Quantifying the effects of segmentation in image classification for melanoma recognition

• Rafael Luz Araújo IFPI / UFPI
• Daniel de S. Luz IFPI / UFPI
• Bruno Vicente de Lima IFMA
• Júlio V. M. Marques UFPI
• Rodrigo de M. S. Veras UFPI
• Antônio O. de C. Filho UFPI
• Flávio H. D. Araújo UFPI
• Romuere Rodrigues Veloso e Silva UFPI

DOI: https://doi.org/10.5753/eniac.2024.245228

Resumo

Melanoma remains the leading cause of skin cancer-related deaths worldwide, emphasizing the critical need for early detection to enhance survival rates. Computational methods are pivotal in aiding its diagnosis through medical imaging, necessitating accurate lesion segmentation to facilitate effective interpretation. Our study investigates the comparative efficacy of skin lesion classification with and without segmentation, leveraging pre-trained convolutional neural networks (CNNs) and CapsNet architectures. Findings underscore CNNs’ superiority, highlighting segmentation’s beneficial impact on their classification performance, while CapsNet exhibits a degree of independence from segmentation.

Palavras-chave: Melanoma, Dermatoscopic Images, Convolutional Neural Network, Capsule Network, Transfer Learning, Fine-tuning

Referências

Al-Masni, M. A., Al-Antari, M. A., Choi, M.-T., Han, S.-M., and Kim, T.-S. (2018). Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Computer methods and programs in biomedicine, 162:221–231.

Al Nazi, Z. and Abir, T. A. (2020). Automatic skin lesion segmentation and melanoma detection: Transfer learning approach with u-net and dcnn-svm. In Proceedings of International Joint Conference on Computational Intelligence, pages 371–381. Springer.

Alom, M. Z., Aspiras, T., Taha, T. M., and Asari, V. K. (2019). Skin cancer segmentation and classification with nabla-n and inception recurrent residual convolutional networks. arXiv preprint arXiv:1904.11126.

Amin, J., Sharif, A., Gul, N., Anjum, M. A., Nisar, M. W., Azam, F., and Bukhari, S. A. C. (2020). Integrated design of deep features fusion for localization and classification of skin cancer. Pattern Recognition Letters, 131:63–70.

Araújo, R. L., de Araújo, F. H., and Silva, R. R. (2021). Automatic segmentation of melanoma skin cancer using transfer learning and fine-tuning. Multimedia Systems, pages 1–12.

Argenziano, G. and Soyer, H. P. (2001). Dermoscopy of pigmented skin lesions–a valuable tool for early. The lancet oncology, 2(7):443–449.

Barata, C., Ruela, M., Francisco, M., Mendonça, T., and Marques, J. S. (2013). Two systems for the detection of melanomas in dermoscopy images using texture and color features. IEEE Systems Journal, 8(3):965–979.

Bi, L., Kim, J., Ahn, E., Feng, D., and Fulham, M. (2016). Automatic melanoma detection via multi-scale lesion-biased representation and joint reverse classification. In 2016 IEEE 13th international symposium on biomedical imaging (ISBI), pages 1055–1058. IEEE.

Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258.

Codella, N., Rotemberg, V., Tschandl, P., Celebi, M. E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., Marchetti, M., et al. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368.

Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1):37–46.

DermIS (2020). Dermatology information system. [link]. Online; accessed 25 June 2020.

Giotis, I., Molders, N., Land, S., Biehl, M., Jonkman, M. F., and Petkov, N. (2015). Med-node: A computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert systems with applications, 42(19):6578–6585.

Han, S. S., Kim, M. S., Lim, W., Park, G. H., Park, I., and Chang, S. E. (2018). Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. Journal of Investigative Dermatology, 138(7):1529–1538.

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.

Hosny, K. M., Kassem, M. A., and Foaud, M. M. (2019). Classification of skin lesions using transfer learning and augmentation with alex-net. PloS one, 14(5):e0217293.

Hosny, K. M., Kassem, M. A., and Foaud, M. M. (2020). Skin melanoma classification using roi and data augmentation with deep convolutional neural networks. Multimedia Tools and Applications, 79(33):24029–24055.

Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.

IARC (2020). Latest global cancer data: Cancer burden rises to 19.3 million new cases and 10.0 million cancer deaths in 2020. International Agency for Research on Cancer.

Jafari, M. H., Samavi, S., Karimi, N., Soroushmehr, S. M. R., Ward, K., and Najarian, K. (2016). Automatic detection of melanoma using broad extraction of features from digital images. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 1357–1360. IEEE.

Karabulut, E. and Ibrikci, T. (2016). Texture analysis of melanoma images for computer-aided diagnosis. In Int. Conference on Intelligent Computing, Computer Science & Information Systems (ICCSIS 16), volume 2, pages 26–29.

Kassani, S. H. and Kassani, P. H. (2019). A comparative study of deep learning architectures on melanoma detection. Tissue and Cell, 58:76–83.

Khan, M. Q., Hussain, A., Rehman, S. U., Khan, U., Maqsood, M., Mehmood, K., and Khan, M. A. (2019). Classification of melanoma and nevus in digital images for diagnosis of skin cancer. IEEE Access, 7:90132–90144.

Mendonca, T., Celebi, M., Mendonca, T., and Marques, J. (2015). Ph2: A public database for the analysis of dermoscopic images. In Dermoscopy image analysis. CRC Press.

Milton, M. A. A. (2019). Automated skin lesion classification using ensemble of deep neural networks in isic 2018: Skin lesion analysis towards melanoma detection challenge. arXiv preprint arXiv:1901.10802.

Moura, N., Veras, R., Aires, K., Machado, V., Silva, R., Araújo, F., and Claro, M. (2019). Abcd rule and pre-trained cnns for melanoma diagnosis. Multimedia Tools and Applications, 78(6):6869–6888.

Namozov, A. and Im Cho, Y. (2018). Convolutional neural network algorithm with parameterized activation function for melanoma classification. In 2018 International Conference on Information and Communication Technology Convergence (ICTC), pages 417–419. IEEE.

Pal, A., Ray, S., and Garain, U. (2018). Skin disease identification from dermoscopy images using deep convolutional neural network. arXiv preprint arXiv:1807.09163.

Reddy, N. D. (2018). Classification of dermoscopy images using deep learning. arXiv preprint arXiv:1808.01607.

Rodrigues, D. d. A., Ivo, R. F., Satapathy, S. C., Wang, S., Hemanth, J., and Reboucas Filho, P. P. (2020). A new approach for classification skin lesion based on transfer learning, deep learning, and iot system. Pattern Recognition Letters, 136:8–15.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.

Saba, T., Khan, M. A., Rehman, A., and Marie-Sainte, S. L. (2019). Region extraction and classification of skin cancer: A heterogeneous framework of deep cnn features fusion and reduction. Journal of medical systems, 43(9):1–19.

Sabour, S., Frosst, N., and Hinton, G. E. (2017). Dynamic routing between capsules. arXiv preprint arXiv:1710.09829.

Sarkar, R., Chatterjee, C. C., and Hazra, A. (2019). Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network. IET Image Processing, 13(12):2130–2142.

SCF (2021). Melanoma overview: A dangerous skin cancer. Disponível em: [link]. Accessed on: 15/02/2021.

Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Tang, P., Liang, Q., Yan, X., Xiang, S., Sun, W., Zhang, D., and Coppola, G. (2019). Efficient skin lesion segmentation using separable-unet with stochastic weight averaging. Computer methods and programs in biomedicine, 178:289–301.

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.