Whole kidney and renal cortex segmentation in contrast-enhanced MRI using a joint classification and segmentation convolutional neural network

• Autorzy: Klepaczko Artur , Majos Marcin , Stefańczyk Ludomir , Eikefjord Eli , Lundervold Arvid

Identyfikatory

DOI

10.1016/j.bbe.2022.02.002

• Języki publikacji: EN

Abstrakty

EN

Contrast-enhanced magnetic resonance imaging (CE-MRI) is one of the methods routinely used in clinics for the diagnosis of renal impairments. It allows assessment of kidney perfusion and also visualization of various lesions and tissue atrophy due to e.g. renal artery stenosis (RAS). An important indicator of the renal tissue state is the volume and shape of the kidney. Therefore it is highly desirable to equip radiological units in clinics with the software capable of automatic segmentation of the kidneys in CE-MRI images. This paper proposes a solution to this task using an original architecture of a deep neural network. The proposed design employs a three-branch convolutional neural network specialized in: 1) detection of renal parenchyma within an MR image patch, 2) segmentation of the whole kidney and 3) annotation of the renal cortex. We tested our architecture for normal kidneys in healthy subjects and for poorly perfused organs in RAS patients. The accuracy of renal parenchyma segmentation was equal to 0.94 in terms of the intersection over union (IoU) ratio. Accuracy of the cortex segmentation depends on the level of tissue health condition and ranges from 0.76 up to 0.92 of IoU.

Słowa kluczowe

EN

kidney segmentation; convolutional neural network; contrast enhanced MRI; kidney volume assessment; renal perfusion modeling

PL

segmentacja nerek; sieć neuronowa konwolucyjna; obraz MRI; ocena objętości nerek

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 1
• Strony: 295--311
• Opis fizyczny: Bibliogr. 59 poz., rys., tab., wykr.

Twórcy

autor

Klepaczko Artur

• Institute of Electronics, Lodz University of Technology, Al. Politechniki 10, 93-590 Lodz, Poland

autor

Majos Marcin

• Department of Radiology - Diagnostic Imaging, Medical University of Lodz, Lodz, Poland

autor

Stefańczyk Ludomir

• Department of Radiology - Diagnostic Imaging, Medical University of Lodz, Lodz, Poland

autor

Eikefjord Eli

• Department of Health and Functioning, Western Norway University of Applied Sciences, Bergen, Norway

autor

Lundervold Arvid

• Department of Health and Functioning, Western Norway University of Applied Sciences, Bergen, Norway; Department of Biomedicine, University of Bergen, Bergen, Norway; Mohn Medical Imaging and Visualization Centre, Department of Radiology, Haukeland University Hospital, Bergen, Norway

Bibliografia

• [1] Doloretta Piras, Marco Masala, Alessandro Delitala, Silvana A M Urru, Nicolò Curreli, Lenuta Balaci, Liana P Ferreli, Francesco Loi, Alice Atzeni, Gianfranca Cabiddu, Walter Racugno, Laura Ventura, Magdalena Zoledziewska, Maristella Steri, Edoardo Fiorillo, Maria G Pilia, David Schlessinger, Francesco Cucca, Andrew D Rule, and Antonello Pani. Kidney size in relation to ageing, gender, renal function, birthweight and chronic kidney disease risk factors in a general population. Nephrology Dialysis Transplantation, 35(4), 640–647, 08 2018.
• [2] Roseman Daniel A, Hwang Shih-Jen, Oyama-Manabe Noriko, Chuang Michael L, O’Donnell Christopher J, Manning Warren J, Fox Caroline S. Clinical associations of total kidney volume: the Framingham Heart Study. Nephrology Dialysis Transplantation 2016;32(8). 1344–1350, 06.
• [3] Eikefjord Eli, Andersen Erling, Hodneland Erlend, Svarstad Einar, Lundervold Arvid, Rürvik Jarle. Quantification of Single-Kidney Function and Volume in Living Kidney Donors Using Dynamic Contrast-Enhanced MRI. American Journal of Roentgenology 2016;207(5):1022–30.
• [4] Nogawa Joji, Kobayashi Etsuko, Inaoka Hiromi, Ishizaki Arinobu. The relationship between the renal effects of cadmium and cadmium concentration in urine among the inhabitants of cadmium-polluted areas. Environmental Research 1977;14(3):391–400.
• [5] Li Qinghai, Wang Dali, Zhu Xiuliang, Shen Keren, Fang Xu, Chen Ying. Combination of renal apparent diffusion coefficient and renal parenchymal volume for better assessment of split renal function in chronic kidney disease. European Journal of Radiology 2018;108:194–200.
• [6] Daniel Lange, Andreas Helck, Axel Rominger, Alexander Crispin, Bruno Meiser, Jens Werner, Michael Fischereder, Manfred Stangl, and Antje Habicht. Renal volume assessed by MRI volumetry correlates with renal function in living kidney donors pre- and postdonation: a retrospective cohort study. Transplant International, 31(7), 773–780, 07 2018.
• [7] Galliani M, Vitaliano E, Chicca S, Calvaruso L, Di Lullo L, Iorio F, Tosti ME, Paone A. Renal Volume in ADPKD Patient Evaluation. International Journal of Nephrology 2020;9286728 (02):2020.
• [8] Massimiliano Veroux, Cecilia Gozzo, Daniela Corona, Paolo Murabito, Daniele Carmelo Caltabiano, Luca Mammino, Alessia Giaquinta, Domenico Zerbo, Nunziata Sinagra, Pierfrancesco Veroux, and Stefano Palmucci. Change in kidney volume after kidney transplantation in patients with autosomal polycystic kidney disease. PLOS ONE, 13(12), 1–15, 12 2018.
• [9] Chrysochou Constantina, Green Darren, Ritchie James, Buckley David L, Kalra Philip A. Kidney volume to GFR ratio predicts functional improvement after revascularization in atheromatous renal artery stenosis. PLOS ONE 2017;12(6), 1– 14:06.
• [10] Zöllner Frank G, Kociński Marek, Hansen Laura, Golla Alena-Kathrin. Amira Šerifović Trbalić, Arvid Lundervold, Andrzej Materka, and Peter Rogelj. Kidney segmentation in renal magnetic resonance imaging - current status and prospects. IEEE Access 2021;9:71577–605.
• [11] Yoruk Umit, Hargreaves Brian A, Vasanawala Shreyas S. Automatic renal segmentation for MR urography using 3D-GrabCut and random forests. Magnetic Resonance in Medicine 2018;79(3):1696–707.
• [12] Xin Yang, Hung Le Minh, Kwang-Ting (Tim) Cheng, Kyung Hyun Sung, and Wenyu Liu. Renal compartment segmentation in DCE-MRI images. Medical Image Analysis, 32(C):269–280, 2016.
• [13] Rusinek Henry, Lim Jeremy C, Wake Nicole, Seah Jas-mine, Botterill Elissa, Farquharson Shawna, Mikheev Artem, Lim Ruth P. A semi-automated blanket method for renal segmentation from non-contrast T1-weighted MR images. Magnetic Resonance Materials in Physics, Biology and Medicine 2016;29(2):197–206.
• [14] Sandmair Martin, Hammon Matthias, Seuss Hannes, Theis Ragnar, Uder Michael, Janka Rolf. Semiautomatic segmentation of the kidney in magnetic resonance images using unimodal thresholding. BMC Research Notes 2016;9 (1):489.
• [15] Warner Joshua D, Irazabal Maria V, Krishnamurthi Ganapathy, King Bernard F, Torres Vicente E, Erickson Bradley J. Supervised segmentation of polycystic kidneys: a new application for stereology data. Journal of Digital Imaging 2014;27(4):514–9.
• [16] Gloger Oliver, Tönnies Klaus, Laqua Rene, Völzke Henry. Fully Automated Renal Tissue Volumetry in MR Volume Data Using Prior-Shape-Based Segmentation in Subject-Specific Probability Maps. IEEE Transactions on Biomedical Engineering 2015;62(10):2338–51.
• [17] Skalski Andrzej, Heryan Katarzyna, Jakubowski Jacek, Drewniak Tomasz. Kidney segmentation in CT data using hybrid level-set method with ellipsoidal shape constraints. Metrology and Measurement Systems 2017;24(1):101–12.
• [18] O’Reilly Jamie A, Tanpradit Sakuntala, Puttasakul Tasawan, Sangworasil Manas, Matsuura Takenobu. Pornphan Wibulpolprasert, and Khaisang Chousangsuntorn. Automatic segmentation of polycystic kidneys from magnetic resonance images using decision tree classification and snake algorithm. In: 2019 12th Biomedical Engineering International Conference (BMEiCON). p. 1–5.
• [19] Kline Timothy, Korfiatis Panagiotis, Edwards Marie, Blais Jaime, Czerwiec Frank, Harris Peter, King Bernard, Torres Vicente, Erickson Bradley. Performance of an Artificial Multi-observer Deep Neural Network for Fully Automated Segmentation of Polycystic Kidneys. Journal of Digital Imaging May 2017;30.
• [20] Taro Langner, Andreas ’Ostling, Lukas Maldonis, Albin Karlsson, Daniel Olmo, Dag Lindgren, Andreas Wallin, Lowe Lundin, Robin Strand, Hakan Ahlström, and Joel Kullberg. Kidney segmentation in neck-to-knee body MRI of 40,000 UK Biobank participants. Scientific Reports, 10 (1):20963, 2020.
• [21] Daniel Alexander J, Buchanan Charlotte E, Allcock Thomas, Scerri Daniel, Cox Eleanor F, Prestwich Benjamin L, Francis Susan T. Automated renal segmentation in healthy and chronic kidney disease subjects using a convolutional neural network. Magnetic Resonance in Medicine 2021;86 (2):1125–36.
• [22] M. Haghighi, S.K. Warfield, and S. Kurugol. Automatic renal segmentation in DCE-MRI using convolutional neural networks. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 1534–1537, 2018.
• [23] Bammer Roland. MR and CT Perfusion and Pharmacokinetic Imaging. Clinical Applications and Theory. Philadelphia: Wolters Kluwer; 2016.
• [24] Milecki Leo, Bodard Sylvain, Correas Jean-Michel, Timsit Marc-Olivier, Vakalopoulou Maria. 3D Unsupervised Kidney Graft Segmentation Based On Deep Learning And Multi-Sequence MRI. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). p. 1781–5.
• [25] Lundervold AS, Rorvik J, Lundervold A. Fast semi-supervised segmentation of the kidneys in DCE-MRI using convolutional neural networks and transfer learning. In: 2nd Int. Sci. Symp. p. 79–81.
• [26] Kanishka Sharma, Christian Rupprecht, Anna Caroli, Maria Carolina Aparicio, Andrea Remuzzi, Maximilian Baust, and Nassir Navab. Automatic segmentation of kidneys using deep learning for total kidney volume quantification in autosomal dominant polycystic kidney disease. Scientific Reports, 7 (1):2049, 2017.
• [27] Price Jackson, Nicholas Hardcastle, Noel Dawe, Tomas Kron, Michael S. Hofman, and Rodney J. Hicks. Deep learning renal segmentation for fully automated radiation dose estimation in unsealed source therapy. Frontiers in Oncology, 8, 2018.
• [28] Couteaux V, Si-Mohamed S, Renard-Penna R, Nempont O, Lefevre T, Popoff A, Pizaine G, Villain N, Bloch I, Behr J, Bellin M-F, Roy C, Rouvière O, Montagne S, Lassau N, Boussel L. Kidney cortex segmentation in 2D CT with U-Nets ensemble aggregation. Diagnostic and Interventional Imaging 2019;100 (4):211–7.
• [29] Kevin Yin, Chengfeng Liu, Michelle Bardis, Jeremy Martin, Hannah Liu, Alexander Ushinsky, Justin Glavis-Bloom, Chanon Chantaduly, Daniel S. Chow, Roozbeh Houshyar, and Peter Chang. Deep learning segmentation of kidneys with renal cell carcinoma. Journal of Clinical Oncology, 37 (15_suppl):e16098–e16098, 2019.
• [30] Türk Fuat, Lüy Murat, Barısçı Necaattin. Kidney and renal tumor segmentation using a hybrid V-Net-based model. Mathematics October 2020;8(10):1772.
• [31] Wenshuai Zhao, Dihong Jiang, Jorge Peöa Queralta, and Tomi Westerlund. MSS U-Net: 3D segmentation of kidneys and tumors from CT images with a multi-scale supervised U-Net. Informatics in Medicine Unlocked, 19, 2020.
• [32] Heller Nicholas, Isensee Fabian, Maier-Hein Klaus H, Hou Xiaoshuai, Xie Chunmei, Li Fengyi, Nan Yang, Guangrui Mu, Lin Zhiyong, Han Miofei, Yao Guang, Gao Yaozong, Zhang Yao, Wang Yixin, Hou Feng, Yang Jiawei, Xiong Guangwei, Tian Jiang, Zhong Cheng, Ma Jun, Rickman Jack, Dean Joshua, Stai Bethany, Tejpaul Resha, Oestreich Makinna, Blake Paul, Kaluzniak Heather, Raza Shaneabbas, Rosenberg Joel, Moore Keenan, Walczak Edward, Rengel Zachary, Edgerton Zach, Vasdev Ranveer, Peterson Matthew, McSweeney Sean, Peterson Sarah, Kalapara Arveen, Sathianathen Niranjan, Papanikolopoulos Nikolaos, Weight Christopher. The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the kits19 challenge. Medical Image Analysis 2021;67 101821.
• [33] Lin Zhiyong, Cui Yingpu, Liu Jia, Sun Zhaonan, Ma Shuai, Zhang Xiaodong, Wang Xiaoying. Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network. European Radiology 2021;31:5021–31.
• [34] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Lecture Notes in Computer Science, volume 9351, pages 234–241, 10 2015.
• [35] Artur Klepaczko, Eli Eikefjord, and Arvid Lundervold. Deep Convolutional Neural Networks in Application to Kidney Segmentation in the DCE-MR Images. In Maciej Paszynski, Dieter Kranzlmüller, Valeria V. Krzhizhanovskaya, Jack J. Dongarra, and Peter M.A. Sloot, editors, Computational Science – ICCS 2021, pages 609–622. Springer International Publishing, 2021.
• [36] Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 2017;39(12):2481–95.
• [37] Jégou S, Drozdzal M, Vazquez D, Romero A, Bengio Y. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). p. 1175–83.
• [38] Jennifer R Charlton, Yanzhe Xu, Neda Parvin, Teresa Wu, Fei Gao, Edwin J Baldelomar, Darya Morozov, Scott C Beeman, Jamal Derakhshan, and Kevin M Bennett. Image analysis techniques to map pyramids, pyramid structure, glomerular distribution, and pathology in the intact human kidney from 3-D MRI. American Journal of Physiology-Renal Physiology, 321:F293–F304, 202.
• [39] Gregory Adriana V, Anaam Deema A, Vercnocke Andrew J, Edwards Marie E, Torres Vicente E, Harris Peter C, Erickson Bradley J, Kline Timothy L. Semantic Instance Segmentation of Kidney Cysts in MR Images: A Fully Automated 3D Approach Developed Through Active Learning. Journal of Digital Imaging 2021;34(773–787):8.
• [40] Kline Timothy L, Edwards Marie E, Fetzer Jeffrey, Gregory Adriana V, Anaam Deema, Metzger Andrew J, Erickson Bradley J. Automatic semantic segmentation of kidney cysts in MR images of patients affected by autosomal-dominant polycystic kidney disease. Abdominal Radiology 2021;46 (1053–1061):3.
• [41] Kwang Hyun Uhm, Seung Won Jung, Moon Hyung Choi, Hong Kyu Shin, Jae Ik Yoo, Se Won Oh, Jee Young Kim, Hyun Gi Kim, Young Joon Lee, Seo Yeon Youn, Sung Hoo Hong, and Sung Jea Ko. Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography. npj Precision Oncology, 5, 12 2021.
• [42] Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis & Machine Intelligence 2018;40(04):834–48.
• [43] Pierre Delanaye, Natalie Ebert, Toralf Melsom, Flavio Gaspari, Christophe Mariat, Etienne Cavalier, Jonas Björk, Anders Christensson, Ulf Nyman, Esteban Porrini, Giuseppe Remuzzi, Piero Ruggenenti, Elke Schaeffner, Inga Soveri, Gunnar Sterner, Bjürn Odvar Eriksen, and Sten-Erik Bäck. Iohexol plasma clearance for measuring glomerular filtration rate in clinical practice and research: a review. Part 1: How to measure glomerular filtration rate with iohexol? Clinical Kidney Journal, 9(5), 682–699, 2016.
• [44] Srivastava Nitish, Hinton Geoffrey, Krizhevsky Alex, Sutskever Ilya, Salakhutdinov Ruslan. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 2014;15(56):1929–58.
• [45] Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss, editors, Computer Vision – ECCV 2018, pages 833– 851. Springer International Publishing, 2018.
• [46] Paul Tofts, Marica Cutajar, Iosif Mendichovszky, A Peters, and Isky Gordon. Precise measurement of renal filtration and vascular parameters using a two-compartment model for dynamic contrast-enhanced MRI of the kidney gives realistic normal values. European Radiology, 22:1320–30, March 2012.
• [47] Klepaczko Artur, Strzelecki Michał, Kociołek Marcin, Eikefjord Eli, Lundervold Arvid. A multi-layer perceptron network for perfusion parameter estimation in DCE-MRI studies of the healthy kidney. Applied Sciences 2020;10(16).
• [48] Yuan Ya-xiang. Recent advances in trust region algorithms. Mathematical Programming 2015;151(1):249–81.
• [49] Paul S. Tofts. QA: Quality Assurance, Accuracy, Precision and Phantoms, chapter 3, pages 55–81. John Wiley & Sons, Ltd, 2003.
• [50] Bartlett JW, Frost C. Reliability, repeatability and reproducibility: analysis of measurement errors in continuous variables. Ultrasound in Obstetrics & Gynecology 2008;31(4):466–75.
• [51] Gardan Edouard, Jacquemont Lola, Perret Christophe, Heudes Pierre-Marie, Gourraud Pierre-Antoine, Hourmant Maryvonne, Frampas Eric, Limou Sophie. Renal cortical volume: High correlation with pre- and post-operative renal function in living kidney donors. European Journal of Radiology 2018;99:118–23.
• [52] Cheong Benjamin, Muthupillai Raja, Rubin Mario F, Flamm Scott D. Normal values for renal length and volume as measured by magnetic resonance imaging. Clinical Journal of the American Society of Nephrology 2007;2(1):38–45.
• [53] Youngwoo Kim, Yinghui Ge, Cheng Tao, Jianbing Zhu, Arlene B. Chapman, Vicente E. Torres, Alan S.L. Yu, Michal Mrug, William M. Bennett, Michael F. Flessner, Doug P. Landsittel, Kyongtae T. Bae, and for the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP). Automated Segmentation of Kidneys from MR Images in Patients with Autosomal Dominant Polycystic Kidney Disease. Clinical Journal of the American Society of Nephrology, 11(4), 576–584, 2016.
• [54] Marica Cutajar, David L Thomas, Patrick W Hales, T Banks, Christopher A Clark, and Isky Gordon. Comparison of ASL and DCE MRI for the non-invasive measurement of renal blood flow: quantification and reproducibility. European radiology, 24(6):1300–1308, June 2014.
• [55] Eikefjord E, Andersen E, Hodneland E, Hanson E, Sourbron S, Svarstad E, Lundervold A, Rørvik J. Dynamic contrast-enhanced MRI measurement of renal function in healthy participants. Acta Radiologica 2017;58:748–57.
• [56] Fedorov Andriy, Beichel Reinhard, Kalpathy-Cramer Jayashree, Finet Julien, Fillion-Robin Jean-Christophe, Pujol Sonia, Bauer Christian, Jennings Dominique, Fennessy Fiona, Sonka Milan, Buatti John, Aylward Stephen, Miller James V, Pieper Steve, Kikinis Ron. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magnetic Resonance Imaging 2012;30(9):1323–41.
• [57] Jiang Lei, Chen Wenkai, Dong Bao, Mei Ke, Zhu Chuang, Liu Jun, Meishun Cai Yu, Yan Gongwei Wang, Zuo Li, Shi Hongxia. A deep learning-based approach for glomeruli instance segmentation from multistained renal biopsy pathologic images. American Journal of Pathology 2021;191:1431–41.
• [58] Catherine P. Jayapandian, Yijiang Chen, Andrew R. Janowczyk, Matthew B. Palmer, Clarissa A. Cassol, Miroslav Sekulic, Jeffrey B. Hodgin, Jarcy Zee, Stephen M. Hewitt, John O’Toole, Paula Toro, John R. Sedor, Laura Barisoni, Anant Madabhushi, J. Sedor, K. Dell, M. Schachere, J. Negrey, K. Lemley, E. Lim, T. Srivastava, A. Garrett, C. Sethna, K. Laurent, G. Appel, M. Toledo, L. Barisoni, L. Greenbaum, C. Wang, C. Kang, S. Adler, C. Nast, J. LaPage, John H. Stroger, A. Athavale, M. Itteera, A. Neu, S. Boynton, F. Fervenza, M. Hogan, J. Lieske, V. Chernitskiy, F. Kaskel, N. Kumar, P. Flynn, J. Kopp, J. Blake, H. Trachtman, O. Zhdanova, F. Modersitzki, S. Vento, R. Lafayette, K. Mehta, C. Gadegbeku, D. Johnstone, S. Quinn Boyle, D. Cattran, M. Hladunewich, H. Reich, P. Ling, M. Romano, A. Fornoni, C. Bidot, M. Kretzler, D. Gipson, A. Williams, J. LaVigne, V. Derebail, K. Gibson, A. Froment, S. Grubbs, L. Holzman, K. Meyers, K. Kallem, J. Lalli, K. Sambandam, Z. Wang, M. Rogers, A. Jefferson, S. Hingorani, K. Tuttle, M. Bray, M. Kelton, A. Cooper, B. Freedman, and J.J. Lin. Development and evaluation of deep learning–based segmentation of histologic structures in the kidney cortex with multiple histologic stains. Kidney International, 99:86– 101, 2021.
• [59] Jesper Kers, Roman D Bülow, Barbara M Klinkhammer, Gerben E Breimer, Francesco Fontana, Adeyemi Adefidipe Abiola, Rianne Hofstraat, Garry L Corthals, Hessel PetersSengers, Sonja Djudjaj, Saskia von Stillfried, David L Hölscher, Tobias T Pieters, Arjan D van Zuilen, Frederike J Bemelman, Azam S Nurmohamed, Maarten Naesens, Joris J T H Roelofs, Sandrine Florquin, Jürgen Floege, Tri Q Nguyen, Jakob N Kather, and Peter Boor. Deep learning-based classification of kidney transplant pathology: a retrospective, multicentre, proof-of-concept study. The Lancet Digital Health, 4:e18–e26, 2022.