Dataset Information

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization.

ABSTRACT:

Background

This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability.

Methods

Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences (T1, T1c, T2, FLAIR) underwent N4-Bias Field Correction (N4) and WhiteStripe normalization (N4/WS). Apparent diffusion coefficient (ADC) maps were normalized using N4 or N4/z-score. Nine machine-learning algorithms were trained for multiclass prediction of glioma types (IDH-mutant 1p/19q codeleted, IDH-mutant 1p/19q non-codeleted, IDH-wild type). Four approaches were compared: Anatomical, anatomical + ADC naive, anatomical + ADC N4, and anatomical + ADC N4/z-score. The University of California San Francisco (UCSF)-glioma dataset (n = 409) was used for external validation.

Results

Naïve-Bayes algorithms yielded overall the best performance on the internal test set. Adding ADC radiomics significantly improved AUC from 0.79 to 0.86 (P = .011) for the IDH-wild-type subgroup, but not for the other 2 glioma subgroups (P > .05). In the external UCSF dataset, the addition of ADC radiomics yielded a significantly higher AUC for the IDH-wild-type subgroup (P ≤ .001): 0.80 (N4/WS anatomical alone), 0.81 (anatomical + ADC naive), 0.81 (anatomical + ADC N4), and 0.88 (anatomical + ADC N4/z-score) as well as for the IDH-mutant 1p/19q non-codeleted subgroup (P < .012 each).

Conclusions

ADC radiomics can enhance the performance of conventional MRI-based radiomic models, particularly for IDH-wild-type glioma. The benefit of intensity normalization of ADC maps depends on the type and context of the used data.

SUBMITTER: Foltyn-Dumitru M

PROVIDER: S-EPMC11003539 | biostudies-literature | 2024 Jan-Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization.

Foltyn-Dumitru Martha M Schell Marianne M Sahm Felix F Kessler Tobias T Wick Wolfgang W Bendszus Martin M Rastogi Aditya A Brugnara Gianluca G Vollmuth Philipp P

Neuro-oncology advances 20240101 1

<h4>Background</h4>This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability.<h4>Methods</h4>Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences ...[more]

PMID: 38596719

Similar Datasets

Project description:BackgroundDiagnostic classification of diffuse gliomas now requires an assessment of molecular features, often including IDH-mutation and 1p19q-codeletion status. Because genetic testing requires an invasive process, an alternative noninvasive approach is attractive, particularly if resection is not recommended. The goal of this study was to evaluate the effects of training strategy and incorporation of biologically relevant images on predicting genetic subtypes with deep learning.MethodsOur dataset consisted of 384 patients with newly diagnosed gliomas who underwent preoperative MRI with standard anatomical and diffusion-weighted imaging, and 147 patients from an external cohort with anatomical imaging. Using tissue samples acquired during surgery, each glioma was classified into IDH-wildtype (IDHwt), IDH-mutant/1p19q-noncodeleted (IDHmut-intact), and IDH-mutant/1p19q-codeleted (IDHmut-codel) subgroups. After optimizing training parameters, top performing convolutional neural network (CNN) classifiers were trained, validated, and tested using combinations of anatomical and diffusion MRI with either a 3-class or tiered structure. Generalization to an external cohort was assessed using anatomical imaging models.ResultsThe best model used a 3-class CNN containing diffusion-weighted imaging as an input, achieving 85.7% (95% CI: [77.1, 100]) overall test accuracy and correctly classifying 95.2%, 88.9%, 60.0% of the IDHwt, IDHmut-intact, and IDHmut-codel tumors. In general, 3-class models outperformed tiered approaches by 13.5%-17.5%, and models that included diffusion-weighted imaging were 5%-8.8% more accurate than those that used only anatomical imaging.ConclusionTraining a classifier to predict both IDH-mutation and 1p19q-codeletion status outperformed a tiered structure that first predicted IDH-mutation, then 1p19q-codeletion. Including apparent diffusion coefficient (ADC), a surrogate marker of cellularity, more accurately captured differences between subgroups.

Project description:ObjectivesRadiomic features have demonstrated encouraging results for non-invasive detection of molecular biomarkers, but the lack of guidelines for pre-processing MRI-data has led to poor generalizability. Here, we assessed the influence of different MRI-intensity normalization techniques on the performance of radiomics-based models for predicting molecular glioma subtypes.MethodsPreoperative MRI-data from n = 615 patients with newly diagnosed glioma and known isocitrate dehydrogenase (IDH) and 1p/19q status were pre-processed using four different methods: no normalization (naive), N4 bias field correction (N4), N4 followed by either WhiteStripe (N4/WS), or z-score normalization (N4/z-score). A total of 377 Image-Biomarker-Standardisation-Initiative-compliant radiomic features were extracted from each normalized data, and 9 different machine-learning algorithms were trained for multiclass prediction of molecular glioma subtypes (IDH-mutant 1p/19q codeleted vs. IDH-mutant 1p/19q non-codeleted vs. IDH wild type). External testing was performed in public glioma datasets from UCSF (n = 410) and TCGA (n = 160).ResultsSupport vector machine yielded the best performance with macro-average AUCs of 0.84 (naive), 0.84 (N4), 0.87 (N4/WS), and 0.87 (N4/z-score) in the internal test set. Both N4/WS and z-score outperformed the other approaches in the external UCSF and TCGA test sets with macro-average AUCs ranging from 0.85 to 0.87, replicating the performance of the internal test set, in contrast to macro-average AUCs ranging from 0.19 to 0.45 for naive and 0.26 to 0.52 for N4 alone.ConclusionIntensity normalization of MRI data is essential for the generalizability of radiomic-based machine-learning models. Specifically, both N4/WS and N4/z-score approaches allow to preserve the high model performance, yielding generalizable performance when applying the developed radiomic-based machine-learning model in an external heterogeneous, multi-institutional setting.Clinical relevance statementIntensity normalization such as N4/WS or N4/z-score can be used to develop reliable radiomics-based machine learning models from heterogeneous multicentre MRI datasets and provide non-invasive prediction of glioma subtypes.Key points• MRI-intensity normalization increases the stability of radiomics-based models and leads to better generalizability. • Intensity normalization did not appear relevant when the developed model was applied to homogeneous data from the same institution. • Radiomic-based machine learning algorithms are a promising approach for simultaneous classification of IDH and 1p/19q status of glioma.

Project description:ObjectivesTo investigate the predictors of telomerase reverse transcriptase (TERT) promoter mutations in adults suffered from high-grade glioma (HGG) through radiomics analysis, develop a noninvasive approach to evaluate TERT promoter mutations.Methods126 adult patients with HGG (88 in the training cohort and 38 in the validation cohort) were retrospectively enrolled. Totally 5064 radiomics features were, respectively, extracted from three VOIs (necrosis, enhanced, and edema) in MRI. Firstly, an optimal radiomics signature (Radscore) was established based on LASSO regression. Secondly, univariate and multivariate logistic regression analyses were performed to investigate important potential variables as predictors of TERT promoter mutations. Besides, multiparameter models were established and evaluated. Eventually, an optimal model was visualized as radiomics nomogram for clinical evaluations.Results6 radiomics features were selected to build Radscore signature through LASSO regression. Among them, 5 were from necrotic VOIs and 1 was from enhanced ones. With univariate and multivariate analysis, necrotic volume percentages of core (CNV), Age, Cho/Cr, Lac, and Radscore were significantly higher in TERTm than in TERTw (p < 0.05). 4 models were built in our study. Compared with Model B (Age, Cho/Cr, Lac, and Radscore), Model A (Age, Cho/Cr, Lac, Radscore, and CNV) has a larger AUC in both training (0.955 vs. 0.917, p = 0.049) and validation (0.889 vs. 0.868, p = 0.039) cohorts. It also has higher performances in net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA) evaluation. Conclusively, Model A was visualized as a radiomics nomogram. Calibration curve shows a good agreement between estimated and actual probabilities.ConclusionsAge, Cho/Cr, Lac, CNV, and Radscore are important indicators for TERT promoter mutation predictions in HGG. Tumor necrosis seems to be closely related to TERT promoter mutations. Radiomics nomogram based on multiparameter MRI and CNV has higher prediction accuracies.

Dataset Information

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization.

Background

Methods

Results

Conclusions

Publications

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets