Correlation Between Blood Oxygen Level-Dependent Magnetic Resonance Imaging Images and Prognosis of Patients with Multicenter Diabetic Nephropathy on Account of Artificial Intelligence Segmentation Algorithm

Overview

Journal Comput Math Methods Med

Publisher Hindawi

Specialty Medical Informatics

Date 2022 Jul 21

PMID 35860185

Authors

Yifan Zhang

Xiaohan Wang

Zhaoyu Lin

Guojian Shao

Renban Wang

Zhoutao Xie

Affiliations

Soon will be listed here.

Abstract

This study was aimed to analyze the correlation between blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) images and prognosis of patients with diabetic nephropathy (DN) based on artificial intelligence (AI) segmentation algorithm, so as to provide references for diagnosis and treatment as well as prognosis analysis of patients DN. In this study, a kernel function-based fuzzy C-means algorithm (KFCM) model was proposed, and the FCM algorithm based on neighborhood pixel information (BCFCM) and the FCM algorithm based on efficiency improvement (EnFCM) were introduced for comparison to analyze the image segmentation effects of three algorithms. The results showed that the partition coefficient (V) and partition entropy (V) of the KFCM algorithm were 0.801 and 0.602, respectively, which were better than those of the traditional FCM, BCFCM, and EnFCM algorithm. At the same time, the effects of correlation between renal cortex R2∗ (RC-R2∗), renal medulla R2∗ (RM-R2∗), renal cortex D (RC-D), renal medulla D (RM-D) and renal function on the prognosis were compared. The results showed that the correlation coefficients between RC-R2∗, RM-R2∗, RC-D, RM-D and renal function were 0.57, 0.62, 0.49, and 0.38, respectively; among them, RC-R2∗ and RM-R2∗ were negatively correlated to the estimated glomerular filtration rate (eGFR), and the difference between the groups was statistically significant ( <0.05). Among the factors affecting the prognosis of DN patients, the GFR, hemoglobin (Hb), RC-R2∗, RM-R2∗, and RC-D were all related to the prognosis of DN, and the difference between groups was statistically obvious ( <0.05). It suggested that the KFCM algorithm proposed in this study showed the relatively best segmentation effect on BOLD-MRI images for DN patients; an increase in R2∗ indicated a poor prognosis, and an increase in the RC-D value indicated a better prognosis.

Citing Articles

Neuroimaging studies of resting-state functional magnetic resonance imaging in eating disorders.

Chen X, Ai C, Liu Z, Wang G BMC Med Imaging. 2024; 24(1):265.

PMID: 39375605 PMC: 11460144. DOI: 10.1186/s12880-024-01432-z.

References

Mora-Gutierrez J, Garcia-Fernandez N, Slon Roblero M, Paramo J, Javier Escalada F, Wang D . Arterial spin labeling MRI is able to detect early hemodynamic changes in diabetic nephropathy. J Magn Reson Imaging. 2017; 46(6):1810-1817. DOI: 10.1002/jmri.25717. View

Bijkerk R, Kallenberg M, Zijlstra L, van den Berg B, de Bresser J, Hammer S . Circulating angiopoietin-2 and angiogenic microRNAs associate with cerebral small vessel disease and cognitive decline in older patients reaching end-stage renal disease. Nephrol Dial Transplant. 2020; 37(3):498-506. DOI: 10.1093/ndt/gfaa370. View

Gooding K, Lienczewski C, Papale M, Koivuviita N, Maziarz M, Dutius Andersson A . Prognostic imaging biomarkers for diabetic kidney disease (iBEAt): study protocol. BMC Nephrol. 2020; 21(1):242. PMC: 7323369. DOI: 10.1186/s12882-020-01901-x. View

Pruijm M, Hofmann L, Zanchi A, Maillard M, Forni V, Muller M . Blockade of the renin-angiotensin system and renal tissue oxygenation as measured with BOLD-MRI in patients with type 2 diabetes. Diabetes Res Clin Pract. 2012; 99(2):136-44. DOI: 10.1016/j.diabres.2012.11.004. View

Yin W, Liu F, Li X, Yang L, Zhao S, Huang Z . Noninvasive evaluation of renal oxygenation in diabetic nephropathy by BOLD-MRI. Eur J Radiol. 2011; 81(7):1426-31. DOI: 10.1016/j.ejrad.2011.03.045. View

Wang R, Lin Z, Yang X, Zhao K, Wang S, Sui X . Noninvasive Evaluation of Renal Hypoxia by Multiparametric Functional MRI in Early Diabetic Kidney Disease. J Magn Reson Imaging. 2021; 55(2):518-527. DOI: 10.1002/jmri.27814. View

Samoilova Y, Matveeva M, Tonkikh O, Kudlay D, Oleinik O, Fimushkina N . [Brain tractography in type 1 and 2 diabetes and cognitive impairment]. Zh Nevrol Psikhiatr Im S S Korsakova. 2020; 120(10):33-37. DOI: 10.17116/jnevro202012010133. View

Gupta R, Haobam S, Krishna A, Ramchandran R, Satyaraddi A, Shetty S . Clinico-radiological characteristics and not laboratory markers are useful in diagnosing diabetic myonecrosis in Asian Indian patients with type 2 diabetes mellitus: A 10-year experience from South India. J Family Med Prim Care. 2019; 7(6):1243-1247. PMC: 6293897. DOI: 10.4103/jfmpc.jfmpc_4_18. View

Wang Z, Kumar R, Banerjee S, Hsu C . Blood oxygen level-dependent (BOLD) MRI of diabetic nephropathy: preliminary experience. J Magn Reson Imaging. 2011; 33(3):655-60. PMC: 3573698. DOI: 10.1002/jmri.22501. View

10.

Wang T, Zhang Y, Wang N, Liu Q, Wang Z, Liu B . Synergistical action of the β2 adrenoceptor and fatty acid binding protein 2 polymorphisms on the loss of glomerular filtration rate in Chinese patients with type 2 diabetic nephropathy. Int Urol Nephrol. 2018; 50(4):715-723. DOI: 10.1007/s11255-018-1812-2. View

11.

Wang C, Pedrycz W, Yang J, Zhou M, Li Z . Wavelet Frame-Based Fuzzy C-Means Clustering for Segmenting Images on Graphs. IEEE Trans Cybern. 2019; 50(9):3938-3949. DOI: 10.1109/TCYB.2019.2921779. View

12.

Zhou S, Zhang Y, Wang T, Huang S, Gong S, Wang J . Canagliflozin could improve the levels of renal oxygenation in newly diagnosed type 2 diabetes patients with normal renal function. Diabetes Metab. 2021; 47(5):101274. DOI: 10.1016/j.diabet.2021.101274. View

13.

Feng Y, Ye Y, Cheng Z, Hu J, Zhang C, Qian L . Non-invasive assessment of early stage diabetic nephropathy by DTI and BOLD MRI. Br J Radiol. 2019; 93(1105):20190562. PMC: 6948087. DOI: 10.1259/bjr.20190562. View

14.

Li Z, Cai Y, Tang Z, Zuo P, Liu R, Liu F . Lipo-prostaglandin E1 improves renal hypoxia evaluated by BOLD-MRI in patients with diabetic kidney disease. Clin Imaging. 2018; 50:239-242. DOI: 10.1016/j.clinimag.2018.04.015. View

15.

Wang Y, Jiang L, Wang X, Chen W, Shao Y, Chen Q . Evidence of altered brain network centrality in patients with diabetic nephropathy and retinopathy: an fMRI study using a voxel-wise degree centrality approach. Ther Adv Endocrinol Metab. 2019; 10:2042018819865723. PMC: 6661786. DOI: 10.1177/2042018819865723. View

16.

Lu W, Yan Z . An improved fuzzy C-means clustering algorithm for assisted therapy of chronic bronchitis. Technol Health Care. 2015; 23(6):699-713. DOI: 10.3233/THC-151023. View

17.

Saito J, Suzuki E, Tajima Y, Takami K, Horikawa Y, Takeda J . Increased plasma serotonin metabolite 5-hydroxyindole acetic acid concentrations are associated with impaired systolic and late diastolic forward flows during cardiac cycle and elevated resistive index at popliteal artery and renal insufficiency in.... Endocr J. 2015; 63(1):69-76. DOI: 10.1507/endocrj.EJ15-0343. View

18.

Wang Y, Feng Y, Lu C, Ju S . Renal fat fraction and diffusion tensor imaging in patients with early-stage diabetic nephropathy. Eur Radiol. 2018; 28(8):3326-3334. DOI: 10.1007/s00330-017-5298-6. View

19.

Wang S, Yang D, Rong R, Zhan X, Xiao G . Pathology Image Analysis Using Segmentation Deep Learning Algorithms. Am J Pathol. 2019; 189(9):1686-1698. PMC: 6723214. DOI: 10.1016/j.ajpath.2019.05.007. View

20.

Zhang H, Liu J, Chen L, Chen N, Yang X . Fuzzy Clustering Algorithm with Non-Neighborhood Spatial Information for Surface Roughness Measurement Based on the Reflected Aliasing Images. Sensors (Basel). 2019; 19(15). PMC: 6695898. DOI: 10.3390/s19153285. View