Differential Kidney Function Research Articles

Automated Analysis of Split Kidney Function from CT Scans Using Deep Learning and Delta Radiomics.

Background: Differential kidney function assessment is an important part of preoperative evaluation of various urological interventions. It is obtained through dedicated nuclear medical imaging and is not yet implemented through conventional Imaging. Objective: We assess if differential kidney function can be obtained through evaluation of contrast-enhanced computed tomography(CT) using a combination of deep learning and (2D and 3D) radiomic features. Methods: All patients who underwent kidney nuclear scanning at Mayo Clinic sites between 2018-2022 were collected. CT scans of the kidneys were obtained within a 3-month interval before or after the nuclear scans were extracted. Patients who underwent a urological or radiological intervention within this time frame were excluded. A segmentation model was used to segment both kidneys. 2D and 3D radiomics features were extracted and compared between the two kidneys to compute delta radiomics and assess its ability to predict differential kidney function. Performance was reported using receiver operating characteristics, sensitivity, and specificity. Results: Studies from Arizona & Rochester formed our internal dataset (n = 1,159). Studies from Florida were separately processed as an external test set to validate generalizability. We obtained 323 studies from our internal sites and 39 studies from external sites. The best results were obtained by a random forest model trained on 3D delta radiomics features. This model achieved an area under curve (AUC) of 0.85 and 0.81 on internal and external test sets, while specificity and sensitivity were 0.84,0.68 on the internal set, 0.70, and 0.65 on the external set. Conclusion: This proposed automated pipeline can derive important differential kidney function information from contrast-enhanced CT and reduce the need for dedicated nuclear scans for early-stage differential kidney functional assessment. Clinical Impact: We establish a machine learning methodology for assessing differential kidney function from routine CT without the need for expensive and radioactive nuclear medicine scans.

MP09-07 DEVELOPING AN ARTIFICIAL INTELLIGENCE MODEL TO PREDICT DIFFERENTIAL RENAL FUNCTION USING CONTRAST-ENHANCED CT SCANS

You have accessJournal of UrologyCME1 Apr 2023MP09-07 DEVELOPING AN ARTIFICIAL INTELLIGENCE MODEL TO PREDICT DIFFERENTIAL RENAL FUNCTION USING CONTRAST-ENHANCED CT SCANS Ramon Correa Medero, Daniel Salevitz, Jiwoong Jeong, Bhavik Patel, Imon Banerjee, and Haidar Abdul-Muhsin Ramon Correa MederoRamon Correa Medero More articles by this author , Daniel SalevitzDaniel Salevitz More articles by this author , Jiwoong JeongJiwoong Jeong More articles by this author , Bhavik PatelBhavik Patel More articles by this author , Imon BanerjeeImon Banerjee More articles by this author , and Haidar Abdul-MuhsinHaidar Abdul-Muhsin More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003224.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Differential kidney function plays an important role in the management of kidney disorders. We sought to assess if this can be obtained through an automated evaluation of contrast enhanced computed tomography using a combination of deep learning and machine learning algorithms without nuclear medical imaging. METHODS: All patients who underwent kidney nuclear scanning at Mayo Clinic between 2018-2022 were collected. Computerized tomographic (CT) scans of the kidneys that were obtained within a three-month interval before or after the nuclear scans were extracted. Patients who underwent a urological or radiological intervention within this time frame were excluded. A deep learning segmentation model was used to automatically segment kidneys (Figure 1). 2D and 3D radiomics features were extracted and compared between the two kidneys to compute delta radiomics and assess its ability to predict differential kidney function. The performance of these models was reported using receiver operating characteristics, precision, recall, and F1 score. RESULTS: There were 4118 nuclear medical scans. We randomly selected 303 CT scans for review. Following exclusion, there were 203 paired studies (Figure 2). The fine-tuned segmentation model demonstrated a Sorensen-Dice score of 0.7. The best results were obtained when the support vector classifier model was used on 3D delta radiomics features computed from the venous phase of contrast-enhanced CT scans. This model has an AUC of 0.90 with a precision, recall, and F1 score of 0.80, 0.80, and 0.82 respectively, to detect abnormal kidney function. CONCLUSIONS: This proposed automated pipeline can provide important differential kidney function information from contrast-enhanced cross section imaging without the need for dedicated nuclear scans. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e106 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Ramon Correa Medero More articles by this author Daniel Salevitz More articles by this author Jiwoong Jeong More articles by this author Bhavik Patel More articles by this author Imon Banerjee More articles by this author Haidar Abdul-Muhsin More articles by this author Expand All Advertisement PDF downloadLoading ...

The role of Plasma Renin Activity in prenatally diagnosed non-obstructed hydronephrosis at risk for surgery-an observational study.

Patients with asymptomatic prenatally diagnosed hydronephrosis may progress to needing surgery; no biomarker supporting the identification of these cases is currently available. The aim of the study wasto assess the role of Plasma Renin Activity (PRA) as a discriminatory factor to identify patients with asymptomatic prenatally diagnosed hydronephrosis who require close monitoring and are at-risk for surgery. The study group consists of 30 children prenatally diagnosed with asymptomatic unilateral hydronephrosis, initially managed with medical follow-up. Pyeloplasty was indicated if patients became symptomatic or if there was a significant drop in split renal function (SRF) during follow-up. An association was sought between PRA and renal parameters in post-hoc analysis. During the mean follow-up of 55.5 ± 8.2months, 13/30 (43.3%) patients developed delayed drainage and 8/30 (26.6%) underwent pyeloplasty. Mean PRA was higher at presentation in the group which later presented with a drop in differential kidney function ≥ 10%, while it was within the normal range for age in the other patients. Before pyeloplasty, progression to delayed drainage coincided with a drop in SRFand a rise in PRA. While PRA levels normalized after pyeloplasty, SRF improved but did not reach initial values. A mean rise of 68.9% in PRA preceded current indications for surgery by 27.5 ± 9.5months. A progressive increase in PRA in children with asymptomatic prenatally diagnosed hydronephrosis reflects obstructive stress in the tubulo-interstitial compartment. This stress is relieved by pyeloplasty and is reflected by a drop in PRA after surgery. PRA can, thus, serve as the discriminatory factor to identify hydronephrosis patients 'at-risk' for surgery even before the current criteria for pyeloplasty are met.

X-Capsular Incision for Tumor Enucleation (X-CITE)-Technique: A Method to Maximize Renal Parenchymal Preservation for Completely Endophytic Renal Tumors

ObjectiveTo describe the X-Capsular Incision for Tumor Enucleation (X-CITE) technique to resect endophytic renal tumors while preserving the overlying renal parenchyma. Subjects and methodsWe reviewed 1-year outcomes of 12 consecutive patients with a history of bilateral or multifocal renal tumors who presented to our institution with completely endophytic renal masse(s) between August 2017 and August 2018. Endophytic tumors were resected by making an X-shaped incision in the renal capsule and developing parenchymal flaps overlying the tumor pseudocapsule. Following tumor enucleation, the overlying parenchymal flaps were reapproximated. ResultsMedian follow up was 19.9 months (range 10.6-14.9). Most patients also had additional exophytic tumors with a median of 5 renal tumors removed per operation with a median largest renal tumor size of 3.2 cm. No intraoperative or postoperative complications occurred. There was no decline in renal function after surgery when comparing median pre- and 12-month postoperative eGFR (94.5 vs 91.5, P= 0.18).). Postoperative nuclear mercaptoacetyltriglycine (MAG-3) renal scans demonstrated equal differential kidney function after surgery. Limitations include short-term follow-up and referral bias at center specializing in multi-focal kidney surgery. ConclusionThe X-Capsular Incision for Tumor Enucleation technique is feasible, safe and effective with minimal collateral damage in the treatment of completely endophytic renal masses. Further investigation should identify which patients may benefit from this procedure and explore intermediate and long-term outcomes.

Acute renal infarction: a single center experience.

Acute renal infarction is a rare condition whose diagnosis is often delayed. Major risk factors include atrial fibrillation, valvular or ischemic heart disease, renal artery thrombosis/dissection and coagulopathy. We reviewed the medical records of 18 patients admitted to our Nephrology Department between 1999 and 2015 for acute renal infarction diagnosed by computed tomography. Tc-99m dimercaptosuccinic acid (DMSA) scintigraphy was performed in some patients during follow-up to assess parenchymal lesions and estimate differential kidney function. Mean age was 59.8years. Major associated risk factors included hypertension (44%), obesity (33%), atrial fibrillation (28%), peripheral vascular disease (17%), smoking (17%), prior thromboembolic event (11%), diabetes (11%), estroprogestinic therapy (11%). Seventy-two percent of patients presented with flank pain. Mean serum creatinine was 1.2±0.6mg/dl. Acute kidney injury occurred as the initial manifestation in two patients. Patients were managed conservatively, with low molecular weight heparin (83%) or aspirin (11%). At the end of follow-up serum creatinine was 1.1±0.3mg/dl; one patient remained on chronic hemodialysis. 58% of patients who underwent renal scintigraphy after a median of 8months had a reduced contribution of the previously affected kidney to total renal function. Risk factors associated with the development of chronic kidney disease following renal infarction are unknown. In our subjects, renal function remained stable in all but one patient who developed end stage renal disease. Further studies should focus on etiology and evolution of kidney function in patients with acute renal infarction.

Evaluation of the Impact of Shock Wave Lithotripsy on Kidneys Using a New Marker: How Do Neutrophil Gelatinese-associated Lypocalin Values Change After Shock Wave Lithotripsy?

To determine possible acute kidney injury with new marker neutrophil gelatinase-associated lipocalin (NGAL) in urine and to show the relationship between changes of this marker and conventional markers in patients undergoing shock wave lithotripsy (SWL). In patients with kidney stones, serum urea, creatinine, urine microalbumin, and NGAL levels were determined before SWL and at the first, second, and seventh days after SWL. In addition, patients who had undergone SWL were evaluated with Technetium-99m (Tc99m)-dimercaptosuccinic acid (DMSA) and Tc99m-diethylenetriaminepenta acetate renal scintigraphy 1 week before and 3 months after SWL. Forty patients were included in the study. All patients had a single stone in the kidney with an average size of 9.25 mm (range 5-15). No statistical change was found in the levels of average serum urea and creatinine levels, urine microglobulin, and NGAL levels, which were measured before SWL and after SWL. No significant difference was identified in urine NGAL and microalbumin levels of the groups, which were separated by shock wave number and shock energy amount on the first, second, and seventh days after SWL. In the high-energy SWL group, 3 patients had a statistical decrease in their differential kidney function measured with Tc99m difference between differential function rates of the kidney before and after SWL (DMSA) after 3 months after SWL. Our study found that, using both new and conventional parameters in the acute stage and 3 months later, SWL treatment does not cause acute kidney damage.

Normal differential renal function does not indicate a normal kidney after partial ureteropelvic obstruction and subsequent relief in 2-week-old piglets

We investigated the functional consequences of relieving ureteric obstruction in young pigs with experimental hydronephrosis (HN) induced by partial unilateral ureteropelvic obstruction. Three groups of animals were followed from the age of 2 weeks to the age of 14 weeks: Eight animals had severe or grades 3-4 HN throughout the study. Six animals had relief of the obstruction after 4 weeks. Six animals received sham operations at both ages. Morphological and functional examinations were performed at age 6 weeks and again at age 14 weeks and consisted of magnetic resonance imaging (MRI), technetium-diethylenetriaminepentaaceticacid ((99m)Tc-DTPA) renography, renal technetium-dimercaptosuccinicacid ((99m)Tc-DMSA) scintigraphy, and glomerular filtration rate (GFR) measurement. After relief of the partial obstruction, there was reduction of the pelvic diameter and improvement of urinary drainage. Global and relative kidney function was not significantly affected by either obstruction or its relief. Renal (99m)Tc-DMSA scintigraphy showed a change in both the appearance of the kidney and a change in the distribution within kidneys even after relief of obstruction. This study shows that partial ureteric obstruction in young pigs may be associated with little effect on global and differential kidney function. However, even after relief of HN, the distribution of (99m)Tc-DMSA in the kidney remains abnormal suggesting that a normal differential renal function may not represent a normal kidney.

Effects of background substraction on differential kidney function measured by static scintigraphy with DMSA and dynamic scintigraphy with MAG 3

The aim of this study was to assess the influence of background subtraction (BS) on estimation of differential kidney function (DF) on the static scintigraphy with (99m)Tc dimercaptosuccinic acid (DMSA) and dynamic scintigraphy with (99m)Tc mercaptoacetyltriglicine (MAG3) and to establish possible differences between DF values estimated with these methods. Patients (n=106) were selected among those scheduled to static and dynamic scintigraphies within 3 months, with no interim clinical and laboratory changes, regardless the kidney pathology. DF was estimated according to the uptake ratio method. Four background regions of interest (ROIs) were applied, identical for both studies, and DF values were recalculated after BS. The corrected values were compared to the values before correction, separately for DMSA and MAG3, and between the studies. The results showed that ROIs used introduce variable results for the same patients, predominantly when noncorrected DF values were <45%. There were no significant differences between DF values (corrected and noncorrected) obtained from static and dynamic scintigraphy in all groups of patients. Since numerous reasons can bring to the errors in DF estimation when BS is used, the conclusions are that it would probably be more accurate to avoid BS, particularly when DF values are compared in a patient follow-up, and when kidney function is normal. BS should be used, but always in the same way, only when there is a significant difference in kidney size, or when DF is <25%, since background activity is then considerable. MAG3 and DMSA can be equally used for DF estimation and their results compared in patient follow-up.

Pelvi-ureteric junction obstruction by crossing renal vessels: clinical and imaging features.

To present the characteristic clinical and imaging findings of pelvi-ureteric junction (PUJ) obstruction caused by crossing renal vessels (CRV), as it presents particular features within the spectrum of congenital hydronephrosis. Between April 1982 and December 2000, 384 children underwent surgery for PUJ obstruction. In 71 (18.5%; mean age 8.5 years, range 2 months to 14 years; 49 aged> 5 years), the obstruction was caused by CRV. The data collected from the medical records of these patients were analysed for their clinical presentation and imaging findings, i.e. ultrasonography (US), intravenous urography (IVU) and diuretic renography. The main presenting symptom was recurrent renal colic (pain, nausea, vomiting) in 59%, followed by urinary infection (UTI) in 20%, gross haematuria in 11% and an incidental diagnosis in 10%. By contrast, in the 313 children with intrinsic PUJ obstruction, renal colic was present in only 10.5%. Moreover, from 1991 to 2000, when the use of prenatal US became widespread, hydronephrosis was detected prenatally in 42 of 212 children (20%) with intrinsic PUJ obstruction, but in only two of 31 (6%) with obstruction by CRV. However, in 10 children with CRV operated on during this period, prenatal US had shown mild hydronephrosis (< 15 mm), which during the follow-up decreased until the children became symptomatic after 5-9 years (eight renal colic, two UTI). US during acute symptoms showed significant hydronephrosis (> 25 mm), and colour Doppler US of two patients directly showed the CRV. In all 71 children with CRV obstruction diuretic IVU and renography during the acute symptoms had an obstructive pattern, and in 24 renal colic was reproduced during the examination. The differential kidney function was < 40% in 11 children who presented with UTI; two required nephrectomy and in the remaining 69 an Anderson-Hynes pyeloplasty, after which none had an episode of renal colic or UTI during a mean (range) follow-up of 10.2 (2-20) years. PUJ obstruction by CRV should be suspected in older children presenting with recurrent renal colic and hydronephrosis. Good kidney function is expected in most of these children, despite their age, because the vascular obstruction is intermittent. Mild prenatal hydronephrosis that could decrease postnatally does not exclude the possibility of vascular obstruction, which may later become symptomatic. Imaging (US, diuretic IVU and renography) during an episode of pain is essential and colour Doppler US could help to establish the diagnosis in these cases. Knowing that a child has a CRV is important for choosing an open surgical approach rather than endoscopic pyelotomy, to avoid potential complications

The determination of relative kidney function in obstructive uropathy with 99Tcm-DMSA.

In this investigation differential kidney function studies were carried out for eight patients with obstructive uropathy and seven patients who did not suffer from obstruction. The aim of this investigation was to determine whether possible retention of 99Tcm-DMSA in the dilated system would lead to overestimation of the functional mass of an obstructed kidney. The clinical examination took place 4 and 24 h after i.v. injection of the 99Tcm-DMSA. From our results we conclude that this is not a major problem. It appeared that the 4 h values are as reliable as the 24 h values in the clinical situation.

The reliability of Tc-99m-DMSA scintigraphy in obstructive uropathy: is late scanning at 24 hours necessary?

Differential kidney function is usually studied by quantification of relative renal uptake at 2–4 h after injection of the radiopharmaceutical99mTc-dimercaptosuccinic acid (DMSA). The outcome of this measurement, however, may be unreliable in cases of obstructive uropathy. The obstructed kidney may retain the radiopharmaceutical in the dilated system, which may lead to relatively high values for functioning cortical mass. In this situation, determination of the split kidney function at 24 h instead of 4 h after application of99mTc-DMSA has been advocated. In order to compare results at 4 h and 24 h an investigation was performed in 8 patients with obstructive renal disease present for more than 2 weeks, and in 7 patients who did not suffer from obstruction. In these 15 patients the differential function measured at 4 h and at 24 h was the same. From our results we conclude that overestimation of the function of an obstructed kidney by99mTc-DMSA scanning at 4 h is not a major problem. According to the literature, however, in cases of acute obstruction or “complicated” obstruction with stones or infection,99mTc-DMSA scintigraphy can underestimate the potential function of the obstructed kidney.

The Use of Cryoscopy of the Urine in the Determination of the Differential Kidney Function

The Use of Cryoscopy of the Urine in the Determination of the Differential Kidney Function

Technic for an Accurate Performance of the Differential Kidney Function with Phenolsulphonephthalein

Technic for an Accurate Performance of the Differential Kidney Function with Phenolsulphonephthalein