INTRODUCTION

Around 850 million people globally have chronic kidney disease (CKD), a serious public health issue that raises morbidity, mortality, and medical expenses [1]. High-quality nephrology care rests on three pillars: prompt detection, accurate risk assessment, and individualized treatment regimens [2]. For assessing the activity and progression of the disease, standard clinical indicators such as albuminuria and estimated glomerular filtration rate (eGFR) are insufficient and late indicators. The measurements indicate considerable biological variability, inadequate spatial resolution, and insufficient characterization of the microstructural and functional alterations related to kidney injury [3, 4]. The CKD blind spot phenomenon is illustrated by the ability of imaging to diagnose CKD in patients with autosomal dominant polycystic kidney disease (ADPKD) decades earlier than eGFR or albuminuria thresholds, enabling the initiation of specific treatment [5–7]. This supports the biological plausibility that imaging advances can enable earlier, proactive management of CKD, potentially preserving kidney health [8].

Recent advancements in quantitative imaging have markedly improved the assessment of kidney disease. Advanced ultrasound (US) techniques, such as US elastography and contrast-enhanced Doppler, and multiparametric magnetic resonance imaging (MRI) enable the noninvasive evaluation of renal perfusion, fibrosis, oxygenation, lipid accumulation, and microvascular integrity, providing improved spatial and temporal accuracy [9, 10]. These modalities may surpass conventional laboratory assays and kidney biopsy in identifying early, subclinical changes that occur prior to significant functional decline, categorizing patients by progression risk, and facilitating real-time therapeutic monitoring [3, 10]. While biopsy remains the reference standard for histologic assessment, imaging offers a complementary, non-invasive view of both kidneys and can detect spatial heterogeneity beyond the limited sampling inherent to biopsy [11].

The integration of radiomics, artificial intelligence (AI), and multimodal data fusion enhances the diagnostic and prognostic capabilities of renal imaging, especially in the areas of transplant nephrology and CKD [12, 13]. This review synthesizes recent evidence on the role of renal imaging in risk stratification, therapeutic monitoring, and prognostic evaluation across kidney diseases. We highlight applications in CKD, its major causes [diabetic kidney disease (DKD) and hypertensive nephrosclerosis], and kidney transplantation, and explore integration with molecular biomarkers, AI, and omics-based tools. Future directions involve establishing imaging as a cornerstone of precision nephrology through clinical trials, multimodal approaches, and integration with molecular biomarkers, AI, and omics-based tools.

Specific features of renal imaging, such as multiparametric MRI in CKD, sophisticated US techniques, and the use of radiomics and AI in KT or CKD, have lately been covered in a number of authoritative reviews and position papers. Although these studies have yielded valuable insights related to modality or disease, they primarily take imaging into account in isolated clinical settings or as a technological supplement [3, 9, 13]. The current review, on the other hand, purposefully takes a cross-disease approach, incorporating data from early kidney injury through advanced CKD and KT, and placing more emphasis on quantitative imaging biomarkers with proven prognostic and therapeutic relevance than just descriptive imaging features (Fig. 1). This review attempts to provide a unified, translational roadmap for how renal imaging can inform risk prediction, therapeutic monitoring, and personalized care across the spectrum of kidney disease by synthesizing biomarkers of fibrosis, perfusion, oxygenation, microvascular integrity, and renal adiposity derived from ultrasound and MRI across disease states and placing these markers within emerging AI-enabled and multimodal precision-nephrology frameworks. Targeted searches of PubMed, Embase, and Web of Science were used to inform this narrative review, which mostly focused on research published in the last 10–15 years. Combinations of “chronic kidney disease,” “diabetic kidney disease,” “kidney transplantation,” “ultrasound elastography,” “contrast-enhanced ultrasound,” “BOLD MRI,” “arterial spin labeling,” “diffusion-weighted imaging,” “radiomics,” “renal fibrosis,” and “fatty kidney” were among the search terms used. Human studies, prospective cohorts, meta-analyses, and studies showing therapeutic or prognostic relationships were prioritized, with some preclinical data included where mechanistically instructive.

Figure 1:: Quantitative and functional renal imaging across the CKD spectrum. Quantitative MRI and ultrasound modalities enable early detection of key pathophysiological changes—fibrosis, hypoxia, and microvascular rarefaction—before traditional biomarkers (eGFR, albuminuria) decline. Techniques, such as, BOLD MRI, ASL, IVIM-DWI, T1 mapping, and elastography characterize oxygenation, perfusion, and tissue stiffness across chronic, diabetic, and metabolic kidney diseases. Early imaging-based detection and risk stratification may facilitate timely therapeutic action, slowing or halting CKD progression. Abbreviations: ADC, apparent diffusion coefficient; AI, artificial intelligence; ARFI, acoustic radiation force impulse; ASL, arterial spin labeling; BOLD, blood oxygenation level-dependent; CEUS, contrast-enhanced ultrasound; CKD, chronic kidney disease; CVD, cardiovascular disease; DKD, diabetic kidney disease; DWFG, death with functioning graft; eGFR, estimated glomerular filtration rate; IVIM-DWI , intravoxel incoherent motion diffusion-weighted imaging; MRA. magnetic resonance angiography; MRE. magnetic resonance elastography; MRI. magnetic resonance imaging; MRS. magnetic resonance spectroscopy; PAI. photoacoustic imaging; PDFF. proton-density fat fraction; PRS. polygenic risk score; R2*. transverse relaxation rate; RI. resistive index; RRI, renal resistive index; RSF, renal sinus fat; SMI, superb microvascular imaging; SWE, shear-wave elastography; STE, strain-tensor elastography; T1/T2, relaxation times; and US, ultrasound.