Imaging evaluation of kidney transplant recipients

RtNet: a deep hybrid neural network for the identification of acute rejection and chronic allograft nephropathy after renal transplantation using multiparametric MRI

BACKGROUND

Reliable diagnosis of the cause of renal allograft dysfunction is of clinical importance. The aim of this study is to develop a hybrid deep-learning approach for determining acute rejection (AR), chronic allograft nephropathy (CAN) and renal function in kidney-allografted patients by multimodality integration.

METHODS

Clinical and magnetic resonance imaging (MRI) data of 252 kidney-allografted patients who underwent post-transplantation MRI between December 2014 and November 2019 were retrospectively collected. An end-to-end convolutional neural network, namely RtNet, was designed to discriminate between AR, CAN and stable renal allograft recipient (SR), and secondarily, to predict the impaired renal graft function [estimated glomerular filtration rate (eGFR) ≤50 mL/min/1.73 m2]. Specially, clinical variables and MRI radiomics features were integrated into the RtNet, resulting in a hybrid network (RtNet+). The performance of the conventional radiomics model RtRad, RtNet and RtNet+ was compared to test the effect of multimodality interaction.

RESULTS

Out of 252 patients, AR, CAN and SR was diagnosed in 20/252 (7.9%), 92/252 (36.5%) and 140/252 (55.6%) patients, respectively. Of all MRI sequences, T2-weighted imaging and diffusion-weighted imaging with stretched exponential analysis showed better performance than other sequences. On pairwise comparison of resulting prediction models, RtNet+ produced significantly higher macro-area-under-curve (macro-AUC) (0.733 versus 0.745; P = 0.047) than RtNet in discriminating between AR, CAN and SR. RtNet+ performed similarly to the RtNet (macro-AUC, 0.762 versus 0.756; P > 0.05) in discriminating between eGFR ≤50 mL/min/1.73 m2 and >50 mL/min/1.73 m2. With decision curve analysis, adding RtRad and RtNet to clinical variables resulted in more net benefits in diagnostic performance.

CONCLUSIONS

Our study revealed that the proposed RtNet+ model owned a stable performance in revealing the cause of renal allograft dysfunction, and thus might offer important references for individualized diagnostics and treatment strategy.

Multimodality imaging features, treatment, and prognosis of post-transplant lymphoproliferative disorder in renal allografts: A case report and literature review

RATIONALE

Among patients with post-transplant lymphoproliferative disorder (PTLD), there is a high incidence of immunosuppressed transplant recipients. It is necessary to make an early diagnosis to increase the likelihood of a good prognosis.

PATIENT CONCERNS

We report a case of a 54-year-old female patient who developed PTLD after liver and kidney transplantation.

DIAGNOSES

We aimed to analyze the standard diagnosis and follow-up of PTLD with imaging. Radiologists need to be familiar with all imaging modalities when dealing with PTLD, including ultrasonography, computed tomography, magnetic resonance imaging, positron-emission tomography/computed tomography.

INTERVENTIONS

The initial treatment included both reduction of immunosuppression and rituximab. Then the treatment strategy changed to rituximab and chemotherapy. Finally, the treatment strategy combined glucocorticoid therapy.

OUTCOMES

The patient was in a stable condition at the 3-month follow-up.

LESSONS

Systematic evaluation of the various imaging modalities, treatment options, and prognoses of PTLD in renal allografts suggested that in cases with a poor prognosis, the proper imaging modalities provide essential information with regard to the determination of the appropriate treatment.

ACR Appropriateness Criteria® Renal Transplant Dysfunction

Renal transplantation is the treatment of choice in patients with end-stage renal disease because the 5-year survival rates range from 72% to 99%. Although graft survival has improved secondary to the introduction of newer immunosuppression drugs and the advancements in surgical technique, various complications still occur. Ultrasound is the first-line imaging modality for the evaluation of renal transplants in the immediate postoperative period and for long-term follow-up. In addition to depicting many of the potential complications of renal transplantation, ultrasound can also guide therapeutic interventions. Nuclear medicine studies, CT, and MRI are often helpful as complementary examinations for specific indications. Angiography remains the reference standard for vascular complications and is utilized to guide nonsurgical intervention. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer-reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Functional Evaluation of Transplanted Kidneys with Reduced Field-of-View Diffusion-Weighted Imaging at 3T

Objective

To determine the feasibility of reduced field-of-view diffusion-weighted imaging (rFOV DWI) with multi-b values to detect functional variability in transplanted kidneys.

Materials and Methods

Using a 3T MRI scanner, multi-b rFOV DWI of transplanted kidney or native kidney was performed in 40 renal transplantation recipients and 18 healthy volunteers. The patients were stratified, according to an estimated glomerular filtration rate (eGFR): Group 1, eGFR ≥ 60 mL/min/1.73 m²; Group 2, eGFR ≥ 30 mL/min/1.73 m² and < 60 mL/min/1.73 m²; Group 3, eGFR < 30 mL/min/1.73 m². Total apparent diffusion coefficient (ADC_T), perfusion-free ADC (ADC_D) and perfusion fraction (F_P) of kidneys were calculated and compared among the four groups. Correlations between the imaging results and eGFR were assessed.

Results

All volunteers had eGFR ≥ 60 mL/min/1.73 m², while 16, 16, and 8 patients were included in Groups 1, 2, and 3, respectively. In the renal cortex, ADCT was higher in Group 1 ([1.65 ± 0.13] × 10^-3 mm²/s) than Group 3 ([1.44 ± 0.11] × 10^-3 mm²/s) (p < 0.05), and the inter-group differences of F_P values were significant (all p < 0.05) (0.330 ± 0.024, 0.309 ± 0.019, 0.278 ± 0.033, and 0.250 ± 0.028 for control group, Groups 1, 2, and 3, respectively). Renal cortical ADC_T, ADC_D, F_P, and renal medullary ADC_T and F_P correlated positively with eGFR (r = 0.596, 0.403, 0.711, 0.341, and 0.323, respectively; all p < 0.05). When using 0.278 as the cutoff value, renal cortical F_P had a sensitivity of 97.1% and a specificity of 66.7% for predicting decreased renal function.

Conclusion

Multi-b rFOV DWI presents transplanted kidneys with high resolution, which is a promising functional tool for non-invasively monitoring function of transplanted kidneys.

Scintigraphic texture analysis for assessment of renal allograft function

Purpose

Early detection and monitoring of kidney function during the post-transplantation period is one of the most important issues for improving the accuracy of an initial diagnosis. The aim of this study was to evaluate texture analysis (TA) in scintigraphic imaging to detect changes in kidney status after transplantation.

Material and methods

Scintigraphic images were used for TA from a total of 94 kidney allografts (39 rejected and 55 non-rejected). Images corresponding to the frames at the 2^nd, 5^th, and 20^th minute of the study were used to determine the optimum time point for analysis of differences in texture features between the rejected and non-rejected allografts.

Results

Linear discriminant analysis indicated the best performance at the fifth minute frame for classification of the rejected and non-rejected allografts with receiver operating characteristic curve (A_z) of 0.982, corresponding to 91.89% sensitivity, 96.49% specificity, and 94.68% accuracy. Also, TA can differentiate acute tubular necrosis from acute rejection with A_z of 0.953 corresponding to 88% sensitivity, 92.31% specificity, and 90.62% accuracy at the 5^th minute frame. The best correlation between texture feature and kidney function was achieved at the 20^th minute frame (r = -0.396) for glomerular filtration rate.

Conclusions

TA has good potential for the characterisation of kidney failure after transplantation and can improve clinical diagnosis.

Role of nuclear medicine imaging in evaluation of complications following renal transplant

Evaluation of a failing renal allograft is a complex and challenging diagnostic problem. While ultrasonography with colour Doppler is usually the first approach for evaluation of graft dysfunction, radionuclide imaging is an excellent modality which provides complementary information regarding the perfusion and function of the allograft without any deleterious effect on the precious allograft. In this article, we review the imaging techniques of the nuclear medicine studies most commonly performed after renal transplant, discuss their roles and limitations in different clinical settings and illustrate with cases from our institution. Lastly, we will explore future development in the arena of nuclear imaging for renal transplant related complications.

Renal transplant vascular complications: the role of Doppler ultrasound

Improvements in the care of kidney transplant recipients and advances in immunosuppressive therapy have reduced the incidence of graft rejection. As a result, other types of kidney transplant complications, such as surgical, urologic, parenchymal, and vascular complications, have become more common. Although vascular complications account for only 5-10 % of all post-transplant complications, they are a frequent cause of graft loss. Ultrasonography, both in B-mode and with Doppler ultrasound, is a fundamental tool in the differential diagnosis of renal allograft dysfunction. Doppler ultrasound is highly specific in cases of transplanted renal artery stenosis, pseudoaneurysms, arteriovenous fistulas, and thrombosis with complete or partial artery or vein occlusion. A single measurements of color Doppler indexes display high diagnostic accuracy and in particular cases are more useful during the post-transplantation follow-up period. More recent techniques, such as contrast-enhanced ultrasound, undoubtedly increase the accuracy of ultrasonography in the diagnosis of vascular complications involving the transplanted kidney.

Ultrasound tissue characterization of the normal kidney

AIM

Ultrasound tissue characterization (USTC) is a precursor of ultrasound virtual histology (USVH), already applied to B-mode images of coronary, carotid, and peripheral arteries, as well as venous thrombosis. Elevated echogenicity has been described for a rejected transplanted kidney. We analyzed data from healthy young adults as reference for further renal USTC.

METHODS

Ultrasound kidney images of 10 volunteers were analyzed. Pixel brightness in the 0-to-255 range was rescaled to zero for black and 200 for fascia brightness before automatic classification into 14 ranges, including "blood-like" (0-4), "fat-like" (8-26), "hypoechoic muscle-like" (41-60), "hyperechoic muscle-like" (61-76), 4 ranges of "fiber-like" (112-196), "calcium-like" (211-255) and intermediary intervals. Nomenclature was readapted using nonechoic, hypoechoic I to IV, echoic I to IV, hyperechoic I to IV, and saturated echoes to avoid inference to actual kidney tissue. Descriptive and comparative statistics were based on percentages of pixels in specific brightness ranges.

SAMPLE POPULATION

Eight women and 2 men, 26 ± 4 years (range, 22-34 years) old, were studied. Kidney length was 10.5 ± 0.9 cm (9.0-12.0 cm). Doppler US resistivity index was 0.67 ± 0.03 (0.62-0.71).

RESULTS

Original fascia brightness converted to 200 value had a mean ± SD of 206 ± 16 (range, 181-236). Kidney grayscale median averaged 37 ± 6 (27-48). Most pixels were hypoechoic II to IV (8-60), averaging 78% ± 6% (66%-87%). Percentages for fat-like, intermediary fat/muscle-like, and hypoechoic muscle-like intervals averaged 25%, 28%, and 25%, respectively.

CONCLUSIONS

A reference database for USTC/USVH of normal young kidneys was created for future comparisons with transplanted and abnormal kidneys. Normal renal echoes have low brightness. Hyperechoic pixels may represent abnormalities.