A Semi-Automated Region of Interest Detection Method in the Scintigraphic Glomerular Filtration Rate Determination for Patients With Abnormal Low Renal Function

A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy

OBJECTIVE

Accurate delineation of renal regions of interest (ROIs) is critical for the assessment of renal function in pediatric dynamic renal scintigraphy (DRS). The purpose of this study was to develop and evaluate a deep learning (DL) model that can fully automatically delineate renal ROIs and calculate renal function in pediatric 99mTechnetium-ethylenedicysteine (99mTc-EC) DRS.

METHODS

This study retrospectively analyzed 1,283 pediatric DRS data at a single center from January to December 2018. These patients were divided into training set (n = 1027), validation set (n = 128), and testing set (n = 128). A fully automatic segmentation of ROIs (FASR) model was developed and evaluated. The pixel values of the automatically segmented ROIs were calculated to predict renal blood perfusion rate (BPR) and differential renal function (DRF). Precision, recall rate, intersection over union (IOU), and Dice similarity coefficient (DSC) were used to evaluate the performance of FASR model. Intraclass correlation (ICC) and Pearson correlation analysis were used to compare the consistency of automatic and manual method in assessing the renal function parameters in the testing set.

RESULTS

The FASR model achieved a precision of 0.88, recall rate of 0.94, IOU of 0.83, and DSC of 0.91. In the testing set, the r values of BPR and DRF calculated by the two methods were 0.94 (P < 0.01) and 0.97 (P < 0.01), and the ICCs (95% confidence interval CI) were 0.94 (0.90-0.96) and 0.94 (0.91-0.96).

CONCLUSION

We propose a reliable and stable DL model that can fully automatically segment ROIs and accurately predict renal function in pediatric 99mTc-EC DRS.

Deep regression using 99mTc-DTPA dynamic renal imaging for automatic calculation of the glomerular filtration rate

OBJECTIVES

To develop and evaluate an artificial intelligence (AI) system that can automatically calculate the glomerular filtration rate (GFR) from dynamic renal imaging without manually delineating the regions of interest (ROIs) of kidneys and the corresponding background.

METHODS

This study was a single-center retrospective analysis of the data of 14,634 patients who underwent ^99mTc-DTPA dynamic renal imaging. Two systems based on convolutional neural networks (CNN) were developed and evaluated: sGFR_a predicts the radioactive counts of ROIs and calculates GFR using the Gates equation and sGFR_b directly predicts GFR from dynamic renal imaging without using other information. The root-mean-square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R² were used to evaluate the performance of our approach.

RESULTS

sGFR_a achieved an RMSE of 5.05, MAE of 4.03, MAPE of 6.07%, and R² of 0.93 for total GFR while sGFR_b achieved an RMSE of 7.61, MAE of 5.92, MAPE of 8.92%, and R² of 0.85 for total GFR. The accuracy of sGFR_a and sGFR_b in determining the stage of chronic kidney disease was 87.41% and 82.44%, respectively.

CONCLUSIONS

The findings of sGFR_a show that automatic GFR calculation based on CNN and using dynamic renal imaging is feasible and efficient and, additionally, can aid clinical diagnosis. Furthermore, the promising results of sGFR_b demonstrate that CNN can predict GFR from dynamic renal imaging without additional information.

KEY POINTS

• Our CNN-based AI systems can automatically calculate GFR from dynamic renal imaging without manually delineating the ROIs of kidneys and the corresponding background. • sGFR_a accurately predicted the radioactive counts of ROIs and calculated GFR using the Gates method. • sGFR_b-predicted GFR directly without any parameters related to the Gates equation.

Quantitative evaluation of chronically obstructed kidneys from noncontrast computed tomography based on deep learning

OBJECTIVE

To quantitatively report renal parenchymal volume (RPV), renal sinus volume (RSV), and renal parenchymal density (RPD) for chronically obstructed kidneys from noncontrast computed tomography (NCCT).

METHODS

This retrospective study was approved by the institutional review board of our hospital with a waiver of informed consent. We retrospectively collected 304 consecutive NCCT scans of urinary obstruction and constructed two datasets: one with 167 patient scans for parenchyma and sinus segmentation (segmentation dataset) and the other containing 137 scans from different patients diagnosed with chronic urinary obstruction (CUO dataset) and paired with split glomerular filtration rate (sGFR). A cascaded three-dimensional (3D) U-Net model was developed and validated for parenchyma and sinus segmentation. The RPV, RSV, and RPD of the CUO dataset were calculated by the model with manual editing. A multivariate analysis was performed to show the association between all parameters and the sGFR.

RESULTS

In the test dataset, the Dice values for parenchyma and sinus segmentation were 0.95 ± 0.04 and 0.90 ± 0.05, respectively. Compared with those of nonobstructed kidneys, the RSV and RPD of obstructed kidneys increased, but RPV and sGFR decreased (P < .001). For chronically obstructed kidneys, age (r = -0.292, P < .001), RPV (r = 0.849, P < .001), RSV (r = -0.331, P < .001), and RPD (r = -0.296, P < .001) were significantly correlated with sGFR. The fitted regression model was sGFR = 10.873-0.111 Age + 0.211 RPV - 0.022 RSV (r² = 0.712).

CONCLUSIONS

NCCT combined with deep learning has the potential to be a single radiological procedure for morphological and functional evaluation of chronically obstructed kidneys.

Influence of Early Bladder Imaging in Experimental Rabbits on the Quantitative Determination of Glomerular Filtration Rate by the Gates Method

Objective

To investigate the influence of early bladder imaging (EBI) in experimental rabbits on the quantitative calculation of glomerular filtration rate (GFR) by the Gates method.

Methods

We retrospectively analyzed the data of dynamic renal scintigraphy (DRS) in experimental rabbits. We calculated renal uptake during minutes 1-2 and 2-3 by correcting bladder radioactivity and computed the split GFR by renal uptake. Then, the EBI and GFR between 1-2 min and 2-3 min were compared, respectively.

Results

The EBI proportion (57.3%) at 2-3 min of DRS was higher than that (8.5%) at 1-2 min (P < 0.05). The correlations between the 1-2 min and 2-3 min uptake rates of unobstructed kidneys after correction (r = 0.952‐0.979) were higher than those before correction (r = 0.859‐0.936). However, the correlation between the two in obstructed kidneys was not improved (r_before = 0.967 versus r_after = 0.968). For unobstructed kidneys, the difference in GFR based on 2-3 min uptake between before and after correction was significant (P < 0.05), but not in obstructed kidneys (P > 0.05). For GFR based on 1-2 min uptake, the difference between before and after correction was not significant in obstructed or unobstructed kidneys (P > 0.05). Before correction, the GFR of unobstructed kidneys of 10.5% of the rabbits in the protein load test was lower than that in the baseline status, but not so after correction.

Conclusion

The 2-3 min EBI on DRS has a significant influence on the GFR calculated by the Gates method in experimental rabbits. Controlling water intake or calculating the GFR by 1-2 min renal uptake helps to avoid the influence of EBI on GFR.

Relative Ectopic Kidney Function Quantification Using DMSA Tomoscintigraphy Modality

The ectopic renal function estimation based on a manual region of interest (ROI) extraction could be considered as time consuming. It could also affect the clinical interpretation and thus deviate the therapeutic attitude. For this purpose, we propose an advanced tool to evaluate such function through the dimercaptosuccinic acid (DMSA) kidney scintigraphy scans. Methods. The proposed study has been performed on one hundred patients (fifty cases with normal kidneys and fifty cases with ectopic kidneys). We present our segmentation problems as several cost functions' optimization, each containing two terms: (i) a distribution matching prior, which evaluates a global similarity between distributions, and (ii) a smoothness prior to avoid the occurrence of small, isolated regions in the solution. Obtained following recent bound-relaxation results, the optima of the cost functions yield each kidney region in near real time. The Dice Metric (DM), the Jaccard Index (JI), and the correlation parameter have been adopted as validation parameters in order to evaluate the segmentation results. The obtained relative function of both kidneys has been then compared with that evaluated in clinical routine (planar projection) and then validated statistically by the Bland-Altman plots and the Interclass Correlation Coefficient (ICC). Results. Compared to the expert's manual kidney segmentation, the obtained results have been judged to be acceptable for clinical use with high Mean Dice Metric (MDM) value and high Jaccard Index (JI). The evaluated relative renal function has been different from those calculated by the projection planar method usually used in clinical routines. Conclusion. The proposed system could efficiently extract the renal region. The relative function estimation could be considered as more accurate. In fact, the background noise correction and the attenuation phenomenon, which could yield an error measure for renal ectopia, have been avoided. Our clinical staff members have validated the results and have suggested using such tool in their clinical routines.

Using Post Transplant 1 Week Tc-99m DPTA Renal Scan as Another Method for Predicting Renal Graft Failure

Purpose

The aims of this study were to determine whether post transplant renal scan performed at around 1 week can predict graft failure, and to identify the best predictive factors among easy-to-measure variables.

Materials and methods

We retrospectively evaluated patients who underwent Tc-99m DTPA renal scan at approximately 1 week after renal transplantation. They were separated into two categories at 3 months after the operation; graft failure and non-failure. Graft failure was confirmed by biopsy (rejection). Non-failure was confirmed either by biopsy or clinical follow-up with serum creatine (Cr). Scan parameters including glomerular filtration rate (GFR), Hilson perfusion index, peaks of the iliac and graft perfusion curves were analyzed. Clinical variables including age, sex, height, weight, systolic blood pressure, serum Cr, type of donated kidney, side of transplant, and immunosuppressant were also analyzed.

Results

Among total 45 patients, graft failure was present in 11 cases. The serum Cr level was significantly higher in the failure group. Among scan variables, only the GFR was significantly different between groups. GFR of <44.48 mL/min was predictive of graft failure (sen 88.9%). Serum Cr level >2.13 mg/dL was also predictive (sen 72.7%).

Conclusion

GFR on renal scan at approximately 1 week after kidney transplant can predict graft failure.

Automated Region of Interest Detection Method in Scintigraphic Glomerular Filtration Rate Estimation

The glomerular filtration rate (GFR) is a crucial index to measure renal function. In daily clinical practice, the GFR can be estimated using the Gates method, which requires the clinicians to define the region of interest (ROI) for the kidney and the corresponding background in dynamic renal scintigraphy. The manual placement of ROIs to estimate the GFR is subjective and labor-intensive, however, making it an undesirable and unreliable process. This work presents a fully automated ROI detection method to achieve accurate and robust GFR estimations. After image preprocessing, the ROI for each kidney was delineated using a shape prior constrained level set (spLS) algorithm and then the corresponding background ROIs were obtained according to the defined kidney ROIs. In computer simulations, the spLS method had the best performance in kidney ROI detection compared with the previous threshold method (threshold) and the Chan-Vese level set (cvLS) method. In further clinical applications, 223 sets of ^99mTc-diethylenetriaminepentaacetic acid renal scintigraphic images from patients with abnormal renal function were reviewed. Compared with the former ROI detection methods (threshold and cvLS), the GFR estimations based on the ROIs derived by the spLS method had the highest consistency and correlations (r = 0.98, p < 0.001) with the reference estimated by experienced physicians. The results indicate that the proposed automated ROI detection method has great potential in automated ROI detection for accurate and robust GFR estimation in dynamic renal scintigraphy.

GammaKey system for improved diagnostics with gamma cameras

We designed the GammaKey system for the acquisition, storage and analysis of images from semi-analogue gamma scintillation cameras (GSCs). The GammaKey system, operating on a standard PC, replicates the functionality of earlier dedicated computer systems, allows the exchange of data in the DICOM format and has an open architecture enabling the development of new diagnostic techniques. The main purpose of the GammaKey is to enable the continued use of old GSCs which have functional scintillation crystals, but also to permit data exchange with new digital GSCs. The GammaKey has been technically validated by standards established by the National Electrical Manufacturers Association. The GammaKey has been used for seven years in two leading centres for nuclear medicine in Serbia (the Clinical Center of Serbia, Belgrade, and the Clinical Center of Vojvodina, Novi Sad) in approximately 30,000 patients. Clinical application proves that the GammaKey is a robust and reliable system with high-quality image output. Data processing can be upgraded with non-standard features added on request as shown in two examples: (1) the testing of splenectomy efficacy in the case of thrombocytopenia with normal production; and (2) the detection and localisation of parathyroid adenomas.