Search

Purpose: MRI-based radiomics models can predict genetic markers in pediatric low-grade glioma (pLGG). These models usually require tumour segmentation, which is tedious and time consuming if done manually. We propose a deep learning (DL) model to automate tumour segmentation and build an end-to-end radiomics-based pipeline for pLGG classification. Methods: The proposed architecture is a 2-step U-Net based DL network. The first U-Net is trained on downsampled images to locate the tumour. The second U-Net is trained using image patches centred around the located tumour to produce more refined segmentations. The segmented tumour is then fed into a radiomics-based model to predict the genetic marker of the tumour. Results: Our segmentation model achieved a correlation value of over 80% for all volume-related radiomic features and an average Dice score of.795 in test cases. Feeding the auto-segmentation results into a radiomics model resulted in a mean area under the ROC curve (AUC) of.843, with 95% confidence interval (CI) [.78-.906] and.730, with 95% CI [.671-.789] on the test set for 2-class (BRAF V600E mutation BRAF fusion) and 3-class (BRAF V600E mutation BRAF fusion and Other) classification, respectively. This result was comparable to the AUC of.874, 95% CI [.829-.919] and.758, 95% CI [.724-.792] for the radiomics model trained and tested on the manual segmentations in 2-class and 3-class classification scenarios, respectively. Conclusion: The proposed end-to-end pipeline for pLGG segmentation and classification produced results comparable to manual segmentation when it was used for a radiomics-based genetic marker prediction model. [ABSTRACT FROM AUTHOR]

Background: The determinants of outcomes for adult survivors of pediatric low-grade glioma (PLGG) are largely unknown.Methods: This study collected population-based follow-up information for all PLGG patients diagnosed in Ontario, Canada from 1985 to 2012 (n = 1202) and determined factors affecting survival. The impact of upfront radiation treatment on overall survival (OS) was determined for a cohort of Ontario patients and an independent reference cohort from the Surveillance, Epidemiology, and End Results database.Results: At a median follow-up of 12.73 years (range, 0.02-33 years), only 93 deaths (7.7%) were recorded, and the 20-year OS rate was 90.1% ± 1.1%. Children with neurofibromatosis type 1 had excellent survival and no tumor-related deaths during adulthood. Adverse risk factors included pleomorphic xanthoastrocytoma (P < .001) and a thalamic location (P < .001). For patients with unresectable tumors surviving more than 5 years after the diagnosis, upfront radiotherapy was associated with an approximately 3-fold increased risk of overall late deaths (hazard ratio [HR], 3.3; 95% confidence interval [CI], 1.6-6.6; P = .001) and an approximately 4-fold increased risk of tumor-related deaths (HR, 4.4; 95% CI, 1.3-14.6; P = .013). In a multivariate analysis, radiotherapy was the most significant factor associated with late all-cause deaths (HR, 3.0; 95% CI, 1.3-7.0; P = .012) and tumor-related deaths (HR, 4.4; 95% CI, 1.3-14.6; P = 0.014). A similar association between radiotherapy and late deaths was observed in the independent reference cohort (P < .001). In contrast to early deaths, late mortality was associated not with PLGG progression but rather with tumor transformation and non-oncological causes.Conclusions: The course of PLGG is associated with excellent long-term survival, but this is hampered by increased delayed mortality in patients receiving upfront radiotherapy. These observations should be considered when treatment options are being weighed for these patients. [ABSTRACT FROM AUTHOR]

Purpose: Biopsy-based assessment of H3 K27 M status helps in predicting survival, but biopsy is usually limited to unusual presentations and clinical trials. We aimed to evaluate whether radiomics can serve as prognostic marker to stratify diffuse intrinsic pontine glioma (DIPG) subsets. Methods: In this retrospective study, diagnostic brain MRIs of children with DIPG were analyzed. Radiomic features were extracted from tumor segmentations and data were split into training/testing sets (80:20). A conditional survival forest model was applied to predict progression-free survival (PFS) using training data. The trained model was validated on the test data, and concordances were calculated for PFS. Experiments were repeated 100 times using randomized versions of the respective percentage of the training/test data. Results: A total of 89 patients were identified (48 females, 53.9%). Median age at time of diagnosis was 6.64 years (range: 1–16.9 years) and median PFS was 8 months (range: 1–84 months). Molecular data were available for 26 patients (29.2%) (1 wild type, 3 K27M-H3.1, 22 K27M-H3.3). Radiomic features of FLAIR and nonenhanced T1-weighted sequences were predictive of PFS. The best FLAIR radiomics model yielded a concordance of.87 [95% CI:.86–.88] at 4 months PFS. The best T1-weighted radiomics model yielded a concordance of.82 [95% CI:.8–.84] at 4 months PFS. The best combined FLAIR + T1-weighted radiomics model yielded a concordance of.74 [95% CI:.71–.77] at 3 months PFS. The predominant predictive radiomic feature matrix was gray-level size-zone. Conclusion: MRI-based radiomics may predict progression-free survival in pediatric diffuse midline glioma/diffuse intrinsic pontine glioma. [ABSTRACT FROM AUTHOR]