Model incorporating multiple diffusion MRI features: development and validation of a radiomics-based model to predict adult-type diffuse gliomas grade

Wang, Peng; Xie, Shaolei; Wu, Qiong; Weng, Lixin; Hao, Zhiyue; Yuan, Pengxuan; Zhang, Chi; Gao, Wei; Wang, Shaoyu; Zhang, Huapeng; Song, Yang; He, Jinlong; Gao, Yang

doi:10.1007/s00330-023-09861-0

Cited by 6 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have considered perfusion modeling for inclusion in subsequent studies ( 33 ). Finally, some new state-of-the-art diffusion models should be tried to be analyzed, even if short-term studies do not prove their practical superiority ( 34 ).…”

Section: Discussionmentioning

confidence: 99%

Heterogeneity matching and IDH prediction in adult-type diffuse gliomas: a DKI-based habitat analysis

Liu,

Wang,

Wang

et al. 2023

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

ObjectiveTo explain adult-type diffuse gliomas heterogeneity through diffusion kurtosis imaging-based habitat characteristics and develop and validate a comprehensive model for predicting isocitrate dehydrogenase (IDH) status.Materials and methodsIn this prospective secondary analysis, 103 participants (mean age, 52 years; range, 21-77; 54 [52%] male) pathologically diagnosed with adult-type diffuse gliomas were enrolled between June 2018 and February 2022. The Otsu method was used to generate habitat maps with mean diffusivity (MD) and mean kurtosis (MK) for a total of 4 subhabitats containing 16 habitat features. Habitat heatmaps were created based on the Pearson correlation coefficient. The Habitat imAging aNd clinicraD INtegrated prEdiction SyStem (HANDINESS) was created by combining clinical features, conventional MRI morphological features, and habitat image features. ROC, calibration curve, and decision curve analyses were used to select the optimal model after 32 pipelines for model training and validation.ResultsIn the restricted diffusion and high-density subhabitat, MK was highly correlated with MD (R2 = 0.999), volume (0.608) and percentage of volume (0.663), and this region had the highest MK value (P<.001). The unrestricted diffusion and low-density subhabitat had the highest MD value (P<.001). When MK was less than the Otsu threshold, there was still a difference between restricted diffusion and low-density and unrestricted diffusion and low-density subhabitats (P<.01). The HANDINESS enabled more accurate prediction of the IDH status in the training (AUC=0.951 [0.902-0.987]) and internal validation cohorts (0.938 [0.881-0.949]). AUC values for single-modality models and independent factors ranged from 0.593 to 0.916. Calibration and decision curve analyses showed that the HANDINESS demonstrated a high level of clinical applicability and predictive consistency.ConclusionDiffusion kurtosis imaging-based habitat analysis provides additional important information on microscopic tumor spatial heterogeneity. The HANDINESS has higher diagnostic performance and robustness than single-modality models.

show abstract

Section: Discussionmentioning

confidence: 99%

Heterogeneity matching and IDH prediction in adult-type diffuse gliomas: a DKI-based habitat analysis

Liu,

Wang,

Wang

et al. 2023

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

show abstract

Tumor Multiregional Mean Apparent Propagator (MAP) Features in Evaluating Gliomas—A Comparative Study With Diffusion Kurtosis Imaging (DKI)

Zeng,

Ma,

Xie

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundGlioma classification affects treatment and prognosis. Reliable imaging methods for preoperatively evaluating gliomas are essential.PurposeTo evaluate tumor multiregional mean apparent propagator (MAP) features in glioma diagnosis and to compare those with diffusion‐kurtosis imaging (DKI).Study TypeRetrospective study.Subjects70 untreated glioma patients (31 LGGs (low‐grade gliomas), 34 women; mean age, 47 ± 12 years, training (60%, n = 42) and testing cohorts (40%, n = 28)).Field Strength/Sequence3‐T, diffusion‐MRI using q‐space Cartesian grid sampling with 11 different b‐values.AssessmentTumor multiregional MAP (mean squared displacement (MSD); q‐space inverse variance (QIV); non‐Gaussianity (NG); axial/radial non‐Gaussianity (NGAx, NGRad); return‐to‐origin/axis/plane probability (RTOP, RTAP, and RTPP)); and DKI metrics (axial/mean/radial kurtosis (AK, MK, and RK)) on tumor parenchyma (TP) and peritumoral areas (PT) in histopathologically gliomas grading and genotyping were assessed.Statistical TestsMann–Whitney U; Kruskal–Wallis; Benjamini–Hochberg; Bonferroni‐correction; receiver operating curve (ROC) and area under curve (AUC); DeLong's test; Random Forest (RF). P value<0.05 was considered statistically significant after multiple comparisons correction.ResultsCompared with LGGs, MSD, and QIV were significantly lower in TP, whereas NG, NGAx, NGRad, RTOP, RTAP, RTPP, and DKI metrics were significantly higher in HGGs (high‐grade gliomas) (P ≤ 0.007), as well as in isocitrate‐dehydrogenase (IDH)‐mutated than IDH‐wildtype gliomas (P ≤ 0.039). These trends were reversed for PT (tumor grades, P ≤ 0.011; IDH‐mutation status, P ≤ 0.012). ROC analysis showed that, in TP, DKI metrics performed best in TP (AUC 0.83), whereas in PT, RTPP performed best (AUC 0.77) in glioma grading. AK performed best in TP (AUC 0.77), whereas MSD and RTPP performed best in PT (AUC 0.73) in IDH genotyping. Further RF analysis with DKI and MAP demonstrated good performance in grading (AUC 0.91, Accuracy 82%) and IDH genotyping (AUC 0.87, Accuracy 79%).Data ConclusionTumor multiregional MAP features could effectively evaluate gliomas. The performance of MAP may be similar to DKI in TP, while in PT, MAP may outperform DKI.Level of Evidence4Technical EfficacyStage 2

show abstract

Editorial for “Tumor Multiregional Mean Apparent Propagator (MAP) Features in Evaluating Gliomas—A Comparative Study With Diffusion Kurtosis Imaging (DKI)”

Medhi,

Varadharajan

2024

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Model incorporating multiple diffusion MRI features: development and validation of a radiomics-based model to predict adult-type diffuse gliomas grade

Cited by 6 publications

References 27 publications

Heterogeneity matching and IDH prediction in adult-type diffuse gliomas: a DKI-based habitat analysis

Heterogeneity matching and IDH prediction in adult-type diffuse gliomas: a DKI-based habitat analysis

Tumor Multiregional Mean Apparent Propagator (MAP) Features in Evaluating Gliomas—A Comparative Study With Diffusion Kurtosis Imaging (DKI)

Editorial for “Tumor Multiregional Mean Apparent Propagator (MAP) Features in Evaluating Gliomas—A Comparative Study With Diffusion Kurtosis Imaging (DKI)”

Contact Info

Product

Resources

About