for skin lesion classification. IET Image Processing, v. 14, n. 4, p. 720-726, 2020.
Sherif, F.; Mohamed, W. A.; Mohra, A. S. Skin lesion analysis toward melanoma detection using deep learning techniques. International Journal of Electronics and Telecommunications, v. 65, n. 4, p. 597-602, 2019. Doi: https://doi.org/10.3390/s18020556.
Silva, T. Visão computacional e racismo algorítmico: branquitude e opacidade no aprendizado de máquina. Revista da Associação Brasileira de Pesquisadores/as Negros/as, v. 12, n. 31, p. 428-448, 2020.
Singh, C. Medical imaging using deep learning models. European Journal of Engineering and Technology Research, v. 6, n. 5, p. 156-167, 2021.
Song, L. et al. An end-to-end multi-task deep learning framework for skin lesion analysis. IEEE Journal of Biomedical and Health Informatics, v. 24, n. 10, p. 2912-2921, 2020.
Srinivasu, P. N. et al. Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM. Sensors (Basel), v. 21, n. 8, p. 2852, 2021. Doi: https://doi.org/10.3390/s21082852.
Tan, T. Y.; Zhang, L.; Lim, C. P. Intelligent skin cancer diagnosis using improved particle swarm optimization and deep learning models. Applied Soft Computing, v. 84, n. 4, p. 105725, 2019. Doi: https://doi.org/10.1016/j.asoc.2019.105725.
Taylor, S. C. et al. Health disparities in arthritis and musculoskeletal and skin diseases: The dermatology session: National Institute of Arthritis and Musculoskeletal and Skin Diseases, Bethesda, Maryland, December 15-16, 2000. Journal of the American Academy of Dermatology, v. 47, n. 5, p. 770-773, 2002. Doi: https://doi.org/10.1067/mjd.2002.124691.
Thieme, A. H. et al. A deep-learning algorithm to classify skin lesions from mpox virus infection. Nature Medicine, v. 29, n. 3, p. 738-747, 2023.
Thomsen, K. et al. Deep learning for diagnostic binary classification of multiple-lesion skin diseases. Frontiers in Medicine, v. 7, p. 1-7, 2020. Doi: https://doi.org/10.3389/fmed.2020.574329.
Torres, V. et al. Refining the ideas of “ethnic” skin. Anais Brasileiros de Dermatologia, v. 92, n. 2, p. 221-225, 2017. Doi: https://doi.org/10.1590/abd1806-4841.20174846.
Tschandl, P. et al. Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: An open, web-based, international, diagnostic study. The Lancet Oncology, v. 20, n. 7, p. 938-947, 2019. Doi: https://doi.org/10.1016/S1470-2045(19)30333-X.
Tschandl, P.; Rosendahl, C.; Kittler, H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, v. 14, n. 5, p. 180161, 2018. Doi: https://doi.org/10.1038/sdata.2018.161.
Tsuneki, M. Deep learning models in medical image analysis. Journal of Oral Biosciences, v. 64, n. 3, p. 312-320, 2022.
Viknesh, C. K. et al. Detection and classification of melanoma skin cancer using image processing technique. Diagnostics, v. 13, n. 21, p. 3313, 2023. Doi: https://doi.org/10.3390/diagnostics13213313.
Wang, H. et al. Assessment of deep learning using nonimaging infor-mation and sequential medical records to develop a prediction model for nonmelanoma skin cancer. JAMA Dermatology, v. 155, n. 11, p. 1277-1283, 2019. Doi: https://doi.org/10.1001/jamadermatol.2019.2335.
Wei, L.; Ding, K.; Hu, H. Automatic skin cancer detection in dermoscopy images based on ensemble lightweight deep learning network. IEEE Access, v. 8, p. 99633-99647, 2020. Doi: https://doi.org/10.1109/. ACCESS.2020.2997710.
Wernick, M. et al. Machine learning in medical imaging. IEEE Signal Processing Magazine, v. 27, p. 25-38, 2010. Doi: https://doi.org/10.1109/MSP.2010.936730.
Yap, J.; Yolland, W.; Tschandl, P. Multimodal skin lesion classification using deep learning. Experimental Dermatology, v. 27, n. 11, p. 1261-1267, 2018.
Zhu, C. Y. et al. A deep learning based framework for diagnosing multiple skin diseases in a clinical environment. Frontiers in Medicine, v. 8, p. 1-13, 2021. Doi: https://doi.org/10.3389/fmed.2021.626369.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Transinformação
This work is licensed under a Creative Commons Attribution 4.0 International License.