Predicting the 1p/19q Codeletion Status of Presumed Low-Grade Glioma with an Externally Validated Machine Learning Algorithm

Voort, Sebastian R. van der; Incekara, Fatih; Wijnenga, Maarten M.J.; Kapas, Georgios; Gardeniers, Mayke; Schouten, Joost W.; Starmans, Martijn P.A.; Tewarie, Rishie Nandoe; Lycklama, Geert J.; French, Pim J.; Dubbink, Hendrikus J.; Bent, Martin J. van den; Vincent, Arnaud; Niessen, Wiro J.; Klein, Stefan; Smits, Marion

doi:10.1158/1078-0432.ccr-19-1127

Cited by 83 publications

(63 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Their analysis reveals that the cranial/caudal location of the tumor is one of the most important features in predicting 1p/19q co-deletion. Comparing the performance of our 1p/19q co-deletion prediction and the performance of van der Voort et al 61 , our 1p/19q co-deletion prediction model outperforms their model as illustrated in Table 3.…”

Section: Discussionmentioning

confidence: 79%

“…In addition, Akkus et al 60 do not consider the global information of the tumor, since their dataset uses only 3 slices of the MRI sequence of each patient as input, not the whole volume of the tumor. Another recent study by van der Voort et al 61 (Table 3) utilizes MR imaging features along with patients' age and sex using an SVM classifier to predict 1p/19q co-deletion in LGG patients. The authors use 284 LGG patients for training and another 129 LGG patients for testing.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Shboul

Chen

Iftekharuddin

2020

Sci Rep

View full text Add to dashboard Cite

Diffuse low-grade gliomas (LGG) have been reclassified based on molecular mutations, which require invasive tumor tissue sampling. Tissue sampling by biopsy may be limited by sampling error, whereas non-invasive imaging can evaluate the entirety of a tumor. This study presents a non-invasive analysis of low-grade gliomas using imaging features based on the updated classification. We introduce molecular (MGMT methylation, IDH mutation, 1p/19q co-deletion, ATRX mutation, and TERT mutations) prediction methods of low-grade gliomas with imaging. Imaging features are extracted from magnetic resonance imaging data and include texture features, fractal and multi-resolution fractal texture features, and volumetric features. Training models include nested leave-one-out crossvalidation to select features, train the model, and estimate model performance. The prediction models of MGMT methylation, IDH mutations, 1p/19q co-deletion, ATRX mutation, and TERT mutations achieve a test performance AUC of 0.83 ± 0.04, 0.84 ± 0.03, 0.80 ± 0.04, 0.70 ± 0.09, and 0.82 ± 0.04, respectively. Furthermore, our analysis shows that the fractal features have a significant effect on the predictive performance of MGMT methylation IDH mutations, 1p/19q co-deletion, and ATRX mutations. The performance of our prediction methods indicates the potential of correlating computed imaging features with LGG molecular mutations types and identifies candidates that may be considered potential predictive biomarkers of LGG molecular classification. Diffuse low-grade gliomas (LGG) are World Health Organization (WHO) Grade II and III gliomas. They are infiltrative in their nature and arising from glial cells (astrocytes or oligodendrocytes) of the central nervous system (CNS) 1,2. Recurrence and malicious progression are possible because of the difficulty in complete tumor resection 3. A group of these tumors may also develop into glioblastoma (GBM). An updated classification of diffuse LGG was included in the 2016 WHO Classification of Tumors of the CNS 4. The new classification of the diffuse LGG depends on the genetic driver mutations (IDH mutations, 1p/19q co-deletion, TERT mutations, and ATRX mutations). This new classification correlates well with patients' treatment and survival, for example, oligodendroglioma, defined by the 1p/19q co-deletion, are associated with longer survival compared to astrocytoma, which do not harbor the 1p/19q co-deletion 5. Molecular mutations are determined using invasive methods by obtaining usable tissue samples that have an increase in proliferation and neovascularization 6. Tissue sampling may also be associated with high cost, morbidity, and even mortality 7 , and depending on the sample, may undersample tumor components, especially in heterogeneous tumors. Consequently, developing alternative methods and non-invasively classify diffuse LGG into its different subtypes using imaging features and machine learning techniques have emerged as a promising body of research. In this work, we propose a non-invasive imaging-based...

show abstract

Section: Discussionmentioning

confidence: 79%

Section: Discussionmentioning

confidence: 99%

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Shboul

Chen

Iftekharuddin

2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Han et al [5] used an analysis to generate radiomics signature by extracting 647 MRI-based features from T2-MRIs and side information of patients. Van der Voort et al [11] used support vector machine classifier to extract features from T1 and T2-MRI along with age and sex information on 284 patients and validated results on 129 patients from TCIA. Yu et al [10] used radiomics based approach on FLAIR-MRI data from single hospital.…”

Section: Case Study Methods # Of Patients Test Accuracy (%)mentioning

confidence: 99%

“…Another radiomics based approach was studied by Yu et al [10] on IDH mutation prediction. Van der Voort et al [11] extracted 78 MR image features and applied support vector machine (SVM) on them together with age and sex information for 1p/19q status prediction. Zhang et al [12] also used SVM based approach for prediction of IDH mutation.…”

Section: Related Workmentioning

confidence: 99%

Domain Mapping and Deep Learning from Multiple MRI Clinical Datasets for Prediction of Molecular Subtypes in Low Grade Gliomas

Ali

Berger

et al. 2020

Brain Sciences

View full text Add to dashboard Cite

Brain tumors, such as low grade gliomas (LGG), are molecularly classified which require the surgical collection of tissue samples. The pre-surgical or non-operative identification of LGG molecular type could improve patient counseling and treatment decisions. However, radiographic approaches to LGG molecular classification are currently lacking, as clinicians are unable to reliably predict LGG molecular type using magnetic resonance imaging (MRI) studies. Machine learning approaches may improve the prediction of LGG molecular classification through MRI, however, the development of these techniques requires large annotated data sets. Merging clinical data from different hospitals to increase case numbers is needed, but the use of different scanners and settings can affect the results and simply combining them into a large dataset often have a significant negative impact on performance. This calls for efficient domain adaption methods. Despite some previous studies on domain adaptations, mapping MR images from different datasets to a common domain without affecting subtitle molecular-biomarker information has not been reported yet. In this paper, we propose an effective domain adaptation method based on Cycle Generative Adversarial Network (CycleGAN). The dataset is further enlarged by augmenting more MRIs using another GAN approach. Further, to tackle the issue of brain tumor segmentation that requires time and anatomical expertise to put exact boundary around the tumor, we have used a tight bounding box as a strategy. Finally, an efficient deep feature learning method, multi-stream convolutional autoencoder (CAE) and feature fusion, is proposed for the prediction of molecular subtypes (1p/19q-codeletion and IDH mutation). The experiments were conducted on a total of 161 patients consisting of FLAIR and T1 weighted with contrast enhanced (T1ce) MRIs from two different institutions in the USA and France. The proposed scheme is shown to achieve the test accuracy of 74 . 81 % on 1p/19q codeletion and 81 . 19 % on IDH mutation, with marked improvement over the results obtained without domain mapping. This approach is also shown to have comparable performance to several state-of-the-art methods.

show abstract

“…Although the 1p/19q codeletion is a prognostic marker of ODs with IDH1/2 mutations [6,7], 30-40% of all ODs are not codeleted at 1p/19q and have a worse prognosis [8][9][10]. Hence, the 1p/19q codeletion is reportedly associated with diagnosis, prognosis, and clinically favorable overall survival (OS) in glioma; however, the exact underlying mechanism remains unclear [3,[11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

CeRNA Network Analysis Representing Characteristics of Different Tumor Environments Based on 1p/19q Codeletion in Oligodendrogliomas

Ahn

Park

Kang

et al. 2020

Cancers

View full text Add to dashboard Cite

Oligodendroglioma (OD) is a subtype of glioma occurring in the central nervous system. The 1p/19q codeletion is a prognostic marker of OD with an isocitrate dehydrogenase (IDH) mutation and is associated with a clinically favorable overall survival (OS); however, the exact underlying mechanism remains unclear. Long non-coding RNAs (lncRNAs) have recently been suggested to regulate carcinogenesis and prognosis in cancer patients. Here, we performed in silico analyses using low-grade gliomas from datasets obtained from The Cancer Genome Atlas to investigate the effects of ceRNA with 1p/19q codeletion on ODs. Thus, we selected modules of differentially expressed genes that were closely related to 1p/19q codeletion traits using weighted gene co-expression network analysis and constructed 16 coding RNA–miRNA–lncRNA networks. The ceRNA network participated in ion channel activity, insulin secretion, and collagen network and extracellular matrix (ECM) changes. In conclusion, ceRNAs with a 1p/19q codeletion can create different tumor microenvironments via potassium ion channels and ECM composition changes; furthermore, differences in OS may occur. Moreover, if extrapolated to gliomas, our results can provide insights into the consequences of identical gene expression, indicating the possibility of tracking different biological processes in different subtypes of glioma.

show abstract

Predicting the 1p/19q Codeletion Status of Presumed Low-Grade Glioma with an Externally Validated Machine Learning Algorithm

Cited by 83 publications

References 35 publications

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Domain Mapping and Deep Learning from Multiple MRI Clinical Datasets for Prediction of Molecular Subtypes in Low Grade Gliomas

CeRNA Network Analysis Representing Characteristics of Different Tumor Environments Based on 1p/19q Codeletion in Oligodendrogliomas

Contact Info

Product

Resources

About