Possibilities of Using Multi-b-value Diffusion Magnetic Resonance Imaging for Classification of Brain Lesions

Grading of clear cell renal cell carcinoma using diffusion MRI with a multimodal apparent diffusion model

Objective

To assess the feasibility of utilizing parameters derived from a multimodal apparent diffusion (MAD) model to distinguish between low- and high-grade clear cell renal cell carcinoma (ccRCC).

Method

Diffusion-weighted imaging (DWI) scans with 12 b-values (0 - 3000 s/mm²) were conducted on 54 patients diagnosed with ccRCC (30 low-grade and 24 high-grade). The MAD model parameters, including diffusion coefficients (Dr, Dh, Dui, Df) representing restricted diffusion, hindered diffusion, unimpeded diffusion, and flow, respectively, were computed. Proportions corresponding to these diffusion types (fr, fh, fui, ff) and the heterogeneous nature of hindered diffusion (αh) were also obtained. Parameters were compared between low- and high-grade groups. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of these parameters, compared with the apparent diffusion coefficient (ADC) from a mono-exponential model.

Result

Significant differences between low- and high-grade ccRCC were observed in Dh (low-grade: 1.360 ± 0.11 μm2/ms; high-grade group, 1.254 ± 0.13 μm2/ms; P = 0.0327), fr (low-grade: 0.06 ± 0.005; high-grade: 0.08 ± 0.009; P = 0.0233), and αh (low-grade: 0.872 ± 0.22; high-grade: 0.896 ± 0.39; P = 0.0294). Additionally, the ADC values (low-grade: 0.924 ± 0.08 μm2/ms; high-grade group, 0.854 ± 0.04 μm2/ms; P = 0.0323) showed statistical significance. The combination of Dh, fr, and αh provided the highest diagnostic accuracy of 0.667, with a sensitivity of 0.750, specificity of 0.734, and area under the curve of 0.796, outperforming individual parameters and ADC.

Conclusion

The MAD diffusion model shows promise as a non-invasive imaging tool for distinguishing between low- and high-grade ccRCC, which may aid in preoperative planning and personalized treatment strategies.

Deep Learning Accelerated Brain Diffusion-Weighted MRI with Super Resolution Processing

OBJECTIVES

To investigate the clinical feasibility and image quality of accelerated brain diffusion-weighted imaging (DWI) with deep learning image reconstruction and super resolution.

METHODS

85 consecutive patients with clinically indicated MRI at a 3 T scanner were prospectively included. Conventional diffusion-weighted data (c-DWI) with four averages were obtained. Reconstructions of one and two averages, as well as deep learning diffusion-weighted imaging (DL-DWI), were accomplished. Three experienced readers evaluated the acquired data using a 5-point Likert scale regarding overall image quality, overall contrast, diagnostic confidence, occurrence of artefacts and evaluation of the central region, basal ganglia, brainstem, and cerebellum. To assess interrater agreement, Fleiss' kappa (ϰ) was determined. Signal intensity (SI) levels for basal ganglia and the central region were estimated via automated segmentation, and SI values of detected pathologies were measured.

RESULTS

Intracranial pathologies were identified in 35 patients. DL-DWI was significantly superior for all defined parameters, independently from applied averages (p-value <0.001). Optimum image quality was achieved with DL-DWI by utilizing a single average (p-value <0.001), demonstrating very good (80.9%) to excellent image quality (14.5%) in nearly all cases, compared to 12.5% with very good and 0% with excellent image quality for c-MRI (p-value <0.001). Comparable results could be shown for diagnostic confidence. Inter-rater Fleiss' Kappa demonstrated moderate to substantial agreement for virtually all defined parameters, with good accordance, particularly for the assessment of pathologies (p = 0.74). Regarding SI values, no significant difference was found.

CONCLUSION

Ultra-fast diffusion-weighted imaging with super resolution is feasible, resulting in highly accelerated brain imaging while increasing diagnostic image quality.