U-Net based frames partitioning and volumetric analysis for kidney detection in tomographic images

• Autorzy: Les Tomasz

Identyfikatory

DOI

10.24425/bpasts.2021.137051

• Języki publikacji: EN

Abstrakty

EN

This work presents an automatic system for generating kidney boundaries in computed tomography (CT) images. This paper presents the main points of medical image processing, which are the parts of the developed system. The U-Net network was used for image segmentation, which is now widely used as a standard solution for many medical image processing tasks. An innovative solution for framing the input data has been implemented to improve the quality of the learning data as well as to reduce the size of the data. Precision-recall analysis was performed to calculate the optimal image threshold value. To eliminate false-positive errors, which are a common issue in segmentation based on neural networks, the volumetric analysis of coherent areas was applied. The developed system facilitates a fully automatic generation of kidney boundaries as well as the generation of a three-dimensional kidney model. The system can be helpful for people who deal with the analysis of medical images, medical specialists in medical centers, especially for those who perform the descriptions of CT examination. The system works fully automatically and can help to increase the accuracy of the performed medical diagnosis and reduce the time of preparing medical descriptions.

Słowa kluczowe

EN

kidney detection; medical image processing; U-net; frames partitioning; volumetric analysis

PL

wykrywanie nerek; przetwarzanie obrazu medycznego; U-net; partycjonowanie ramek; analiza objętościowa

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2021
• Tom: Vol. 69, nr 3
• Strony: art. no. e137051
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Les Tomasz

• Faculty of Electrical Engineering, Warsaw University of Technology, ul. Koszykowa 75, 00-662 Warszawa, Poland

Bibliografia

• [1] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition”, Proc. IEEE 86(11), 2278‒2324 (1998), doi: 10.1109/5.726791.
• [2] F. Isensee, “An attempt at beating the 3D U-Net”, ed. K.H. Maier-Hein, 2019.
• [3] Ö. Çiçek, A. Abdulkadir, S.S. Lienkamp, T. Brox, and O. Ronneberger, “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation”, in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016), 424‒432, Springer International Publishing, 2016.
• [4] C. Li, W. Chen, and Y. Tan, “Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation”, Appl. Sci. 10(18), 6439 (2020), doi: 10.3390/app10186439.
• [5] Z. Fatemeh, S. Nicola, K. Satheesh, and U. Eranga, “Ensemble U‐net‐based method for fully automated detection and segmentation of renal masses on computed tomography images”, Med. Phys. 47(9), 4032‒4044 (2020), doi: 10.1002/mp.14193.
• [6] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation”, ArXiv, abs/1505.04597, 2015.
• [7] M.E.J. Ferlay, F. Lam, M. Colombet, L. and Mery. “Global Cancer Observatory: Cancer Today.” [Online] Available: https://gco.iarc.fr/today, accessed (accessed).
• [8] P.A. Humphrey, H. Moch, A.L. Cubilla, T. M. Ulbright, and V.E. Reuter, “The 2016 WHO Classification of Tumours of the Urinary System and Male Genital Organs-Part B: Prostate and Bladder Tumours”, Eur. Urol. 70(1), 106‒119 (2016), doi: 10.1016/j.eururo.2016.02.028.
• [9] D.L. Pham, C. Xu, and J.L. Prince, “Current Methods in Medical Image Segmentation”, Ann. Rev. Biomed. Eng. 2(1), 315‒337 (2000), doi: 10.1146/annurev.bioeng.2.1.315.
• [10] B. Tsagaan, A. Shimizu, H. Kobatake, and K. Miyakawa, “An Automated Segmentation Method of Kidney Using Statistical Information”, in Medical Image Computing and Computer-Assisted Intervention — MICCAI 2002, pp. 556‒563, Springer Berlin Heidelberg, 2002.
• [11] J.C. Bezdek, “Objective Function Clustering”, in Pattern Recognition with Fuzzy Objective Function Algorithms , pp. 43‒93, Boston: Springer US, 1981.
• [12] K. Sharma et al., “Automatic Segmentation of Kidneys using Deep Learning for Total Kidney Volume Quantification in Autosomal Dominant Polycystic Kidney Disease”, Sci. Rep. 7(1), 2049 (2017), doi: 10.1038/s41598-017-01779-0.
• [13] P. Jackson, N. Hardcastle, N. Dawe, T. Kron, M.S. Hofman, and R. J. Hicks, “Deep Learning Renal Segmentation for Fully Automated Radiation Dose Estimation in Unsealed Source Therapy”, Front. Oncol. 14(8), 215, (2018), doi: 10.3389/fonc.2018.00215.
• [14] C. Li, W. Chen, and Y. Tan, “Point-Sampling Method Based on 3D U-Net Architecture to Reduce the Influence of False Positive and Solve Boundary Blur Problem in 3D CT Image Segmentation”, Appl. Sci. 10(19), 6838 (2020).
• [15] A. Myronenko and A. Hatamizadeh, “3d kidneys and kidney tumor semantic segmentation using boundary-aware networks”, arXiv preprint arXiv:1909.06684, 2019.
• [16] W. Zhao, D. Jiang, J. P. Queralta, and T. Westerlund, “Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation”, arXiv preprint arXiv:2004.08108, 2020.
• [17] W. Zhao, D. Jiang, J. Peña Queralta, and T. Westerlund, “MSS U-Net: 3D segmentation of kidneys and tumors from CT images with a multi-scale supervised U-Net”, Inform. Med. Unlocked 19, 100357 (2020), doi: 10.1016/j.imu.2020.100357.
• [18] Y. LeCun and Y. Bengio, “Convolutional networks for images, speech, and time series”, in The handbook of brain theory and neural networks, pp. 255–258, MIT Press, 1998.
• [19] T. Les, T. Markiewicz, M. Dziekiewicz, and M. Lorent, “Kidney Boundary Detection Algorithm Based on Extended Maxima Transformations for Computed Tomography Diagnosis”, Appl. Sci. 10(21), 7512 (2020), doi: 10.3390/app10217512.
• [20] Z. Swiderska-Chadaj, T. Markiewicz, J. Gallego, G. Bueno, B. Grala, and M. Lorent, “Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model”, Bull. Pol. Acad. Sci. Tech. Sci. 66(6), 849‒856 (2018).
• [21] W. Wieclawek, “3D marker-controlled watershed for kidney segmentation in clinical CT exams”, Biomed. Eng. Online 17(1), 26 (2018), doi: 10.1186/s12938-018-0456-x.
• [22] T. Les, “Patch-based renal CTA image segmentation with U-Net”, in 2020 IEEE 21st International Conference on Computational Problems of Electrical Engineering (CPEE), Poland, 2020, pp. 1‒4, doi: 10.1109/CPEE50798.2020.9238735.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).