An automatic method for prostate segmentation on 3D MRI scans using local phylogenetic indexes and XGBoost

• Giovanni L. F. da Silva UFMA
• Francisco Y. C. de Oliveira UFMA
• João O. B. Diniz UFMA
• Petterson S. Diniz UFMA
• Darlan B. P. Quintanilha UFMA
• Aristófanes C. Silva UFMA
• Anselmo C. de Paiva UFMA
• Elton A. A. de Cavalcanti UFMA

DOI: https://doi.org/10.5753/sbcas.2021.16062

Resumo

The detection, diagnosis, and treatment of prostate cancer depends on the correct determination of the prostate anatomy. In current practice, the prostate segmentation is performed manually by a radiologist, which is extremely time-consuming that demands experience and concentration. Therefore, this paper proposes an automatic method for prostate segmentation on 3D magnetic resonance imaging scans using a superpixel technique, phylogenetic indexes, and an optimized XGBoost algorithm. The proposed method has been evaluated on the Prostate 3T and PROMISE12 databases presenting a dice similarity coefficient of 84.48% and a volumetric similarity of 95.91%, demonstrating the high-performance potential of the proposed method.

Referências

ACS (2021). American cancer society: Key statistics for prostate cancer. https://www.cancer.org/cancer/prostate-cancer/about/key-statistics.html. Accessed: 2021-03-14.

Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.

Chen, Z., Tian, Z., Li, X., Zhang, Y., and Dormer, J. D. (2020). Exploiting condent information for weakly supervised prostate segmentation based on image-level labels. Image-Guided Procedures, Robotic Interventions, and In Medical Imaging 2020: Modeling, volume 11315, page 1131523. International Society for Optics and Photonics.

Clarke, K. and Warwick, R. (1998). A taxonomic distinctness index and its statistical properties. Journal of applied ecology, 35(4):523–531.

Comelli, A., Dahiya, N., Stefano, A., Vernuccio, F., Portoghese, M., Cutaia, G., Bruno, A., Salvaggio, G., and Yezzi, A. (2021). Deep learning-based methods for prostate segmentation in magnetic resonance imaging. Applied Sciences, 11(2):782.

Costa, R. W. d. S., da Silva, G. L. F., de Carvalho Filho, A. O., Silva, A. C., de Paiva, A. C., and Gattass, M. (2018). Classication of malignant and benign lung nodules using taxonomic diversity index and phylogenetic distance. Medical & biological engineering & computing, 56(11):2125–2136.

Cruz, L. B. d., Souza, J. C., de Sousa, J. A., Santos, A. M., de Paiva, A. C., de Almeida, J. D. S., Silva, A. C., Junior, G. B., and Gattass, M. (2020). Interferometer eye image classication for dry eye categorization using phylogenetic diversity indexes for texture analysis. Computer Methods and Programs in Biomedicine, 188:105269.

De Visschere, P. (2018). Improving the diagnosis of clinically signicant prostate cancer with magnetic resonance imaging. Journal of the Belgian Society of Radiology, 102(1).

Ghose, S., Oliver, A., Martí, R., Lladó, X., Vilanova, J. C., Freixenet, J., Mitra, J., Sidibé, D., and Meriaudeau, F. (2012). A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images. Computer methods and programs in biomedicine, 108(1):262–287.

Gonzales, R. C. and Woods, R. E. (2002). Digital image processing.

INCA (2021). Instituto nacional do câncer, tipos de câncer: Próstata. http://www2.inca.gov.br/wps/wcm/connect/tiposdecancer/=site/home/prostata. Accessed: 2021-03-14.

Izsák, J. and Papp, L. (2000). A link between ecological diversity indices and measures of biodiversity. Ecological Modelling, 130(1-3):151–156.

Jensen, C., Sørensen, K. S., Jørgensen, C. K., Nielsen, C. W., Høy, P. C., Langkilde, N. C., and Østergaard, L. R. (2019). Prostate zonal segmentation in 1.5 t and 3t t2w mri using a convolutional neural network. Journal of Medical Imaging, 6(1):014501.

Johnson, H. J., McCormick, M. M., and Ibanez, L. (2015). The itk software guide book 1: Introduction and development guidelines fourth edition updated for itk version 4.7. Kitware Inc.

Lee, C. H., Akin-Olugbade, O., and Kirschenbaum, A. (2011). Overview of prostate anatomy, histology, and pathology. Endocrinology and Metabolism Clinics, 40(3):565–575.

Litjens, G., Futterer, J., and Huisman, H. (2015). Data from prostate-3t: The cancer imaging archive. http://doi.org/10.7937/K9/TCIA.2015.QJTV5IL5. Accessed: 2020-03-15.

Litjens, G., Toth, R., van de Ven, W., Hoeks, C., Kerkstra, S., van Ginneken, B., Vincent, G., Guillard, G., Birbeck, N., Zhang, J., et al. (2014). Evaluation of prostate segmentation algorithms for mri: the promise12 challenge. Medical image analysis, 18(2):359–373.

Liu, Y.-J., Yu, M., Li, B.-J., and He, Y. (2017). Intrinsic manifold slic: a simple and efficient method for computing content-sensitive superpixels. IEEE transactions on pattern analysis and machine intelligence.

Magurran, A. E. (2005). Species abundance distributions: pattern or process? Functional Ecology, 19(1):177–181.

Paiva, A. M., Diniz, J. O., Silva, A., and Paiva, A. (2019). Segmentação de vértebras e diagnóstico de fraturas em imagens de ressonância magnética utilizando u-net 3d e deep belief network. In Anais do XIX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 106–117, Porto Alegre, RS, Brasil. SBC.

Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental improvement. Computing Research Repository (CoRR).

Rini, D. P., Shamsuddin, S. M., and Yuhaniz, S. S. (2011). Particle swarm optimization: International journal of computer applications, technique, system and challenges. 14(1):19–26.

Siegel, R. L., Miller, K. D., and Jemal, A. (2019). Cancer statistics, 2019. CA: a cancer journal for clinicians, 69(1):7–34.

Silva, G. L. F. d., Carvalho Filho, A. O. d., Silva, A. C., Paiva, A. C. d., and Gattass, M. (2016). Taxonomic indexes for differentiating malignancy of lung nodules on ct images. Research on Biomedical Engineering, 32(3):263–272.

Taha, A. A. and Hanbury, A. (2015). Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool. BMC medical imaging, 15(1):29.

Vane-Wright, R. I., Humphries, C. J., and Williams, P. H. (1991). What to protect?—systematics and the agony of choice. Biological conservation, 55(3):235– 254.

Wang, B., Lei, Y., Tian, S., Wang, T., Liu, Y., Patel, P., Jani, A. B., Mao, H., Curran, W. J., Liu, T., et al. (2019). Deeply supervised 3d fully convolutional networks with group dilated convolution for automatic mri prostate segmentation. Medical physics, 46(4):1707–1718.

Weitzman, M. L. (1992). On diversity. The Quarterly Journal of Economics, 107(2):363–405.

Ye, X., Oyoyo, U., Lu, A., Dixon, J., Rojas, H., Randolph, S., and Kelly, T. (2016). Comparison of 3.0 t pac versus 1.5 t erc mri in detecting local prostate carcinoma. bioRxiv, page 058123.