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
• Kidney transplantation
• Machine learning, Neuronal networks
• Deep learning
• Support vector machines

An aim of this study was to assess the feasibility of DWI in the early period after kidney transplantation. We also aimed to compare ADC and eADC values in the cortex and medulla of the kidney, to estimate image noise and variability of measurements, and to verify possible relation between selected labolatory results and diffusion parameters in the transplanted kidney.

Examinations were performed using a 1.5 T MR unit. DWI (SE/EPI) was performed in the axial plane using b-values of 600 and 1000. ADC and eADC measurements were performed in four regions of interest within the renal cortex and in three regions within the medulla. Relative variability of results and signal-to-noise ratio (SNR) were calculated.

The analysis included 15 patients (mean age 52 years). The mean variability of ADC was significantly lower than that of eADC (6.8% vs. 10.8%, respectively; p<0.0001). The mean variability of measurements performed in the cortex was significantly lower than that in the medulla (6.2% vs. 11.5%, respectively; p<0.005). The mean SNR was higher in the measurements using b600 than b1000, it was higher in ADC maps than in the eADC maps, and it was higher in the cortex than in the medulla. ADC and eADC measured at b1000 in the cortex were higher in the group of the patients with eGFR ≤30 ml/min./1.73 m² as compared to patients with eGFR >30 ml/min./1.73 m² (p<0.05).

Diffusion-weighted imaging of transplanted kidneys is technically challenging, especially in patients in the early period after transplantation. From a technical point of view, the best quality parameters offer quality ADC measurement in the renal cortex using b1000. ADC and eADC values in the renal cortex measured at b1000 present a relationship with eGFR.

• Diffusion Magnetic Resonance Imaging
• Kidney Transplantation
• Magnetic Resonance Imaging