A multimodal computer-aided diagnostic system for precise identification of renal allograft rejection: Preliminary results

Radiologic evaluation of the kidney transplant donor and recipient

The kidney is the most common solid organ transplant globally and rates continue to climb, driven by the increasing prevalence of end stage renal disease (ESRD). Compounded by advancements in surgical techniques and immunosuppression leading to longer graft survival, radiologists evermore commonly evaluate kidney transplant patients and candidates, underscoring their role along the transplant process. Multiphase computed tomography (CT) with multiplanar and 3D reformatting is the primary method for evaluating renal donor candidates, detailing renal size, vascular/collecting system anatomy, and identifying significant pathologies such as renal vascular diseases and nephrolithiasis. Ultrasound is the preferred initial postoperative imaging modality for graft evaluation due to its low cost, accessibility, noninvasiveness, and lack of radiation. CT and magnetic resonance imaging (MRI) may be useful adjunctive imaging techniques in diagnosing transplant pathology when ultrasound alone is not diagnostic. Kidney transplant complications are categorized by an approximate timeline framework, aiding in differential diagnosis based on onset, duration, and severity and include perinephric fluid collections, graft compression, iatrogenic injuries, vascular compromise, graft rejection, and neoplastic processes. This review discusses imaging strategies and important findings along the transplant timeline, from donor assessment to long-term recipient complications.

Present and Future Applications of Artificial Intelligence in Kidney Transplantation

Artificial intelligence (AI) has a wide and increasing range of applications across various sectors. In medicine, AI has already made an impact in numerous fields, rapidly transforming healthcare delivery through its growing applications in diagnosis, treatment and overall patient care. Equally, AI is swiftly and essentially transforming the landscape of kidney transplantation (KT), offering innovative solutions for longstanding problems that have eluded resolution through traditional approaches outside its spectrum. The purpose of this review is to explore the present and future applications of artificial intelligence in KT, with a focus on pre-transplant evaluation, surgical assistance, outcomes and post-transplant care. We discuss its great potential and the inevitable limitations that accompany these technologies. We conclude that by fostering collaboration between AI technologies and medical practitioners, we can pave the way for a future where advanced, personalised care becomes the standard in KT and beyond.

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.

The value of functional magnetic resonance imaging in evaluating renal allograft function

BACKGROUND

To explore the value of arterial spin labeled (ASL) and blood oxygen level dependent (BOLD) imaging in evaluating allogeneic kidney function after renal transplantation.

METHODS

One hundred and thirty-five renal transplant patients were included. Demographic and imaging data were collected. Transplanted renal function, pathology, ASL and BOLD parameters were obtained. The patients were divided into normal, mild and severe injury group. The correlation between BOLD/ASL parameters and clinical data were evaluated. The prediction models were based on ASL and BOLD parameters using multivariate logistic analysis. Cox proportional hazards regression model was used to analyze the effects of gender, age, ASL and BOLD on the survival of renal transplant patients.

RESULTS

ASL and BOLD parameters were independently associated with renal function injury and renal allograft positive pathology. The AUC of prediction model for renal allograft function based on ASL and BOLD parameters was 0.85, while the AUC based on BOLD parameters was 0.70. Renal transplantation time showed a positive correlation with age, BOLD parameters and SCr，while a negative correlation with ASL parameters and eGFR. ASL parameter was positively correlated with eGFR and negatively correlated with Scr. BOLD parameter was negatively correlated with eGFR, ASL and positively correlated with Scr. Cox proportional hazards regression model showed that the increase of age could reduce the risk of renal function injury and positive pathology.

CONCLUSIONS

ASL and BOLD were associated with renal function injury and renal allograft positive pathology. ASL and BOLD had some value in predicting renal allograft function.

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.

Fluorescence spectroscopic profiling of urine samples for predicting kidney transplant rejection

Rejection is the primary factor affecting the functionality of a kidney post-transplant, where its prompt prediction of risk significantly influences therapeutic strategies and clinical outcomes. Current graft health assessment methods, including serum creatinine measurements and transplant kidney puncture biopsies, possess considerable limitations. In contrast, urine serves as a direct indicator of the graft's degenerative stage and provides a more accurate measure than peripheral blood analysis, given its non-invasive collection of kidney-specific metabolite. This research entailed collecting fluorescent fingerprint data from 120 urine samples of post-renal transplant patients using hyperspectral imaging, followed by the development of a learning model to detect various forms of immunological rejection. The model successfully identified multiple rejection types with an average diagnostic accuracy of 95.56 %.Beyond proposing an innovative approach for predicting the risk of complications post-kidney transplantation, this study heralds the potential introduction of a non-invasive, rapid, and accurate supplementary method for risk assessment in clinical practice.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

Multiparametric Functional MRI of the Kidney: Current State and Future Trends with Deep Learning Approaches

BACKGROUND

 Until today, assessment of renal function has remained a challenge for modern medicine. In many cases, kidney diseases accompanied by a decrease in renal function remain undetected and unsolved, since neither laboratory tests nor imaging diagnostics provide adequate information on kidney status. In recent years, developments in the field of functional magnetic resonance imaging with application to abdominal organs have opened new possibilities combining anatomic imaging with multiparametric functional information. The multiparametric approach enables the measurement of perfusion, diffusion, oxygenation, and tissue characterization in one examination, thus providing more comprehensive insight into pathophysiological processes of diseases as well as effects of therapeutic interventions. However, application of multiparametric fMRI in the kidneys is still restricted mainly to research areas and transfer to the clinical routine is still outstanding. One of the major challenges is the lack of a standardized protocol for acquisition and postprocessing including efficient strategies for data analysis. This article provides an overview of the most common fMRI techniques with application to the kidney together with new approaches regarding data analysis with deep learning.

METHODS

 This article implies a selective literature review using the literature database PubMed in May 2021 supplemented by our own experiences in this field.

RESULTS AND CONCLUSION

 Functional multiparametric MRI is a promising technique for assessing renal function in a more comprehensive approach by combining multiple parameters such as perfusion, diffusion, and BOLD imaging. New approaches with the application of deep learning techniques could substantially contribute to overcoming the challenge of handling the quantity of data and developing more efficient data postprocessing and analysis protocols. Thus, it can be hoped that multiparametric fMRI protocols can be sufficiently optimized to be used for routine renal examination and to assist clinicians in the diagnostics, monitoring, and treatment of kidney diseases in the future.

KEY POINTS

  · Multiparametric fMRI is a technique performed without the use of radiation, contrast media, and invasive methods.. · Multiparametric fMRI provides more comprehensive insight into pathophysiological processes of kidney diseases by combining functional and structural parameters.. · For broader acceptance of fMRI biomarkers, there is a need for standardization of acquisition, postprocessing, and analysis protocols as well as more prospective studies.. · Deep learning techniques could significantly contribute to an optimization of data acquisition and the postprocessing and interpretation of larger quantities of data..

CITATION FORMAT

· Zhang C, Schwartz M, Küstner T et al. Multiparametric Functional MRI of the Kidney: Current State and Future Trends with Deep Learning Approaches. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1775-8633.

Artificial intelligence and kidney transplantation

Artificial intelligence and its primary subfield, machine learning, have started to gain widespread use in medicine, including the field of kidney transplantation. We made a review of the literature that used artificial intelligence techniques in kidney transplantation. We located six main areas of kidney transplantation that artificial intelligence studies are focused on: Radiological evaluation of the allograft, pathological evaluation including molecular evaluation of the tissue, prediction of graft survival, optimizing the dose of immunosuppression, diagnosis of rejection, and prediction of early graft function. Machine learning techniques provide increased automation leading to faster evaluation and standardization, and show better performance compared to traditional statistical analysis. Artificial intelligence leads to improved computer-aided diagnostics and quantifiable personalized predictions that will improve personalized patient care.

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.

A DEEP LEARNING-BASED CAD SYSTEM FOR RENAL ALLOGRAFT ASSESSMENT: DIFFUSION, BOLD, AND CLINICAL BIOMARKERS

Recently, studies for non-invasive renal transplant evaluation have been explored to control allograft rejection. In this paper, a computer-aided diagnostic system has been developed to accommodate with an early-stage renal transplant status assessment, called RT-CAD. Our model of this system integrated multiple sources for a more accurate diagnosis: two image-based sources and two clinical-based sources. The image-based sources included apparent diffusion coefficients (ADCs) and the amount of deoxygenated hemoglobin (R2*). More specifically, these ADCs were extracted from 47 diffusion weighted magnetic resonance imaging (DW-MRI) scans at 11 different b-values (b0, b50, b100, …, b1000 s/mm²), while the R2* values were extracted from 30 blood oxygen level-dependent MRI (BOLD-MRI) scans at 5 different echo times (2ms, 7ms, 12ms, 17ms, and 22ms). The clinical sources included serum creatinine (SCr) and creatinine clearance (CrCl). First, the kidney was segmented through the RT-CAD system using a geometric deformable model called a level-set method. Second, both ADCs and R2* were estimated for common patients (N = 30) and then were integrated with the corresponding SCr and CrCl. Last, these integrated biomarkers were considered the discriminatory features to be used as trainers and testers for future deep learning-based classifiers such as stacked auto-encoders (SAEs). We used a k-fold cross-validation criteria to evaluate the RT-CAD system diagnostic performance, which achieved the following scores: 93.3%, 90.0%, and 95.0% in terms of accuracy, sensitivity, and specificity in differentiating between acute renal rejection (AR) and non-rejection (NR). The reliability and completeness of the RT-CAD system was further accepted by the area under the curve score of 0.92. The conclusions ensured that the presented RT-CAD system has a high reliability to diagnose the status of the renal transplant in a non-invasive way.