Evaluating Deep Neural Skin Cancer Classifiers With Multiple Images Inputs
Resumo
O câncer de pele representa um terço de todos os cânceres diagnosticados globalmente. Embora tenha uma taxa de mortalidade geralmente baixa, o diagnóstico tardio continua sendo o principal fator para complicações. Para mitigar esses riscos, sistemas de Diagnóstico Assistido por Computador (CAD) vem sendo desenvolvidos para fornecer métodos de diagnóstico mais acessíveis e oportunos. Embora os CADs vem desmostrando resultados consistentes, a maioria dos sistemas existentes se baseia em uma única imagem da lesão, e o impacto do uso de múltiplas imagens de uma mesma lesão não vem sendo estudado. Este trabalho visa investigar como a incorporação de múltiplas imagens afeta a eficiência e a precisão dos sistemas de CAD. Especificamente, foi avaliado o desempenho de três diferentes modelos de aprendizado profundo integrados em uma estratégia de stacking que processa múltiplas entradas de imagem de uma mesma lesão. De maneira geral, foi observado aumento de até 6% na acurácia balanceada, sem adicionar processamento significativos de treinamento ou de teste aos modelos existentes.Referências
Brinker, T. J., Hekler, A., Utikal, J. S., Grabe, N., Schadendorf, D., Klode, J., Berking, C., Steeb, T., Enk, A. H., and von Kalle, C. (2018). Skin cancer classification using convolutional neural networks: systematic review. Journal of Medical Internet Research, 20(10):e11936.
Celebi, M. E., Codella, N., and Halpern, A. (2019). Dermoscopy image analysis: overview and future directions. IEEE Journal of Biomedical and Health Informatics, 23(2):474–478.
Chen, R. H., Snorrason, M., Enger, S. M., Mostafa, E., Ko, J. M., Aoki, V., and Bowling, J. (2016). Validation of a skin-lesion image-matching algorithm based on computer vision technology. Telemedicine and e-Health, 22(1):45–50.
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., and Halpern, A. (2017). Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). arXiv:1710.05006.
Cui, C., Yang, H., Wang, Y., Zhao, S., Asad, Z., Coburn, L. A., Wilson, K. T., Landman, B. A., and Huo, Y. (2023). Deep multimodal fusion of image and non-image data in disease diagnosis and prognosis: a review. Progress in Biomedical Engineering, 5(2):022001.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.
Derrac, J., García, S., Molina, D., and Herrera, F. (2011). A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation, 1(1):3–18.
Feng, H., Berk-Krauss, J., Feng, P. W., and Stein, J. A. (2018). Comparison of dermatologist density between urban and rural counties in the united states. JAMA Dermatology, 154:1265—-1271.
Gessert, N., Nielsen, M., Shaikh, M., Werner, R., and Schlaefer, A. (2020). Skin lesion classification using ensembles of multi-resolution efficientnets with meta data. MethodsX, pages 1–8.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 770778.
Hernández-Pérez, C., Combalia, M., Podlipnik, S., Codella, N. C., Rotemberg, V., Halpern, A. C., Reiter, O., Carrera, C., Barreiro, A., Helba, B., Puig, S., Vilaplana, V., and Malvehy, J. (2024). Bcn20000: Dermoscopic lesions in the wild. Scientific Data, 11(1):641.
INCA (2023). Incidência do câncer no Brasil. Instituto Nacional do Câncer (INCA). Available on: [link]. Last access: 11 Mar 2025.
Kumar, A., Kumar, M., Bhardwaj, V. P., Kumar, S., and Selvarajan, S. (2024). A novel skin cancer detection model using modified finch deep cnn classifier model. Scientific Reports, 14(1):11235.
Li, W., Zhuang, J., Wang, R., Zhang, J., and Zheng, W.-S. (2020). Fusing metadata and dermoscopy images for skin disease diagnosis. In IEEE International Symposium on Biomedical Imaging, pages 1996–2000.
Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., Gupta, V., Singh, N., Natarajan, V., Hofmann-Wellenhof, R., Corrado, G. S., Peng, L. H., Webster, D. R., Ai, D., Huang, S. J., Liu, Y., Dunn, R. C., and Coz, D. (2020). A deep learning system for differential diagnosis of skin diseases. Nature Medicine, 26(6):900–908.
Maqsood, S. and Damaševičius, R. (2023). Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare. Neural Networks, 160:238–258.
Pacheco, A. G. and Krohling, R. A. (2020a). The impact of patient clinical information on automated skin cancer detection. Computers in Biology and Medicine, 116:103545.
Pacheco, A. G. and Krohling, R. A. (2020b). Learning dynamic weights for an ensemble of deep models applied to medical imaging classification. In IEEE International Joint Conference on Neural Networks, pages 1–8.
Pacheco, A. G., Lima, G. R., Salomão, A. S., Krohling, B., Biral, I. P., de Angelo, G. G., Alves Jr, F. C., Esgario, J. G., Simora, A. C., Castro, P. B., et al. (2020). PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones. Data in Brief, 32:1–10.
Pacheco, A. G. C. and Krohling, R. (2021). 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. In press.
Pavlyshenko, B. (2018). Using stacking approaches for machine learning models. In 2018 IEEE Second International Conference on Data Stream Mining Processing (DSMP), pages 255–258.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In IEEE Conference on Computer Vision and Pattern Pecognition, pages 4510–4520.
Sinz, C., Tschandl, P., Rosendahl, C., Akay, B. N., Argenziano, G., Blum, A., Braun, R. P., Cabo, H., Gourhant, J.-Y., Kreusch, J., et al. (2017). Accuracy of dermatoscopy for the diagnosis of nonpigmented cancers of the skin. Journal of the American Academy of Dermatology, 77(6):1100–1109.
Souza, L., Pacheco, A., Angelo, G., Oliveira-Santos, T., Palm, C., and Papa, J. (2024). Liwterm: A lightweight transformer-based model for dermatological multimodal lesion detection. In Anais da XXXVII Conference on Graphics, Patterns and Images, Porto Alegre, RS, Brasil. SBC.
Tanaka, M., Saito, A., Shido, K., Fujisawa, Y., Yamasaki, K., Fujimoto, M., Murao, K., Ninomiya, Y., Satoh, S., and Shimizu, A. (2021). Classification of large-scale image database of various skin diseases using deep learning. International Journal of Computer Assisted Radiology and Surgery, 16(11):1875–1887.
Tschandl, P., Rosendahl, C., and Kittler, H. (2018). The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, 5:180161.
Tuncer, T., Barua, P. D., Tuncer, I., Dogan, S., and Acharya, U. R. (2024). A lightweight deep convolutional neural network model for skin cancer image classification. Applied Soft Computing, page 111794.
WHO (2025). Skin Cancer. World Health Organization (WHO). Available on: [link]. Last access: 11 Mar 2025.
Celebi, M. E., Codella, N., and Halpern, A. (2019). Dermoscopy image analysis: overview and future directions. IEEE Journal of Biomedical and Health Informatics, 23(2):474–478.
Chen, R. H., Snorrason, M., Enger, S. M., Mostafa, E., Ko, J. M., Aoki, V., and Bowling, J. (2016). Validation of a skin-lesion image-matching algorithm based on computer vision technology. Telemedicine and e-Health, 22(1):45–50.
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., and Halpern, A. (2017). Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). arXiv:1710.05006.
Cui, C., Yang, H., Wang, Y., Zhao, S., Asad, Z., Coburn, L. A., Wilson, K. T., Landman, B. A., and Huo, Y. (2023). Deep multimodal fusion of image and non-image data in disease diagnosis and prognosis: a review. Progress in Biomedical Engineering, 5(2):022001.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.
Derrac, J., García, S., Molina, D., and Herrera, F. (2011). A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation, 1(1):3–18.
Feng, H., Berk-Krauss, J., Feng, P. W., and Stein, J. A. (2018). Comparison of dermatologist density between urban and rural counties in the united states. JAMA Dermatology, 154:1265—-1271.
Gessert, N., Nielsen, M., Shaikh, M., Werner, R., and Schlaefer, A. (2020). Skin lesion classification using ensembles of multi-resolution efficientnets with meta data. MethodsX, pages 1–8.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 770778.
Hernández-Pérez, C., Combalia, M., Podlipnik, S., Codella, N. C., Rotemberg, V., Halpern, A. C., Reiter, O., Carrera, C., Barreiro, A., Helba, B., Puig, S., Vilaplana, V., and Malvehy, J. (2024). Bcn20000: Dermoscopic lesions in the wild. Scientific Data, 11(1):641.
INCA (2023). Incidência do câncer no Brasil. Instituto Nacional do Câncer (INCA). Available on: [link]. Last access: 11 Mar 2025.
Kumar, A., Kumar, M., Bhardwaj, V. P., Kumar, S., and Selvarajan, S. (2024). A novel skin cancer detection model using modified finch deep cnn classifier model. Scientific Reports, 14(1):11235.
Li, W., Zhuang, J., Wang, R., Zhang, J., and Zheng, W.-S. (2020). Fusing metadata and dermoscopy images for skin disease diagnosis. In IEEE International Symposium on Biomedical Imaging, pages 1996–2000.
Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., Gupta, V., Singh, N., Natarajan, V., Hofmann-Wellenhof, R., Corrado, G. S., Peng, L. H., Webster, D. R., Ai, D., Huang, S. J., Liu, Y., Dunn, R. C., and Coz, D. (2020). A deep learning system for differential diagnosis of skin diseases. Nature Medicine, 26(6):900–908.
Maqsood, S. and Damaševičius, R. (2023). Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare. Neural Networks, 160:238–258.
Pacheco, A. G. and Krohling, R. A. (2020a). The impact of patient clinical information on automated skin cancer detection. Computers in Biology and Medicine, 116:103545.
Pacheco, A. G. and Krohling, R. A. (2020b). Learning dynamic weights for an ensemble of deep models applied to medical imaging classification. In IEEE International Joint Conference on Neural Networks, pages 1–8.
Pacheco, A. G., Lima, G. R., Salomão, A. S., Krohling, B., Biral, I. P., de Angelo, G. G., Alves Jr, F. C., Esgario, J. G., Simora, A. C., Castro, P. B., et al. (2020). PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones. Data in Brief, 32:1–10.
Pacheco, A. G. C. and Krohling, R. (2021). 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. In press.
Pavlyshenko, B. (2018). Using stacking approaches for machine learning models. In 2018 IEEE Second International Conference on Data Stream Mining Processing (DSMP), pages 255–258.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In IEEE Conference on Computer Vision and Pattern Pecognition, pages 4510–4520.
Sinz, C., Tschandl, P., Rosendahl, C., Akay, B. N., Argenziano, G., Blum, A., Braun, R. P., Cabo, H., Gourhant, J.-Y., Kreusch, J., et al. (2017). Accuracy of dermatoscopy for the diagnosis of nonpigmented cancers of the skin. Journal of the American Academy of Dermatology, 77(6):1100–1109.
Souza, L., Pacheco, A., Angelo, G., Oliveira-Santos, T., Palm, C., and Papa, J. (2024). Liwterm: A lightweight transformer-based model for dermatological multimodal lesion detection. In Anais da XXXVII Conference on Graphics, Patterns and Images, Porto Alegre, RS, Brasil. SBC.
Tanaka, M., Saito, A., Shido, K., Fujisawa, Y., Yamasaki, K., Fujimoto, M., Murao, K., Ninomiya, Y., Satoh, S., and Shimizu, A. (2021). Classification of large-scale image database of various skin diseases using deep learning. International Journal of Computer Assisted Radiology and Surgery, 16(11):1875–1887.
Tschandl, P., Rosendahl, C., and Kittler, H. (2018). The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, 5:180161.
Tuncer, T., Barua, P. D., Tuncer, I., Dogan, S., and Acharya, U. R. (2024). A lightweight deep convolutional neural network model for skin cancer image classification. Applied Soft Computing, page 111794.
WHO (2025). Skin Cancer. World Health Organization (WHO). Available on: [link]. Last access: 11 Mar 2025.
Publicado
09/06/2025
Como Citar
MAGALHÃES, Afonso S.; SOUZA JR., Luis A.; PACHECO, André G.C..
Evaluating Deep Neural Skin Cancer Classifiers With Multiple Images Inputs. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 25. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 772-782.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2025.7750.
