Non-Contrast-Enhancing Tumor: A New Frontier in Glioblastoma Research

Lasocki, Arian; Gaillard, Frank

doi:10.3174/ajnr.a6025

Cited by 97 publications

(92 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The idea of subtracting the T2 and FLAIR sequence is to demonstrate 1) the enhancing solid T2 heterogeneous portion of the lesion and separating it from non-solid non-enhancing edema. Assessment of the T2 hyperintense portions of the lesion is particularly important on the basis of the new concerns of this appearance on GBMs as noted in the recent papers 48 .…”

Section: Discussionmentioning

confidence: 99%

Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning

Lee

Wang

Türk

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential treatment delay for patients with early glioma recurrence. In this study, we proposed to use a multiparametric MRI data as a sequence input for the convolutional neural network with the recurrent neural network based deep learning structure to discriminate between pseudoprogression and true tumor progression. In this study, 43 biopsy-proven patient data identified as diffuse infiltrating glioma patients whose disease progressed/recurred were used. The dataset consists of five original MRI sequences; pre-contrast T1-weighted, post-contrast T1-weighted, T2-weighted, FLAIR, and ADC images as well as two engineered sequences; T1post–T1pre and T2–FLAIR. Next, we used three CNN-LSTM models with a different set of sequences as input sequences to pass through CNN-LSTM layers. We performed threefold cross-validation in the training dataset and generated the boxplot, accuracy, and ROC curve, AUC from each trained model with the test dataset to evaluate models. The mean accuracy for VGG16 models ranged from 0.44 to 0.60 and the mean AUC ranged from 0.47 to 0.59. For CNN-LSTM model, the mean accuracy ranged from 0.62 to 0.75 and the mean AUC ranged from 0.64 to 0.81. The performance of the proposed CNN-LSTM with multiparametric sequence data was found to outperform the popular convolutional CNN with a single MRI sequence. In conclusion, incorporating all available MRI sequences into a sequence input for a CNN-LSTM model improved diagnostic performance for discriminating between pseudoprogression and true tumor progression.

show abstract

Section: Discussionmentioning

confidence: 99%

Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning

Lee

Wang

Türk

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The Cancer Genome Atlas (TCGA) and Rembrandt). In recent years, however, several studies have started to gain molecular information about tumor cells at the edge located outside the area of contrast enhancement [8][9][10]. Likewise, through the collection of subcortical edge tissues from the non-eloquent deep white matter during supra-total resection during awake procedures, we have molecularly characterized the edge-and core-located glioblastoma cells.…”

Section: Introductionmentioning

confidence: 99%

Endothelial-secreted Endocan protein acts as a PDGFR alpha ligand and regulates vascularity, radioresistance, and regional phenotype in glioblastoma

Bastola

Ghochani³

et al. 2020

Preprint

View full text Add to dashboard Cite

Glioblastoma is a lethal brain cancer with active infiltration of tumor cells at the periphery where the vascular supply is enriched to create its own niche. Given that tumor recurrence is predominantly local, most of the seeds for lethal recurrence are hidden at the tumor edge and are surgically inaccessible. Here, we found that the spatial identity of the edge-located glioblastoma cells is, in the tested models, constructed by inter-cellular signals derived from the soluble factor endocan (protein product of Esm1) that is secreted by tumor-associated vascular endothelial (VE) cells. Injection of two distinct mouse glioblastoma models into Esm1 knockout (KO) mice resulted in tumors that failed to form typical edge lesions, resulting in the formation of compact core-only lesions. In sharp contrast, tumors derived in WT (Esm1-intact) mice harbored both tumor core and edge structures. Despite these obvious phenotypic differences, the aggressiveness of these two tumor types was indistinguishable in vivo. Surprisingly, regardless of the host system, co-injection of mixture of these two tumor subpopulations gave rise tumors with much worse survival, indicating that the accumulating tumor cell heterogeneity contributes to elevate malignancy. Mechanistically, endocan competes with PDGF to bind and activate PDGFRα in human glioblastoma cells, accompanied with the upregulation of the Myc transcriptional activity via alterations in its promoter chromatin structure. One of the mainstays of glioblastoma treatment, radiation, induces endocan secretion from VE cells, which promotes the radioresistance of the edge-located glioblastoma cells, allowing for the persistence of the edge structure. Collectively, these data suggest that intra-tumoral spatial heterogeneity is initiated by the VE cell-derived endocan signals through PDGFRα to construct tumor edge-to-core (E-to-C) architecture to cause lethal tumor recurrence.

show abstract

“…Differentiating non-enhancing tumour from peritumoural oedema is important as each subregion may yield different prognostic information. The non-enhancing tumour within the FLAIR abnormality may represent lower grade disease [40]. We show that non-enhancing tumour proportion relative to the whole-tumour volume rather than FLAIR volume or peritumoural oedema volume was associated with improved survival in the biopsy group.…”

Section: Discussionmentioning

confidence: 71%

Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival

2020

View full text Add to dashboard Cite

Background Measurement of volumetric features is challenging in glioblastoma. We investigate whether volumetric features derived from preoperative MRI using a convolutional neural network–assisted segmentation is correlated with survival. Methods Preoperative MRI of 120 patients were scored using Visually Accessible Rembrandt Images (VASARI) features. We trained and tested a multilayer, multi-scale convolutional neural network on multimodal brain tumour segmentation challenge (BRATS) data, prior to testing on our dataset. The automated labels were manually edited to generate ground truth segmentations. Network performance for our data and BRATS data was compared. Multivariable Cox regression analysis corrected for multiple testing using the false discovery rate was performed to correlate clinical and imaging variables with overall survival. Results Median Dice coefficients in our sample were (1) whole tumour 0.94 (IQR, 0.82–0.98) compared to 0.91 (IQR, 0.83–0.94 p = 0.012), (2) FLAIR region 0.84 (IQR, 0.63–0.95) compared to 0.81 (IQR, 0.69–0.8 p = 0.170), (3) contrast-enhancing region 0.91 (IQR, 0.74–0.98) compared to 0.83 (IQR, 0.78–0.89 p = 0.003) and (4) necrosis region were 0.82 (IQR, 0.47–0.97) compared to 0.67 (IQR, 0.42–0.81 p = 0.005). Contrast-enhancing region/tumour core ratio (HR 4.73 [95% CI, 1.67–13.40], corrected p = 0.017) and necrotic core/tumour core ratio (HR 8.13 [95% CI, 2.06–32.12], corrected p = 0.011) were independently associated with overall survival. Conclusion Semi-automated segmentation of glioblastoma using a convolutional neural network trained on independent data is robust when applied to routine clinical data. The segmented volumes have prognostic significance.

show abstract

Non-Contrast-Enhancing Tumor: A New Frontier in Glioblastoma Research

Cited by 97 publications

References 53 publications

Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning

Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning

Endothelial-secreted Endocan protein acts as a PDGFR alpha ligand and regulates vascularity, radioresistance, and regional phenotype in glioblastoma

Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival

Contact Info

Product

Resources

About