Abstract
Background and purpose
The precise segmentation of the kidneys in computed tomography (CT) images is vital in urology for diagnosis, treatment, and surgical planning. Medical experts can get assistance through segmentation, as it provides information about kidney malformations in terms of shape and size. Manual segmentation is slow, tedious, and not reproducible. An automatic computer-aided system is a solution to this problem. This paper presents an automated kidney segmentation technique based on active contour and deep learning.
Materials and methods
In this work, 210 CTs from the KiTS 19 repository were used. The used dataset was divided into a train set (168 CTs), test set (21 CTs), and validation set (21 CTs). The suggested technique has broadly four phases: (1) extraction of kidney regions using active contours, (2) preprocessing, (3) kidney segmentation using 3D U-Net, and (4) reconstruction of the segmented CT images.
Results
The proposed segmentation method has received the Dice score of 97.62%, Jaccard index of 95.74%, average sensitivity of 98.28%, specificity of 99.95%, and accuracy of 99.93% over the validation dataset.
Conclusion
The proposed method can efficiently solve the problem of tumorous kidney segmentation in CT images by using active contour and deep learning. The active contour was used to select kidney regions and 3D-UNet was used for precisely segmenting the tumorous kidney.
Similar content being viewed by others
References
Jovanović D, Gasic B, Pavlovic S, Naumovic R (2013) Correlation of kidney size with kidney function and anthropometric parameters in healthy subjects and patients with chronic kidney diseases. Ren Fail 35(6):896–900
Pandey M, Gupta A (2021) A systematic review of the automatic kidney segmentation methods in abdominal images. Biocybern Biomed Eng 41(4):1601–1628
What is kidney cancer? https://www.cancer.org/cancer/kidney-cancer/about/what-is-kidney-cancer.html. Accessed 19 Jan 2022
Ghosn M, Roland Eid EH, Azim HA et al (2019) OSSMAR: an observational study to describe the use of sunitinib in real-life practice for the treatment of metastatic renal cell carcinoma. J Global Oncol 5:1–10
BrianShucha AA, Andrew J, Armstrongc JN et al (2015) Understanding pathologic variants of renal cell carcinoma: distilling therapeutic opportunities from biologic complexity. Eur Urol 67.1:85–97
Huysentruyt TNSALC (2013) On the origin of cancer metasta- sis. Crit Rev Oncog 18(1–2):43
Kidney Cancer (2022) https://www.wcrf.org/dietandcancer/kidney. Cancer. Accessed 19 Jan 2022
Gwynne S, Webster R, Adams R et al (2012) Image-guided radiotherapy for rectal cancer—a systematic review. Clin Oncol 24(4):250–260
Gupta A (2020) Challenges for computer aided diagnostics using X-ray and tomographic reconstruction images in craniofacial applications. Int J Comput Vis Robot 10(4):360–371
Mohsen G, Tina Kapur AM, Karssemeijer N et al (2017) Transfer learning for domain adaptation in mri: appli- cation in brain lesion segmentation. Int Conf Med Image Comput Computer-assist Interv (Springer) 516–524
Yang G, Gu J, Chen Y et al (2014) Automatic kidney segmentation in CT images based on multi- atlas image registration. 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE 5538–5541
Hyde ER, Berger L, Ramachandran N, Hughes-Hallett A, Pavithran N, Tran MGB, Ourselin S, Bex A, Mumtaz F (2019) Interactive virtual 3D models of renal cancer patient anatomies alter partial nephrectomy surgical planning decisions and increase surgeon confidence compared to volume-rendered images. Int J Comput Assist Radiol Surg 14(4):723–732
Papalia R, Abreu ALDC, Panebianco V, Duddalwar V, Simone G, Leslie S, Guaglianone S, Tejura T, Ferriero M, Costantini M (2015) Novel kidney segmentation system to describe tumour location for nephron-sparing surgery. World J Urol 33(6):865–871
Dallal AH, Agarwal C, Arbabshirani MR et al (2017) Automatic estimation of heart boundaries and cardiotho- racic ratio from chest x-ray images. In: Medical Imaging 2017: Computer-Aided Diagnosis, vol 10134. pp 134–143
Gupta A (2019) Current research opportunities of image processing and computer vision. Comput Sci 20(4)
Kim H, Hong H, Rha KH (2020) Renal parenchyma segmentation in abdominal CT images based on deep convolutional neural networks with similar atlas selection and transformation. in Medical imaging 2020: computer-aided diagnosis. Int Soc Optics Photonics
Alex DM, Chandy DA (2020) Investigations on performances of pre-trained U-Net models for 2D ultrasound kidney image segmentation. In: International Conference for Emerging Technologies in Computing. Springer
Jayanthi M (2016) Comparative study of different techniques used for medical image segmentation of liver from abdominal CT scan. In: 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET). IEEE
Yan G, Wang B (2010) An automatic kidney segmentation from abdominal CT images. In: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems. IEEE
Torres HR, Queiros S, Morais P et al (2018) Kidney segmentation in ultrasound, magnetic resonance and computed tomography images: A systematic review. Comput Methods Programs Biomed 157:49–67
Netter FH (2010) Netter's atlas of human anatomy. Saunders Elsevier
Khalifa F, Elnakib A, Beache GM et al (2011) 3D kidney segmentation from CT images using a level set approach guided by a novel stochastic speed function. Med Image Comput Comput Assist Interv 14(Pt 3):587–594
Cuingnet R, Prevost R, Lesage D et al (2012) Automatic detection and segmentation of kidneys in 3D CT images using random forests. Med Image Comput Comput Assist Interv 15(Pt 3):66–74
Dai GY, Li ZC, Gu J et al (2013) Segmentation of kidneys from computed tomography using 3D fast growcut algorithm. In: Applied Mechanics and Materials. Trans Tech Publ
Zhang P, Liang Y, Chang S, Fan H (2013) Kidney segmentation in CT sequences using graph cuts based active contours model and contextual continuity. Med Phys 40(8):081905
Zhao E, Liang Y, Fan H (2013) Contextual information-aided kidney segmentation in CT sequences. Optics Communications 290:55–62
Belgherbi A, Hadjidj I, Bessaid A (2014) Morphological segmentation of the kidneys from abdominal ct images. J Mech Med Biol 14(05):1450073
Yang G, Gu J, Chen Y et al (2014) Automatic kidney segmentation in CT images based on multi-atlas image registration. Annu Int Conf IEEE Eng Med Biol Soc 2014:5538–5541
Khalifa F, Soliman A, Takieldeen A et al (2016) Kidney segmentation from CT images using a 3D NMF-guided active contour model. In: 2016 IEEE 13th Inter Symposium Biomed Imaging (ISBI). IEEE
Jin C, Shi F, Xiang D et al (2016) 3D fast automatic segmentation of kidney based on modified AAM and random forest. IEEE Trans Med Imaging 35(6):1395–1407
Skalski A, Heryan K, Jakubowski J, Drewniak T (2017) Kidney segmentation in ct data using hybrid level-set method with ellipsoidal shape constraints. Metrology and Measurement Systems 24(1):101–112
Farzaneh N, Reza Soroushmehr SM, Patel H et al (2018) Automated kidney segmentation for traumatic injured patients through ensemble learning and active contour modeling. Annu Int Conf IEEE Eng Med Biol Soc 3418–3421
Oliveira B, Torres HR, Queirós S et al (2018) Segmentation of kidney and renal collecting system on 3D computed tomography images. In: 2018 IEEE 6th International Conference on Serious Games and Applications for Health (SeGAH). IEEE
Sharma K, Rupprecht C, Caroli A et al (2017) Automatic segmentation of kidneys using deep learning for total kidney volume quantification in autosomal dominant polycystic kidney disease. Sci Rep 7(1):2049
Thong W, Kadoury S, Piché N, Pal CJ (2018) Convolutional networks for kidney segmentation in contrast-enhanced CT scans. Comp Methods Biomech Biomed Eng Imaging Vis 6(3):277–282
Xia KJ, Yin HS, Zhang YD (2018) Deep semantic segmentation of kidney and space-occupying lesion area based on SCNN and ResNet models combined with SIFT-flow algorithm. J Med Syst 43(1):2
Yang G, Li G, Pan T et al (2018) Automatic segmentation of kidney and renal tumor in ct images based on 3d fully convolutional neural network with pyramid pooling module. In: 2018 24th International Conference on Pattern Recognition (ICPR). IEEE
da Cruz LB, Araújo JDL, Ferreira JL et al (2020) Kidney segmentation from computed tomography images using deep neural network. Comput Biol Med 123
Xie X, Li L, Lian S et al (2020) SERU: a cascaded SE-ResNeXT U-Net for kidney and tumor segmentation. Concurr Comput Pract Exp 32(14)
Fatemeh Z, Nicola S, Satheesh K, Eranga U (2020) Ensemble U‐net‐based method for fully automated detection and segmentation of renal masses on computed tomography images. Med Phys
Türk F, Lüy M, Barışçı N (2020) Kidney and renal tumor segmentation using a hybrid v-net-based model. Mathematics 8(10):1–17
Kim T, Lee K, Ham S et al (2020) Active learning for accuracy enhancement of semantic segmentation with CNN-corrected label curations: evaluation on kidney segmentation in abdominal CT. Sci Rep 10(1):1–7
Lin Z, Cui Y, Liu J et al (2021) 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. Eur Radiol 31(7):5021–5031
Zeng W, Fan W, Chen R et al (2021) Accurate 3d kidney segmentation using unsupervised domain translation and adversarial networks. In: Proceedings - International Symposium on Biomedical Imaging
Ashok M, Gupta A (2021) A systematic review of the techniques for the automatic segmentation of organs-at-risk in thoracic computed tomography images. Arch Comput Methods Eng 28:3245–3267
Gupta RK, Kunhare YSN, Gupta A, Prakash D (2021) Deep learning based mathematical model for feature extraction to detect corona virus disease using chest X-ray images. Int J Uncertain Fuzziness Knowl-Based Syst 29:921–947
Gupta MTAA (2022) A lightweight deep learning architecture for the automatic detection of pneumonia using chest X-ray images. Multimed Tools App 81:5515–5536.
Bala Chakravarthy Neelapu OPK, Sardana V, Gupta A et al (2017) A pilot study for segmentation of pharyngeal and sino-nasal airway subregions by automatic contour initialization. Int J Comput Assist Radiol Surg 12(11):1877–1893
Bakoˇs M (2007) Active contours and their utilization at image segmentation. In: 5th Slovakian Hungarian Joint symposium on applied machine intelligence and informatics, Poprad, Slovakia. pp 313–317
Heller N, Kalapara NSA, Walczak E et al (2019) The kits19 challenge data: 300 kidney tumor cases with clinical context, ct semantic segmentations, and surgical outcomes. arXiv:1904.004
Gonzalez RRW (2008) Digital image processing. Pearson, Prentice Hall
Yang G, Li G, Pan T et al (2018) Automatic segmentation of kidney and renal tumor in ct images based on 3d fully convolutional neural network with pyramid pooling module. In: 24th International Conference on Pattern Recognition (ICPR). pp 3790–3795
Software I (2017) Hands-on ai part 14: Image data preprocessing and augmentation. https://software.intel.com/en-us/articles/hands-on-ai-part-14-image-data-preprocessing-andaugmentation. Accessed 04 May 2022
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention. Springer
Yeung M, Sala E, Schönlieb C-B, Rundo L (2022) Unified focal loss: generalising dice and cross entropy-based losses to handle class imbalanced medical image segmentation. Comput Med Imaging Graph 95:102026
Chollet F (2015) Keras: Deep learning library for theano and tensorflow. 7(8):T1. https://keras.io/k
Abadi M, Agarwal A, Barham P et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467
Levandowsky M, Winter D (1971) Distance between sets. Nature 234(5323):34–35
Duda RO, Hart PE (1973) Pattern classification and scene analysis, vol 3. Wiley, New York
Bland M (2015) An introduction to medical statistics. Oxford university press
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Informed consent
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Pandey, M., Gupta, A. Tumorous kidney segmentation in abdominal CT images using active contour and 3D-UNet. Ir J Med Sci 192, 1401–1409 (2023). https://doi.org/10.1007/s11845-022-03113-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11845-022-03113-8