A radiomics-based model to differentiate glioblastoma from solitary brain metastases

Su, Chun-Qiu; Chen, X.-T.; Duan, Shaofeng; Zhang, J.-X.; You, Yongping; Lu, Shanshan; Hong, Xun Ning

doi:10.1016/j.crad.2021.04.012

Cited by 14 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To do that, we used Bland-Altman plots and analysed the accuracy of the predicted values from radiomic model after DL processing in comparison to the original predicted values. Considering radiomic model from [29], only 2 and 3 predicted values are not accurate after resampling and denoising DL process, respectively, which represent accuracies of 95 and 92.5% (same results were obtained with radiomic model from [30]). These results highlight the impressive ability of DL to capture the shape and very precise features of the reference/high quality images during the training step and then re-inject them into new downsampled or denoised images.…”

Section: Discussionsupporting

confidence: 66%

“…In comparison, predicted values obtained from DL images were slightly different from the values obtained from reference images (mean difference = 0.12, p < 0.05). Results for the other radiomic model [30] showed significant differences in predicted values for the fast images and non-significant differences for the DL images (mean difference = 0.15 and 0.01 for fast image and DL images, respectively. and p < 0.001 for fast images, Figure S2c,d).…”

Section: Impact Of Denoising DL Model On Radiomics Featuresmentioning

confidence: 90%

“…To evaluate the impact of DL algorithms on radiomics, we compared predictive radiomic models values before and after DL algorithm processing. Two predictive models of radiomic were used base on [ 29 , 30 ], which are radiomic models for the prediction of treatment response (overall survival) of BM from NSCLC and BM classification. More details on the radiomic models can be found in Table S2 .…”

Section: Methodsmentioning

confidence: 99%

“…A similar approach was undertaken with another radiomic model [30] which showed significant differences in predictive values for the fast images and non-significant differences for the DL images when compared to the reference images (mean difference = −0.36 and −0.07 for fast image and DL image, respectively and p < 0.001 for fast image, Figure S2a,b). As observed in Figure 6, the denoising DL model was able to reduce noise in the fast image and produce a high quality image similar to the reference image both in the healthy and pathological tissues.…”

Section: Impact Of Resampling DL Model On Radiomics Featuresmentioning

confidence: 96%

See 3 more Smart Citations

The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

Moummad

Jaudet

Lechervy

et al. 2021

Cancers

View full text Add to dashboard Cite

Background: Magnetic resonance imaging (MRI) is predominant in the therapeutic management of cancer patients, unfortunately, patients have to wait a long time to get an appointment for examination. Therefore, new MRI devices include deep-learning (DL) solutions to save acquisition time. However, the impact of these algorithms on intensity and texture parameters has been poorly studied. The aim of this study was to evaluate the impact of resampling and denoising DL models on radiomics. Methods: Resampling and denoising DL model was developed on 14,243 T1 brain images from 1.5T-MRI. Radiomics were extracted from 40 brain metastases from 11 patients (2049 images). A total of 104 texture features of DL images were compared to original images with paired t-test, Pearson correlation and concordance-correlation-coefficient (CCC). Results: When two times shorter image acquisition shows strong disparities with the originals concerning the radiomics, with significant differences and loss of correlation of 79.81% and 48.08%, respectively. Interestingly, DL models restore textures with 46.15% of unstable parameters and 25.96% of low CCC and without difference for the first-order intensity parameters. Conclusions: Resampling and denoising DL models reconstruct low resolution and noised MRI images acquired quickly into high quality images. While fast MRI acquisition loses most of the radiomic features, DL models restore these parameters.

show abstract

Section: Discussionsupporting

confidence: 66%

Section: Impact Of Denoising DL Model On Radiomics Featuresmentioning

confidence: 90%

Section: Methodsmentioning

confidence: 99%

Section: Impact Of Resampling DL Model On Radiomics Featuresmentioning

confidence: 96%

See 2 more Smart Citations

The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

Moummad

Jaudet

Lechervy

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…This study extended previous radiomic studies that only extracted features from cMRI sequences on enhancing tumor region or peri-enhancing edema region to differentiate GBM from SBM (12)(13)(14)(15)(32)(33)(34)(35). First, we incorporated DWI and 18 F-FDG PET based on cMRI sequences, which is the first of its kind.…”

mentioning

confidence: 80%

An Integrated Radiomics Model Incorporating Diffusion-Weighted Imaging and 18F-FDG PET Imaging Improves the Performance of Differentiating Glioblastoma From Solitary Brain Metastases

et al. 2021

View full text Add to dashboard Cite

BackgroundThe effectiveness of conventional MRI (cMRI)-based radiomics in differentiating glioblastoma (GBM) from solitary brain metastases (SBM) is not satisfactory enough. Therefore, we aimed to develop an integrated radiomics model to improve the performance of differentiating GBM from SBM.MethodsOne hundred patients with solitary brain tumors (50 with GBM, 50 with SBM) were retrospectively enrolled and randomly assigned to the training set (n = 80) or validation set (n = 20). A total of 4,424 radiomic features were obtained from contrast-enhanced T1-weighted imaging (CE-T1WI) with the contrast-enhancing and peri-enhancing edema region, T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI)-derived apparent diffusion coefficient (ADC), and 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images. The partial least squares (PLS) regression with fivefold cross-validation is used to analyze the correlation between different radiomic features and different modalities. The cross-validity analysis was performed to judge whether a new principal component or a new feature dimension can significantly improve the final prediction effect. The principal components with effective interpretation in all radiomic features were projected to a low-dimensional space (2D in this study). The effective features of the new projection mapping were then sent to the random forest classifier to predict the results. The performance of differentiating GBM from SBM was compared between the integrated radiomics model and other radiomics models or nonradiomics methods using the area under the receiver operating characteristics curve (AUC).ResultsThrough the cross-validity analysis of partial least squares, hundreds of radiomic features were projected into a new two-dimensional space to complete the construction of radiomics model. Compared with the combined radiomics model using DWI + 18F-FDG PET (AUC = 0.93, p = 0.014), cMRI + DWI (AUC = 0.89, p = 0.011), cMRI + 8F-FDG PET (AUC = 0.91, p = 0.015), and single radiomics model using cMRI (AUC = 0.85, p = 0.018), DWI (AUC = 0.84, p = 0.017), and 18F-FDG PET (AUC = 0.85, p = 0.421), the integrated radiomics model (AUC = 0.98) showed more efficient diagnostic performance. The integrated radiomics model (AUC = 0.98) also showed significantly better performance than any single ADC, SUV, or TBR parameter (AUC = 0.57–0.71, p < 0.05). The integrated radiomics model showed better performance in the training (AUC = 0.98) and validation (AUC = 0.93) sets than any other models and methods, demonstrating robustness.ConclusionsWe developed an integrated radiomics model incorporating DWI and 18F-FDG PET, which improved the performance of differentiating GBM from SBM greatly.

show abstract

Artificial Intelligence Imaging for Predicting High-risk Molecular Markers of Gliomas

Liang,

Jing,

Shao

et al. 2024

Clin Neuroradiol

View full text Add to dashboard Cite

A radiomics-based model to differentiate glioblastoma from solitary brain metastases

Cited by 14 publications

References 29 publications

The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

An Integrated Radiomics Model Incorporating Diffusion-Weighted Imaging and 18F-FDG PET Imaging Improves the Performance of Differentiating Glioblastoma From Solitary Brain Metastases

Artificial Intelligence Imaging for Predicting High-risk Molecular Markers of Gliomas

Contact Info

Product

Resources

About