PET-CT Defined Micro-Vascular Dysfunction and Cardiac Allograft Vasculopathy Risk Factors in Heart Transplant Recipients.

Microvascular dysfunction (MVD) is considered a form of cardiac allograft vasculopathy (CAV), independently associated with poor prognosis after heart transplantation (HTX). It is unknown whether traditional risk factors for CAV are also applicable to MVD. We retrospectively analyzed factors associated with MVD in 94 HTX recipients who completed a PET scan after a normal baseline left heart catheterization excluding epicardial CAV. MVD was defined by abnormal PET blood flow. The mean age was 52 ± 14 and MVD was found in 49 patients (53%). No donor risk factors were significantly associated with recipient MVD. Recipients risk factors for MVD included-diabetes mellitus (51% vs. 27%, p = 0.016) and hypertension (78% vs. 49%, p = 0.004) in patients with and without MVD, respectively. In a multivariate model, recipient hypertension and diabetes were the only significant determinants of MVD development (OR = 2.63, 95% CI [1.69-36.98], p = 0.009 and OR 2.1, 95% CI [1.10-15.38], p = 0.035, respectively). In conclusion, MVD was more associated with metabolic risk determinants rather than traditional CAV risk factors.

Transient Elastography for Noninvasive Evaluation of Posttransplant Liver Graft Fibrosis in Turkish Children, Ege University Children Hospital Experience.

OBJECTIVES: The influence of advancing fibrosis on graft survival in the context of pediatric liver transplantation accentuates the critical role of protocol-driven liver biopsies, a practice adopted by numerous medical centers. Consequently, the exigency for noninvasive methodologies to assess graft fibrosis assumes heightened importance when conventional clinical and laboratory parameters fail to reveal signs of liver damage. METHODS: This study aimed to assess the reliability of transient elastography (TE) in pediatric liver transplant recipients to detect graft fibrosis and compare the results of TE in patients who underwent biopsy. RESULTS: This prospective cohort study included liver transplanted children who underwent biopsy at Ege University Children's Hospital between October 1, 2021, and October 31, 2022, and a healthy control group. According to TE, fibrosis was detected in 40 patients, and no fibrosis was detected in 50. The median time to develop fibrosis was 100 months (95% CI [83.1-116.8]). A statistically significant positive correlation existed between LSM and METAVIR fibrosis score (r = 0.562, p = 0.001). There was a statistically significant difference in LSM between patients with F2 fibrosis (7.8-8.8 kPa ± 3.2) compared to patients with F0 fibrosis (5.2 kPa ± 0.7) (p = 0.005) and F1 fibrosis (6.1 kPa ± 1.5) (p = 0.041), on ANOVA. CONCLUSION: Liver allograft fibrosis is common in long-term follow-up in children who have undergone liver transplantation. Abnormal TE may guide physicians to consider liver biopsy to detect late allograft fibrosis in these children.

Cardiac magnetic resonance imaging characterization of acute rejection in a porcine heterotopic heart transplantation model.

Preclinical disease models are important for the advancement of therapeutics towards human clinical trials. One of the difficult tasks of developing a well-characterized model is having a reliable modality with which to trend the progression of disease. Acute rejection is one of the most devastating complications that can occur following organ transplantation. Specifically in cardiac transplantation, approximately 12% of patients will experience at least one episode of moderate or severe acute rejection in the first year. Currently, the gold standard for monitoring rejection in the clinical setting is to perform serial endomyocardial biopsies for direct histological assessment. However, this is difficult to reproduce in a porcine model of acute rejection in cardiac transplantation where the heart is heterotopically transplanted in an abdominal position. Cardiac magnetic resonance imaging is arising as an alternative for serial screening for acute rejection in cardiac transplantation. This is an exploratory study to create and define a standardized cardiac magnetic resonance screening protocol for characterizing changes associated with the presence of acute rejection in this preclinical model of disease. Results demonstrate that increases in T1 mapping, T2 mapping, left ventricular mass, and in late gadolinium enhancement are significantly correlated with presence of acute rejection.

3D Mapping of the DMEK Detachment Area from OCT Scans of the Anterior Segment of the Eye - Clinical Applications. / 3D-Kartierung der DMEK-Abhebungsfläche aus OCT-Scans des vorderen Augensegmentes mit klinischen Anwendungen.

Graft detachment is the most common complication after Descemet membrane endothelial keratoplasty (DMEK). To assess the amount of graft detachment, precision is limited when using slit-lamp biomicroscopy. Detachment of DMEK grafts can be assessed automatically on anterior segment optical coherence tomography (AS OCT) images and allows visualization of the area and volume of detachment using 3D maps. This article provides an overview of its applications such as accurately assessing the course of natural graft attachment, identification of potential risk factors for detachment and evaluation of the long-term effect of graft detachment. The 3D map of DMEK detachment may support researchers and clinicians in precise quantification of the area and volume of graft detachment even in large data sets, and the intuitive, fast and reliable evaluation.

Cardiac magnetic resonance imaging in heart transplant recipients with biopsy-negative graft dysfunction.

AIMS: Graft dysfunction (GD) after heart transplantation (HTx) can develop without evidence of cell- or antibody-mediated rejection. Cardiac magnetic resonance imaging (CMR) has an evolving role in detecting rejection; however, its role in biopsy-negative GD has not been described. This study examines CMR findings, evaluates outcomes based on CMR results, and seeks to identify the possibility of rejection missed through endomyocardial biopsy by using CMR in HTx recipients with biopsy-negative GD. METHODS AND RESULTS: HTx recipients with GD [defined as a decrease in left ventricular ejection fraction (LVEF) by >5% and LVEF < 50%] in the absence of rejection by biopsy or allograft vasculopathy and who underwent CMR were included in the study. The primary outcome was a composite of all-cause mortality, re-transplantation, or persistent LVEF < 50%. Overall, 34 HTx recipients developed biopsy-negative GD and underwent CMR. Left ventricular late gadolinium enhancement (LGE) on CMR was observed in 16 patients with two distinct patterns: diffuse epicardial (n = 13) and patchy (n = 3) patterns. Patients with LGE developed GD later after HTx [4 (1.4-6.8) vs. 0.8 (0.3-1.2) years, P < 0.001], were more often symptomatic (88% vs. 56%, P = 0.06), and had greater haemodynamic derangement (pulmonary capillary wedge pressure: 19 ± 7 vs. 13 ± 3 mmHg, P = 0.002) as compared with those without LGE. No significant difference was observed in the primary composite outcome between patients with LGE and those without LGE (50% vs. 38% of patients with events, P = 0.515). During a median follow-up of 3.8 years, mean LVEF improved similarly in the LGE-negative (37-55%) and LGE-positive groups (32-55%) (P = 0.16). CONCLUSIONS: Biopsy-negative GD occurs with and without LGE when assessed by CMR, indicative of possible rejection/inflammation occurring only in a subset of patients. Irrespective of LGE, LVEF improvement occurs in most GD patients, suggesting that other neurohormonal or immunomodulatory mechanisms may also contribute to GD development.

Using 1/2 Descending Time in CEUS to Identify Renal Allograft Rejection.

RATIONALE AND OBJECTIVES: This study investigates the potential of quantitative Contrast-Enhanced Ultrasound (CEUS) parameters to distinguish between graft dysfunction due to rejection and non-rejection in kidney transplant recipients. METHODS: In this retrospective study, 50 kidney transplant patients who presented elevated serum creatinine or proteinuria were analyzed. They were categorized as rejection or non-rejection based on biopsy outcomes. These classifications were applied in both derivation (n = 33) and validation cohorts (n = 17). Prior to the biopsy, all patients underwent a CEUS. Quantitative parameters derived from the CEUS were further analyzed for their consistency and reliability. Additionally, the relationship between the Banff scores, a standard for diagnosing transplant rejections, and these CEUS parameters was explored. RESULTS: Significant differences between rejection and non-rejection groups were observed in the CEUS parameters of derivation cohorts. Specifically, Peak Intensity (PI), 1/2 Descending Time (DT/2), Area Under Curve (AUC), and Mean Transit Time (MTT) stood out. Sensitivity and specificity for these parameters were 76.5% and 87.5% for PI, 76.5% and 81.2% for DT/2, 76.5% and 87.5% for AUC, and 68.8% and 94.1% for MTT, respectively. DT/2 and MTT showed superior interobserver agreement compared to PI and AUC. When extrapolating the cutoff values from the derivation cohort to the validation group, DT/2 and AUC exhibited optimal diagnostic precision with positive and negative predictive values being 91.7% vs. 100% and 100% vs. 85.7%, respectively. Additionally, DT/2 effectively differentiated between mild and moderate to severe microvascular inflammation, pivotal in diagnosing antibody-mediated renal transplant rejection. CONCLUSION: DT/2 from CEUS parameters presents as a reliable tool to differentiate rejection from non-rejection causes in renal transplant dysfunction. Yet, large-scale, multi-center studies are essential for further validation.

Radiomics in Kidney Transplantation: A Scoping Review of Current Applications, Limitations, and Future Directions.

Radiomics is increasingly applied to the diagnosis, management, and outcome prediction of various urological conditions. The purpose of this scoping review is to evaluate the current evidence of the application of radiomics in kidney transplantation, especially its utility in diagnostics and therapeutics. An electronic literature search on radiomics in the setting of transplantation was conducted on PubMed, EMBASE, and Scopus from inception to September 23, 2022. A total of 16 studies were included. The most widely studied clinical utility of radiomics in kidney transplantation is its use as an adjunct to diagnose rejection, potentially reducing the need for unnecessary biopsies or guiding decisions for earlier biopsies to optimize graft survival. Technology such as optical coherence tomography is a noninvasive procedure to build high-resolution optical cross-section images of the kidney cortex in situ and in real time, which can provide histopathological information of donor kidney candidates for transplantation, and to predict posttransplant function. This review shows that, although radiomics in kidney transplants is still in its infancy, it has the potential for large-scale implementation. Its greatest potential lies in the correlation with conventional established diagnostic evaluation for living donors and potential in predicting and detecting rejection postoperatively.

Contemporary and Emerging MRI Strategies for Assessing Kidney Allograft Complications: Arterial Stenosis and Parenchymal Injury, From the AJR Special Series on Imaging of Fibrosis.

MRI plays an important role in the evaluation of kidney allografts for vascular complications as well as parenchymal insults. Transplant renal artery stenosis, the most common vascular complication of kidney transplant, can be evaluated by MRA using gadolinium and nongadolinium contrast agents as well as by unenhanced MRA techniques. Parenchymal injury occurs through a variety of pathways, including graft rejection, acute tubular injury, BK polyomavirus infection, drug-induced interstitial nephritis, and pyelonephritis. Investigational MRI techniques have sought to differentiate among these causes of dysfunction as well as to assess the degree of interstitial fibrosis or tubular atrophy (IFTA)-the common end pathway for all of these processes-which is currently evaluated by invasively obtained core biopsies. Some of these MRI sequences have shown promise in not only assessing the cause of parenchymal injury but also assessing IFTA noninvasively. This review describes current clinically used MRI techniques and previews promising investigational MRI techniques for assessing complications of kidney grafts.

Functional MRI evaluation of blood oxygen dependent (BOLD) in renal allograft dysfunction: a prospective study.

BACKGROUND: Blood oxygen level dependent-magnetic resonance imaging (BOLD-MRI) is a non-invasive functional imaging technique that can be used to assess renal allograft dysfunction. PURPOSE: To evaluate the diagnostic performance of BOLD-MRI using a 3-T scanner in discriminating causes of renal allograft dysfunction in the post-transplant period. MATERIAL AND METHODS: This prospective study was conducted on 112 live donor-renal allograft recipients: 53 with normal graft function, as controls; 18 with biopsy-proven acute rejection (AR); and 41 with biopsy-proven acute tubular necrosis (ATN). Multiple fast-field echo sequences were performed to obtain T2*-weighted images. Cortical R2* (CR2*) level, medullary R2* (MR2*) level, and medullary over cortical R2* ratio (MCR) were measured in all participants. RESULTS: The mean MR2* level was significantly lower in the AR group (20.8 ± 2.8/s) compared to the normal group (24 ± 2.4/s, P <0.001) and ATN group (27.4 ± 1.7/s, P <0.001). The MCR was higher in ATN group (1.47 ± 0.18) compared to the AR group (1.18 ± 0.17) and normal functioning group (1.34 ± 0.2). Both MR2* (area under the curve [AUC] = 0.837, P <0.001) and MCR (AUC = 0.727, P = 0.003) can accurately discriminate ATN from AR, however CR2* (AUC = 0.590, P = 0.237) showed no significant difference between both groups. CONCLUSION: In early post-transplant renal dysfunction, BOLD-MRI is a valuable non-invasive diagnostic technique that can differentiate between AR and ATN by measuring changes in intra-renal tissue oxygenation.

Defining chronic rejection in vascularized composite allografts - do we have reliable surrogates to look for?

PURPOSE OF REVIEW: Chronic rejection (CR) is a major threat in the field of vascularized composite tissue allografts (VCAs) as it causes graft dysfunction and usually graft loss. Unfortunately, knowledge of CR in VCA is incomplete because of the limited number of VCA recipients, the heterogeneous nature of VCAs and the short follow-up. RECENT FINDINGS: The diagnosis of CR in VCA has relied on clinical and pathological findings. Clinical changes include graft fibrosis, dyschromia and ischemic/necrotic ulcerations. Pathological changes primarily affect allograft vessels and manifest with graft vasculopathy (i.e. myo-intimal proliferation and luminal narrowing of allograft vessels, leading to graft ischemia). Attempts are made to diagnose CR with non- or minimally-invasive techniques, such as imaging studies (ultrasound biomicroscopy, functional magnetic resonance imaging) and serum biomarkers. These techniques provide interesting results and further insight into the mechanisms of CR in VCA. SUMMARY: The diagnosis of CR in VCA still relies mainly on clinicopathological graft alterations; unfortunately, these become overt rather late during the rejection process, when reversal of CR is problematic. More recent, minimally- or non-invasive techniques have provided encouraging results, but their usefulness in the diagnosis of CR requires further studies. These data highlight the paramount importance of CR prevention.

Intestinal ultrasound may be a useful tool in monitoring acute rejection following intestinal transplantation.

BACKGROUND: Acute rejection is the leading cause of mortality and morbidity for children following intestinal transplantation. Rapid detection and prompt treatment are critical; however, the only reliable method of diagnosis and monitoring is endoscopic graft biopsies. The required regular anesthetics are particularly problematic in children, and non-invasive strategies are needed. METHODS: We describe the intestinal ultrasound findings of three children before and after treatment for rejection. Ultrasounds were performed within 24 h of endoscopically obtained biopsies which were used to establish a diagnosis of rejection and to define severity. A single sonographer performed the ultrasounds and was blinded to biopsy results at the time of the scanning. These findings are provided in the context of the ultrasound appearance of seven children who had no features of rejection on surveillance biopsies. RESULTS: Intestinal ultrasound demonstrated increased bowel wall thickness, vascularity, and mesenteric inflammation during moderate to severe rejection episodes. The submucosal layer was particularly thickened, which may represent a finding more specific for rejection. All patients demonstrated improvement in all quantitative ultrasound features correlating with the resolution of acute cellular rejection on histology. Patients with no evidence of rejection on biopsy had a bowel wall thickness range of 0.9-2.8 mm, suggesting a normal upper limit of 3 mm. CONCLUSION: Moderate and severe acute rejection may be detected and response to treatment can be monitored by intestinal ultrasound and, correlating with clinical improvement, can aid in follow-up.

A Novel Three-Dimensional Approach Towards Evaluating Endomyocardial Biopsies for Follow-Up After Heart Transplantation: X-Ray Phase Contrast Imaging and Its Agreement With Classical Histopathology.

Endomyocardial biopsies are the gold standard for surveillance of graft rejection following heart transplantation, and are assessed by classical histopathology using a limited number of previously stained slices from several biopsies. Synchrotron propagation-based X-ray phase contrast imaging is a non-destructive method to image biological samples without tissue preparation, enabling virtual 2D and 3D histopathology. We aimed to show the feasibility of this method to assess acute cellular rejection and its agreement to classical histopathology. Right ventricular biopsies were sampled from 23 heart transplantation recipients (20 males, mean age 54±14 years) as part of standard follow-up. The clinical diagnosis of potential rejection was made using classical histopathology. One additional study sample was harvested and imaged by X-ray phase contrast imaging, producing 3D datasets with 0.65 µm pixel size, and up to 4,320 images per sample. An experienced pathologist graded both histopathological and X-ray phase contrast images in a blinded fashion. The agreement between methods was assessed by weighted kappa, showing substantial agreement (kappa up to 0.80, p < 0.01) between X-ray phase contrast imaging and classical histopathology. X-ray phase contrast imaging does not require tissue processing, allows thorough analysis of a full myocardial sample and allows identification of acute cellular rejection.

Quantitative ultrasound for non-invasive evaluation of subclinical rejection in renal transplantation.

OBJECTIVES: This study aimed to investigate the predictive efficacy of shear-wave elastography, superb microvascular imaging (SMI), and CEUS for allograft rejection in kidney transplants without graft dysfunction. METHODS: From January 2021 to November 2021, 72 consecutive patients who underwent both allograft biopsy and ultrasound were evaluated. Blood test results were obtained within a week of the ultrasound examinations, which were performed before the protocol biopsy. Resistive index (RI), tissue viscoelasticity, vascular index, and quantitative CEUS parameters were measured. Patients were divided based on biopsy results into the rejection and non-rejection groups. RESULTS: Among the 72 patients, 21 patients had pathological characteristics of acute rejection. RI of allograft was significantly higher in the rejection group (p = 0.007), compared to the non-rejection group. There were no significant between-group differences in vascular indices of SMI, mean elasticity, and mean viscosity. Meanwhile, among the parameters obtained by the time-intensity curve on CEUS, the cortical and medullary ratios of average contrast signal intensity, peak enhancement, wash-in area AUC, wash-in perfusion index, wash-out AUC, and wash-in and wash-out AUC were significantly different between the two groups (p < 0.05). In the receiver operating characteristic curve analysis for predicting allograft rejection, the AUC was 0.853 for the combination of six CEUS parameters, RI, and blood urea nitrogen. CONCLUSIONS: Among non-invasive quantitative ultrasound measurements, CEUS parameters are the most useful for diagnosing subclinical allograft rejection. Furthermore, the combination of CEUS parameters, RI, and blood urea nitrogen may be helpful for the early detection of renal allograft rejection. KEY POINTS: • Among non-invasive quantitative ultrasound measurements, CEUS parameters are the most useful for the diagnosis of subclinical allograft rejection. • On CEUS, the C/M ratios of MeanLin, PE, WiAUC, WiPI, WoAUC, and WiWoAUC are significantly lower in the rejection group; the combination of these showed reliable predictive performance for rejection. • The combination of CEUS parameters, RI, and BUN has a high predictive capability for subclinical allograft rejection.

[68Ga]DOTA-TATE PET for the detection of early transplant rejection in a heterotopic allograft heart transplantation model of the rat: a pilot study.

BACKGROUND: The most important cause of heart transplant loss is early acute allograft rejection, caused by the infiltration of lymphocytes, development of edema and myocardial necrosis. It has been propagated that [68Ga]DOTA-TATE PET might be suitable to quantify the presence of SSTR over-expressing lymphocytes. With heterotopic allogenic heart transplant models in the rat readily available, we aimed to investigate, if monitoring and quantification of acute allograft rejection after heterotopic allogenic heart transplantation was feasible by non-invasive serial [68Ga]DOTA-TATE PET. METHODS: Seventeen Lewis rats (9 for serial PET imaging, 8 for histological correlation) received allogenic heterotopic heart transplants from 17 Brown-Norway rats. On days 4, 6 and 7 a [68Ga]DOTA-TATE PET scan was performed. RESULTS: Imaging of acute transplant rejection until 7 days after allogenic heart transplantation in the rat is feasible. Heterotopic allografts showed significantly increased tracer uptake on day 4 until day 7 after transplantation, reflecting the process of histologically detected myocardial lymphocytic infiltration. Both the area of infarction and the amount of necrosis increased over the course of 7 days, with necrosis reaching statistical significance. CONCLUSIONS: We purport that the detected PET signal is primarily a specific marker of lymphocyte infiltration and only to a lesser extent an unspecific marker of infarction and necrosis. Thus, [68Ga]DOTA-TATE PET might be a suitable tool for serial imaging and quantification of lymphocyte infiltration as a direct mediator of acute allograft rejection at an early stage after heart transplantation.

Native T1 mapping detects both acute clinical rejection and graft dysfunction in pediatric heart transplant patients.

BACKGROUND: Cardiovascular magnetic resonance (CMR) is emerging as an important tool for cardiac allograft assessment. Native T1 mapping may add value in identifying rejection and in assessing graft dysfunction and myocardial fibrosis burden. We hypothesized that CMR native T1 values and features of textural analysis of T1 maps would identify acute rejection, and in a secondary analysis, correlate with markers of graft dysfunction, and with fibrosis percentage from endomyocardial biopsy (EMB). METHODS: Fifty cases with simultaneous EMB, right heart catheterization, and 1.5 T CMR with breath-held T1 mapping via modified Look-Locker inversion recovery (MOLLI) in 8 short-axis slices and subsequent quantification of mean and peak native T1 values, were performed on 24 pediatric subjects. A single mid-ventricular slice was used for image texture analysis using nine gray-level co-occurrence matrix features. Digital quantification of Masson trichrome stained EMB samples established degree of fibrosis. Markers of graft dysfunction, including serum brain natriuretic peptide levels and hemodynamic measurements from echocardiography, catheterization, and CMR were collated. Subjects were divided into three groups based on degree of rejection: acute rejection requiring new therapy, mild rejection requiring increased ongoing therapy, and no rejection with no change in treatment. Statistical analysis included student's t-test and linear regression. RESULTS: Peak and mean T1 values were significantly associated with acute rejection, with a monotonic trend observed with increased grade of rejection. Texture analysis demonstrated greater spatial heterogeneity in T1 values, as demonstrated by energy, entropy, and variance, in cases requiring treatment. Interestingly, 2 subjects who required increased therapy despite low grade EMB results had abnormal peak T1 values. Peak T1 values also correlated with increased BNP, right-sided filling pressures, and capillary wedge pressures. There was no difference in histopathological fibrosis percentage among the 3 groups; histopathological fibrosis did not correlate with T1 values or markers of graft dysfunction. CONCLUSION: In pediatric heart transplant patients, native T1 values identify acute rejection requiring treatment and may identify graft dysfunction. CMR shows promise as an important tool for evaluation of cardiac grafts in children, with T1 imaging outperforming biopsy findings in the assessment of rejection.

Progression of Portal Hypertension in Acute Cellular Rejection After Liver Transplantation.

OBJECTIVES: This study was designed to investigate the frequency of computed tomography features indicating progression of portal hypertension and their clinical relevance in patients who experienced acute cellular rejection after liver transplantation. MATERIALS AND METHODS: This retrospective study included 141 patients with pathologically diagnosed acute cellular rejection following liver transplant. Patients were divided into early and late rejection groups according to the time of diagnosis. Two radiologists analyzed the interval changes in spleen size and variceal engorgement on computed tomography images obtained at the times of surgery and biopsy. Aggravation of splenomegaly and variceal engorgement were considered computed tomography features associated with the progression of portal hypertension. Clinical outcomes, including responses to treatment and graft survival, were compared between patients with and without these features. RESULTS: The frequency of progression of portal hypertension was 31.9% and did not differ significantly in patients who experienced early (30.8% [28/91]) and late (34.0% [17/50]) rejection (P = .694). In the late rejection group, computed tomography features indicating progression of portal hypertension were significantly associated with poor response to treatment (P = .033). Graft survival in both the early and late rejection groups did not differ significantly in patients with and without progression of portal hypertension. CONCLUSIONS: Computed tomography features suggesting the progression of portal hypertension were encountered in about one-third of patients who experienced acute cellular rejection after liver transplant. Progression of portal hypertension was significantly related to poor response to treatment in the late rejection group.

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.