Sonographic Grading of Renal Cortical Echogenicity and Raised Serum Creatinine in Patients With Chronic Kidney Disease

Singh, Arvinder; Gupta, Kamal Kumar; Chander, Ramesh; Vira, Mayur

doi:10.14260/jemds/2016/530

Cited by 23 publications

(32 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similar to findings of this study, Singh A et al have reported sonographic echogenicity grade 2 (42%) as the frequent echogenicity grade, that was followed by grade 1 (35%), grade 3 (16%) and grade 4 (7%) 15 . In contrast, Siddappa et al [grade -(48%), grade 2 (35%), grade 3 (11.7%) and grade 4 (5%)] and Khadka et al [grade 1 (32%), grade 2 (31%), grade 3 (20%) and grade 4 (16%)] have reported high frequency of grade 1 and grade 4 renal cortical echogenicities 10,18 .…”

Section: Discussionsupporting

confidence: 90%

See 1 more Smart Citation

Renal ultrasound findings in chronic kidney disease – a single centre study from Hambantota district of Sri Lanka

Kodikara

Gamage²,

Nanayakkara

et al. 2019

SL J. Med.

View full text Add to dashboard Cite

Background The aetiology of chronic kidney disease (CKD) has shown geographical clustering. Renal ultrasound (USS) is used as an aid to diagnose CKD, but USS features are known to vary with aetiology of CKD. Objectives To describe aetiological factors and USS features of CKD. Methods Renal USS was performed in adult patients diagnosed with CKD (n=100) and a control group (CG) with normal renal function (n=90). Demographic data, associated co-morbidities, serum creatinine values, renal length (RL), renal cortical echogenicity, and number of renal cysts were recorded. CKD severity was graded. Results Hypertension (38%) and diabetes (17%) were the commonest aetiological factors of CKD. Severity of CKD was as follows: 35% grade 3a, 39% grade 3b, 11% grade 2, and 15% grade 4. Mean RL of the CKD group (9.07cm; SD=0.84) was significantly lower (p<0.001) than the CG (9.83cm; SD=0.79). In the CG, the left kidney was longer than the right kidney (T=2.89; P=0.04); but no significant RL difference between both sides was seen in the CKD group (T=0.19; p=0.19). CKD patients (14%) had small kidneys with increased renal cortical echogenicity (95.7%); 55% in sonographic echogenicity grade 2, 20% grade 1, 30% grade 3, 3% normal echogenicity, and 2% grade 4. RL progressively decreased with CKD severity.

show abstract

Section: Discussionsupporting

confidence: 90%

“…In contrast to Khadka at al., who reported 21% small kidneys (<8cm) 10 , we found only 14% small kidneys. In agreement with Khadka et al, another study reported 35% small kidneys among CKD patients 15 . In this study, a large kidney was defined if it was >2SD of the mean renal size of the control group: >11.4 cm.…”

Section: Discussionsupporting

confidence: 89%

Renal ultrasound findings in chronic kidney disease – a single centre study from Hambantota district of Sri Lanka

Kodikara

Gamage²,

Nanayakkara

et al. 2019

SL J. Med.

View full text Add to dashboard Cite

show abstract

“…The least frequent cases were in age group >80 years (3%). Study by Singh A et al 1 showed the mean age of 54.32 year (range 19 -85 years). In their study, the most frequent age group was 51 -60 years (33%) followed by 41 -50 years (31%) and least frequent was >80 years (1%).…”

Section: Discussionmentioning

confidence: 96%

“…The grade of kidney disease is determined by cortical echogenicity with Grade 1 mild form, Grade 2 moderate form, Grade 3 severe form and Grade 4 as end-stage renal disease 1 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Correlation of Ultrasound Parameters with Serum Creatinine in Renal Parenchymal Disease

Khadka

Shrestha²,

Sharma

et al. 2019

J. Gandaki Med. Coll. Nepal

View full text Add to dashboard Cite

Introduction: Chronic kidney disease (CKD) is common cause of renal failure. It involves a progressive loss in the structure and function of the kidneys over the course of months, with or without decreased glomerular filtration rate (GFR). CKD can be diagnosed by its pathological abnormalities, changes in the levels of renal function markers in the blood or urine, or by imaging investigations (E.g. USG etc). Objectives: The purpose of our study is 1) To correlate renal echogenicity with serum creatinine in order to determine the significance of renal echogenicity for identifying the progression of chronic kidney disease (CKD) and for the sonographic grading of CKD, 2) To study association of blood pressure, renal cortical cysts and renal size with grade of chronic renal disease. Methods: This hospital based cross sectional study was carried out at National Kidney Centre, Banasthali Kathmandu. Two hundred patients above 20 years, diagnosed with CKD according to the guidelines of the National Kidney Foundation and referred for USG, were included in the study. Patients with kidney transplant, on dialysis, with liver disease and renal tumors were excluded. Ultrasound of kidneys was performed by senior consultant radiologist who was blind to the patients’ serum creatinine levels. The relationship between grade of CKD with serum creatinine, kidney size, blood pressure and cortical cysts were assessed. Statistical analysis was performed by Kruskal wallis test using SPSS version 17. P values less than 0.05 were considered statistically significant. Results: Mean serum creatinine was 1.7 mg/dl for Grade 1 (range: 1.1- 4.7 mg/dl, STD 0.44), 2.38 mg/dl for Grade 2 (range: 1.8-3.9 mg/dl STD 0.40), 4.18 mg/dl for Grade 3 (range: 2.6-6.0 mg/dl, STD 0.88), and 5.65 mg/dl for Grade 4 (range: 3.1-12 mg/dl, STD 2.0. Conclusion: Renal echogenicity and its grading correlates better with serum creatinine in CKD than other sonographic parameters. Hence, renal echogenicity is a better parameter than serum creatinine for estimating renal function in CKD, and has the added advantage of irreversibility.

show abstract

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

et al. 2019

View full text Add to dashboard Cite

Prediction of kidney function and chronic kidney disease (CKD) through kidney ultrasound imaging has long been considered desirable in clinical practice because of its safety, convenience, and affordability. However, this highly desirable approach is beyond the capability of human vision. We developed a deep learning approach for automatically determining the estimated glomerular filtration rate (eGFR) and CKD status. We exploited the transfer learning technique, integrating the powerful ResNet model pretrained on an ImageNet dataset in our neural network architecture, to predict kidney function based on 4,505 kidney ultrasound images labeled using eGFRs derived from serum creatinine concentrations. To further extract the information from ultrasound images, we leveraged kidney length annotations to remove the peripheral region of the kidneys and applied various data augmentation schemes to produce additional data with variations. Bootstrap aggregation was also applied to avoid overfitting and improve the model’s generalization. Moreover, the kidney function features obtained by our deep neural network were used to identify the CKD status defined by an eGFR of <60 ml/min/1.73 m 2 . A Pearson correlation coefficient of 0.741 indicated the strong relationship between artificial intelligence (AI)- and creatinine-based GFR estimations. Overall CKD status classification accuracy of our model was 85.6% —higher than that of experienced nephrologists (60.3%–80.1%). Our model is the first fundamental step toward realizing the potential of transforming kidney ultrasound imaging into an effective, real-time, distant screening tool. AI-GFR estimation offers the possibility of noninvasive assessment of kidney function, a key goal of AI-powered functional automation in clinical practice.

show abstract

Sonographic Grading of Renal Cortical Echogenicity and Raised Serum Creatinine in Patients With Chronic Kidney Disease

Cited by 23 publications

References 24 publications

Renal ultrasound findings in chronic kidney disease – a single centre study from Hambantota district of Sri Lanka

Renal ultrasound findings in chronic kidney disease – a single centre study from Hambantota district of Sri Lanka

Correlation of Ultrasound Parameters with Serum Creatinine in Renal Parenchymal Disease

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

Contact Info

Product

Resources

About