PPM-DeepLab: Módulo de Pirâmide de Pooling como Codificador da rede DeepLabV3+ para Segmentação de Rins, Cistos e Tumores Renais

• Caio Eduardo Falcão Matos UFMA
• Marcus Vinicius Silva Lima Oliveira UFMA
• João Otávio Bandeira Diniz IFMA
• Arthur Guilherme Santos Fernandes UFMA
• Geraldo Braz Junior UFMA
• Anselmo Cardoso de Paiva UFMA

DOI: https://doi.org/10.5753/sbcas.2023.229611

Abstract

Kidney cancer ranks among the leading causes of cancer-related deaths worldwide. Early detection and diagnosis are crucial in the fight against this disease. Recently, convolutional neural networks (CNNs) have demonstrated their effectiveness in semantic segmentation tasks. In this study, we introduce PPM-DeepLab, a novel architectural model designed for the segmentation of kidneys, cysts, and tumors in computed tomography (CT) images. Specifically, we explored the Pyramid Pooling Module (PPM) to enhance the DeepLabv3+ network by incorporating contextual information from various scales. Our proposed model achieved promising results, with Dice indices of 94.89% for kidneys, 83.95% for cysts, and 84.62% for renal tumors.

References

Abdelrahman, A. and Viriri, S. (2022). Kidney tumor semantic segmentation using deep learning: A survey of state-of-the-art. Journal of Imaging, 8(3):55.

ACS - American Cancer Society (2023a). Cancer staging. Disponível em [link].

ACS - American Cancer Society (2023b). Key statistics. Disponível em [link].

Baffa, M., Coelho, A., and Conci, A. (2021). Segmentação de imagens infravermelhas para detecção do câncer de mama utilizando u-net cnn. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 119–128, Porto Alegre, RS, Brasil. SBC.

Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4):834–848.

Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pages 801–818.

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.

Diniz, J., Ferreira, J., Silva, G., Quintanilha, D., Silva, A., and Paiva, A. (2021). Segmentação de coração em tomografias computadorizadas utilizando atlas probabilístico e redes neurais convolucionais. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 83–94, Porto Alegre, RS, Brasil. SBC.

Fleiss, J. L., Levin, B., Paik, M. C., et al. (1981). The measurement of interrater agreement. Statistical methods for rates and proportions, 2(212-236):22–23.

Fonseca, P., Araújo, A., Almeida, J., and Júnior, G. B. (2022). Treinando rede neural profunda com divisão proporcional de imagens para segmentação de estruturas da retina. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 1–12, Porto Alegre, RS, Brasil. SBC.

George, Y. (2022). A coarse-to-fine 3d u-net network for semantic segmentation of kidney ct scans. In Kidney and Kidney Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings, pages 137–142. Springer.

Golts, A., Khapun, D., Shats, D., Shoshan, Y., and Gilboa-Solomon, F. (2022). An ensemble of 3d u-net based models for segmentation of kidney and masses in ct scans. In Kidney and Kidney Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings, pages 103–115. Springer.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.

Heller, N., Isensee, F., Maier-Hein, K. H., Hou, X., Xie, C., Li, F., Nan, Y., Mu, G., Lin, Z., Han, M., et al. (2021). The state of the art in kidney and kidney tumor segmentation in contrast-enhanced ct imaging: Results of the kits19 challenge. Medical image analysis, 67:101821.

INCA Instituto Nacional do Câncer (2022). Ministério da saúde amplia tratamento para câncer renal. Disponível em [link].

INITIATIVE, N. I. T. N. (2000). Neuroimaging informatics technology initiative. Disponível em: https://nifti.nimh.nih.gov/. Acesso em: 1 de dez. de 2022.

Oliveira, M., Matos, C., Júnior, G. B., Paiva, A., Almeida, J., Costa, G., Levy, M., and Freitas, M. (2022). Ppm-unet: Uma rede neural convolucional para a segmentação de rins em imagens de tc. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 268–276, Porto Alegre, RS, Brasil. SBC.

Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., ter Haar Romeny, B., Zimmerman, J. B., and Zuiderveld, K. (1987). Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing, 39(3):355–368.

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, Munich, Germany. Springer.

Smith, R. A., Cokkinides, V., and Eyre, H. J. (2005). American cancer society guidelines for the early detection of cancer, 2005. CA: a cancer journal for clinicians, 55(1):31–44.

Sun, P., Mo, Z., Hu, F., Song, X., Mo, T., Yu, B., Zhang, Y., and Chen, Z. (2022). Segmentation of kidney mass using agdenseu-net 2.5 d model. Computers in Biology and Medicine, 150:106223.

Teixeira, J., Rezende, M., Diniz, D., Carneiro, C., Luz, E., Souza, M., Ushizima, D., Medeiros, F., and Bianchi, A. (2022). Segmentação automática de núcleos cervicais em imagens de papanicolaou. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 346–357, Porto Alegre, RS, Brasil. SBC.

WCRF - World Cancer Research Fund Internacional (2023). Kidney cancer statistics. Disponível em [link].

WHO - World Health Organization (2023). Câncer visão geral. Disponível em [link].

Wu, M. and Liu, Z. (2022). Less is more: Contrast attention assisted u-net for kidney, tumor and cyst segmentations. In Kidney and Kidney Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings, pages 46–52. Springer.

Yang, X., Zhang, J., Zhang, J., and Xia, Y. (2022). Transfer learning for kits21 challenge. In Kidney and Kidney Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings, pages 158–163. Springer.

Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017). Pyramid scene parsing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2881–2890, Honolulu, HI, USA. IEEE.

Zhao, Z., Chen, H., and Wang, L. (2022). A coarse-to-fine framework for the 2021 kidney and kidney tumor segmentation challenge. In Kidney and Kidney Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings, pages 53–58. Springer.