nach oben

European Radiology

Erschienen in:

13.01.2021 | Imaging Informatics and Artificial Intelligence

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

verfasst von: Zhiyong Lin, Yingpu Cui, Jia Liu, Zhaonan Sun, Shuai Ma, Xiaodong Zhang, Xiaoying Wang

Erschienen in: European Radiology | Ausgabe 7/2021

Einloggen, um Zugang zu erhalten

Abstract

Objectives

To develop a 3D U-Net-based deep learning model for automated segmentation of kidney and renal mass, and detection of renal mass in corticomedullary phase of computed tomography urography (CTU).

Methods

Data on 882 kidneys obtained from CTU data of 441 patients with renal mass were used to learn and evaluate the deep learning model. The CTU data of 35 patients with small renal tumors (diameter ≤ 1.5 cm) were used for additional testing. The ground truth data for the kidney, renal tumor, and cyst were manually annotated on corticomedullary phase images of CTU. The proposed segmentation model for kidney and renal mass was constructed based on a 3D U-Net. The segmentation accuracy was evaluated through the Dice similarity coefficient (DSC). The volume of the maximum 3D volume of interest of renal tumor and cyst in the predicted segmentation by the model was used as an identification indicator, while the detection performance of the model was evaluated by the area under the receiver operation characteristic curve.

Results

The proposed model showed a high accuracy in segmentation of kidney and renal tumor, with average DSC of 0.973 and 0.844, respectively. It performed moderately in the renal cyst segmentation, with an average DSC of 0.536 in the test set. Also, this model showed good performance in detecting renal tumor and cyst.

Conclusions

The proposed automated segmentation and detection model based on 3D U-Net shows promising results for the segmentation of kidney and renal tumor, and the detection of renal tumor and cyst.

Key Points

• The segmentation model based on 3D U-Net showed high accuracy in segmentation of kidney and renal neoplasm, and good detection performance of renal neoplasm and cyst in corticomedullary phase of CTU.

• The segmentation model based on 3D U-Net is a fully automated aided diagnostic tool that could be used to reduce the workload of radiologists and improve the accuracy of diagnosis.

• The segmentation model based on 3D U-Net would be helpful to provide quantitative information for diagnosis, treatment, surgical planning, etc.

Nur mit Berechtigung zugänglich

Capitanio U, Bensalah K, Bex A et al (2019) Epidemiology of renal cell carcinoma. Eur Urol 75:74–84CrossRef

Giménez-Bachs JM, Salinas-Sánchez AS (2019) Improving the diagnosis of renal masses: can we approach the histological diagnosis to the image? Ann Transl Med 7:56CrossRef

Hsieh JJ, Purdue MP, Signoretti S et al (2017) Renal cell carcinoma. Nat Rev Dis Primers 3:17009CrossRef

Bryniarski P, Kaletka Z, Życzkowski M, Prokopowicz G, Muskała B, Paradysz A (2013) Ten year treatment outcomes including blood cell count disturbances in patients with simple renal cysts. Med Sci Monit 19:518–523CrossRef

Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A (2018) Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 68:394–424CrossRef

Songib N, Nazri M, Yaakup NA, Nor HM, Sun Z (2013) Multiphase renal CT in the evaluation of renal masses: is the nephrographic phase necessary? Clin Imaging 37:1037–1042CrossRef

Smith ND, Campbell SC (2001) Evaluation of the renal mass. In: Kursh ED, Ulchaker JC (eds) Office urology: the clinician’s guide. Humana Press, Totowa. https://doi.org/10.1007/978-1-59259-010-0_12CrossRef

Garant M, Bonaldi VM, Taourel P, Pinsky MF, Bret PM (1998) Enhancement patterns of renal masses during multiphase helical CT acquisitions. Abdom Imaging 23:431–436CrossRef

Gakis G, Kramer U, Schilling D, Kruck S, Stenzl A, Schlemmer H (2011) Small renal oncocytomas: differentiation with multiphase CT. Eur J Radiol 80:274–278CrossRef

10.

Haji-Momenian S, Lin Z, Patel B et al (2020) Texture analysis and machine learning algorithms accurately predict histologic grade in small (< 4 cm) clear cell renal cell carcinomas: a pilot study. Abdom Radiol (NY) 45:789–798CrossRef

11.

Ganesan A, Alakhras M, Brennan PC, Mello Thoms C (2018) A review of factors influencing radiologists’ visual search behaviour. J Med Imaging Radiat Oncol 62:747–757CrossRef

12.

Yang G, Gu J, Chen Y et al (2014) Automatic kidney segmentation in CT images based on multi-atlas image registration. Annu Int Conf Proc IEEE Eng Med Biol Soc 2014:5538–5541

13.

Zhang X (2010) Automated segmentation and registration of the kidney in CT datasets. Available via https://search.proquest.com/docview/520461346?accountid=13151. Accessed 12 Apr 2020

14.

Ma Y, Cao F, Xu X, Ma W (2020) Can whole-tumor radiomics-based CT analysis better differentiate fat-poor angiomyolipoma from clear cell renal cell carcinoma: compared with conventional CT analysis? Abdom Radiol (NY) 45:2500–2507CrossRef

15.

Lee HS, Hong H, Jung DC, Park S, Kim J (2017) Differentiation of fat-poor angiomyolipoma from clear cell renal cell carcinoma in contrast-enhanced MDCT images using quantitative feature classification. Med Phys 44:3604–3614CrossRef

16.

Lee H, Hong H, Kim J, Jung DC (2018) Deep feature classification of angiomyolipoma without visible fat and renal cell carcinoma in abdominal contrast-enhanced CT images with texture image patches and hand-crafted feature concatenation. Med Phys 45:1550–1561CrossRef

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 10:366CrossRef

18.

Song H, Song H, Kang W et al (2015) Kidney segmentation in CT sequences using SKFCM and improved GrowCut algorithm. BMC Syst Biol 9:S5CrossRef

19.

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. https://doi.org/10.1007/978-3-319-46723-8_49

20.

Sabarinathan D, Beham MP, Roomi SMMM (2019) Hyper Vision Net: kidney tumor segmentation using coordinate convolutional layer and attention unit. Available via https://arxiv.org/abs/1908.03339. Accessed 13 Feb 2020

21.

Chen S, Zhong X, Hu S et al (2020) Automatic multi-organ segmentation in dual-energy CT (DECT) with dedicated 3D fully convolutional DECT networks. Med Phys 47:552–562CrossRef

22.

Heller N, Isensee F, Maier-Hein KH et al (2020) The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: results of the KiTS19 Challenge. Med Image Anal 67:101821. https://doi.org/10.1016/j.media.2020.101821CrossRefPubMed

23.

Heller N, Sathianathen N, Kalapara A et al (2019) The KiTS19 Challenge data: 300 kidney tumor cases with clinical context, CT semantic segmentations, and surgical outcomes. Available via http://arxiv.org/pdf/1904.00445. Accessed 17 Feb 2020

Titel: 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
verfasst von: Zhiyong Lin
Yingpu Cui
Jia Liu
Zhaonan Sun
Shuai Ma
Xiaodong Zhang
Xiaoying Wang
Publikationsdatum: 13.01.2021
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 7/2021
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-020-07608-9

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

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