What question did this study set out to answer?

To compare different IVIM fitting techniques for their effectiveness in glioma grading accuracy.

April 1, 2026Open Access

A Comparative Study of IVIM ‐ MRI Fitting Techniques in Glioma Grading: Conventional, Bayesian, and Voxel‐Wise and Spatially‐Aware Deep Learning Approaches

Key Points

To compare different IVIM fitting techniques for their effectiveness in glioma grading accuracy.
Conducted retrospective analysis using fractal-noise simulations and DWI from glioma patients.
Evaluated fitting methods: least squares, segmented, Bayesian shrinkage, and deep learning approaches.
Used statistical tests like Mann–Whitney U and ROC-AUC analysis to assess tumor grading performance.
Transformer-based methods showed significantly lower median absolute percentage error for IVIM parameters than conventional methods.
In vivo evaluations indicated better visual quality and tumor delineation with deep learning methods.
Spatially-aware transformers achieved higher ROC-AUC values for tumor grading, particularly in differentiating Grade-4 tumors.

Abstract

ABSTRACT Background Intravoxel incoherent motion (IVIM) analysis of diffusion‐weighted MRI (DWI) provides microvascular perfusion and diffusion information. However, parameter estimation is limited by noise sensitivity, variability across fitting methods, and lack of standardization. Deep‐learning (DL)–based approaches, particularly spatially‐aware transformers, may improve robustness, but their clinical utility remains unexplored. Purpose To evaluate conventional, Bayesian, and DL–based IVIM fitting methods in glioma patients, focusing on tumor grading accuracy. Study Type Retrospective. Population Fractal‐noise‐based simulations and preoperative DWI from 20 glioma patients (5 Grade‐2, 3 Grade‐3, 12 Grade‐4). Sequence Spin‐echo echo‐planar DWI, 16 b values (0–900 s/mm 2 ), three orthogonal directions, 3 T. Assessment IVIM parameter maps were compared across least squares (LSQ), segmented (SEG), Bayesian shrinkage (BSP), and spatial‐homogeneity (FBM) priors, and DL–based methods, including IVIM‐NET, novel spatially‐aware transformers (NATTEN‐17), and a refined version (SA‐17). Simulation accuracy was evaluated using median absolute percentage error (MDAPE) and bias using median percentage error. In vivo data were visually assessed by the authors for noise suppression and structural preservation. Whole‐tumor diffusion coefficient ( D ), pseudo‐diffusion coefficient ( D *), and signal fraction ( f ) values were evaluated across tumor grades and for differentiating Grade‐4 from Grade‐2/3 tumors. Statistical Tests Mann–Whitney U tests for group comparisons; tumor grading performance using receiver operating characteristic–area under the curve (ROC‐AUC), and pairwise AUC differences using the DeLong test. Significance: p < 0.05. Results Transformer‐based methods achieved superior simulation accuracy, with significantly lower MDAPE for f and D * than all other approaches: NATTEN‐17 (5.91%, 13.31%), SA‐17 (7.73%, 13.66%), LSQ (21.95%, 54.34%), SEG (17.10%, 21.27%), BSP (12.35%, 22.79%), FBM (16.32%, 20.67%). In vivo, they provided superior visual quality and tumor delineation in f and D * maps, producing seemingly denoised versions of LSQ, while preserving tumor heterogeneity. The spatially‐aware transformers yielded consistently the highest ROC‐AUC values, particularly for D * (SA‐17: 0.78), significantly outperforming LSQ (0.62), SEG (0.58), FBM (0.62), and IVIM‐NET (0.71). Data Conclusion Transformer‐based model fitting has the potential to provide clinically valuable IVIM parameter estimates and improved tumor grading accuracy. Evidence Level 3. Technical Efficacy Stage 2.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper