scholarly journals Diagnostic performance of radiomics using machine learning algorithms to predict MGMT promoter methylation status in glioma patients: a meta-analysis

2021 ◽  
Vol 27 (6) ◽  
pp. 716-724
Author(s):  
Huan Huang ◽  
◽  
Fei-fei Wang ◽  
Shigang Luo ◽  
Guangxiang Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Promoter Methylation ◽  
Diagnostic Performance ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Methylation Status ◽  
Mgmt Promoter Methylation ◽  
Machine Learning Algorithms ◽  
Mgmt Promoter ◽  
Mgmt Promoter Methylation Status

scholarly journals Artificial intelligence for early prediction of treatment response in glioblastoma

2021 ◽  
Vol 23 (Supplement_4) ◽  
pp. iv1-iv1
Author(s):  
Markand Patel ◽  
Jinfeng Zhan ◽  
Kal Natarajan ◽  
Robert Flintham ◽  
Nigel Davies ◽  
...  
Keyword(s):  
Machine Learning ◽  
Treatment Response ◽  
Promoter Methylation ◽  
Clinical Characteristics ◽  
Methylation Status ◽  
Response Assessment ◽  
Mgmt Promoter Methylation ◽  
Mgmt Promoter ◽  
Treatment Response Assessment ◽  
Mgmt Promoter Methylation Status

Abstract Aims Treatment response assessment in glioblastoma is challenging. Patients routinely undergo conventional magnetic resonance imaging (MRI), but it has a low diagnostic accuracy for distinguishing between true progression (tPD) and pseudoprogression (psPD) in the early post-chemoradiotherapy time period due to similar imaging appearances. The aim of this study was to use artificial intelligence (AI) on imaging data, clinical characteristics and molecular information within machine learning models, to distinguish between and predict early tPD from psPD in patients with glioblastoma. Method The study involved retrospective analysis of patients with newly-diagnosed glioblastoma over a 3.5 year period (n=340), undergoing surgery and standard chemoradiotherapy treatment, with an increase in contrast-enhancing disease on the baseline MRI study 4-6 weeks post-chemoradiotherapy. Studies had contrast-enhanced T1-weighted imaging (CE-T1WI), T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) sequences, acquired at 1.5 Tesla with 6-months follow-up to determine the reference standard outcome. 76 patients (mean age 55 years, range 18-76 years, 39% female, 46 tPD, 30 psPD) were included. Machine learning models utilised information from clinical characteristics (age, gender, resection extent, performance status), O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status and 307 quantitative imaging features; extracted from baseline study CE-T1WI/ADC and T2WI sequences using semi-automatically segmented enhancing disease and perilesional oedema masks respectively. Feature selection was performed within bootstrapped cross-validated recursive feature elimination with a random forest algorithm and Naïve Bayes five-fold cross-validation to validate the final model. Results Treatment response assessment based on the standard-of-care reports by clinical neuroradiologists showed an accuracy of 33% (sensitivity/specificity 52%/3%) to distinguish between tPD and psPD from the early post-treatment MRI study at 4-6 weeks. Machine learning-based models based on clinical and molecular features alone demonstrated an AUC of 0.66 and models using radiomic features alone from the early post-treatment MRI demonstrated an AUC of 0.46-0.69 depending on the feature and mask subset. A combined clinico-radiomic model utilising top common features demonstrated an AUC of 0.80 and an accuracy of 74% (sensitivity/specificity 78%/67%). The features in the final model were age, MGMT promoter methylation status, two shape-based features from the enhancing disease mask (elongation and sphericity), three radiomic features from the enhancing disease mask on ADC (kurtosis, correlation, contrast) and one radiomic feature from the perilesional oedema mask on T2WI (dependence entropy). Conclusion Current standard-of-care glioblastoma treatment response assessment imaging has limitations. In this study, the use of AI through a machine learning-based approach incorporating clinical characteristics and MGMT promoter methylation status with quantitative radiomic features from standard MRI sequences at early 4-6 weeks post-treatment imaging showed the best model performance and a higher accuracy to distinguish between tPD and psPD for early prediction of glioblastoma treatment response.

scholarly journals The importance of MGMT Promoter Methylation Status for Glioblastomas Prognosis: meta-analysis

2019 ◽  
Vol 29 (4) ◽  
pp. 595-611
Author(s):  
Marina Longo Machado de Almeida ◽  
Paulo Henrique Pires de Aguiar ◽  
Katharyna De Gois ◽  
Flavia De Sousa Gehrke ◽  
Fernando Fonseca
Keyword(s):  
Polymerase Chain Reaction ◽  
Promoter Methylation ◽  
Meta Analysis ◽  
Methylation Status ◽  
Mgmt Promoter Methylation ◽  
Chain Reaction ◽  
Promoter Methylation Status ◽  
Mgmt Promoter ◽  
Polymerase Chain ◽  
Mgmt Promoter Methylation Status

The authors discussed a meta-analysis on MGMT and glioblastomas and the positivity of methylation expression in patients with these tumors. The review included articles published between 2000 and 2018. As keywords we used: glioblastoma, MGMT or O-6- methylguanine DNA methyltransferase and methylation for the search. A meta-analysis was performed. The survey included only papers written in English, resulting in 34 articles in the review. In the articles, 16,426 glioblastoma samples were analyzed by means of pyrosequencing, methylation-specific polymerase chain reaction, immunohistochemistry or quantitative real time polymerase chain reaction (PCR) to determine the MGMT promoter methylation status. The authors found 2,414 tumor samples having the methylated promoter and 14,012 unmethylated. This article is very impressive, proving the real importance of MGMT methylation and its low positivity rate.

Elderly glioblastoma patients: Survival analysis according adjuvant therapy and tumor molecular analysis.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e14046-e14046
Author(s):  
Maria Angeles Vaz ◽  
Isaac Ceballos Lenza ◽  
Sonia Del Barco Berron ◽  
Maria Cruz Martin Soberón ◽  
Oscar Gallego Rubio ◽  
...  
Keyword(s):  
Survival Analysis ◽  
Adjuvant Therapy ◽  
Surgical Resection ◽  
Promoter Methylation ◽  
Systemic Treatment ◽  
Methylation Status ◽  
Mgmt Promoter Methylation ◽  
Mgmt Promoter ◽  
Mgmt Promoter Status ◽  
Mgmt Promoter Methylation Status

e14046 Background: Glioblastoma (GBM) grade IV represents the most frequent and aggressive primary brain tumor. Despite complete surgical resection, GBM infiltrative potential leads to local recurrence rates of around 100%. Standard treatment with adjuvant chemotherapy (CT) and radiotherapy (RT) according Stupp regimen aims to reduce relapse and improve survival, but toxicities associated with these therapies represent a problem in elderly unfit population. O6-Methylguanine-DNA methyltransferase (MGMT) promoter methylation status has been recognized as a predictive factor of response to alkylating agents as temozolomide. We aimed to compare overall survival (OS) results in elderly GBM patients according with MGMT promoter status and systemic treatment after surgery. Methods: We performed a database from the information available from RETSINE (Registro Nacional Español de Tumores de Sistema Nervioso Central). We selected ≥ 65 years GBM diagnosed patients. Relevant information was tumor MGMT promoter methylation status and adjuvant CT and/or RT after resection. Kaplan- Meier analysis was performed. Selected outcome was OS and 95% confidence intervals (CI) and p value < 0.05 were used as measures of statistical significance. Results: We identified 400 eligible GBM patients diagnosed ≥ 65 years (male = 232- 58%; female = 168-42% ). According tumor MGMT status: 125 (31.3%) methylated tumors, 115 (28.7%) non methylated and 160 unknown MGMT status. Included population median age was 72 years (65-88 years). Median global population OS was 7.93 months (IC95% 6.84-9.02). Survival analysis showed better OS for methylated tumors group, median OS 7.33 (IC 95%4.1-10.56) vs. unmethylated OS 7.06 (IC95% 4.9-9.1) (p = 0.021). Survival analysis in methylated patients showed improved OS in patients treated with RT + CT vs. no adjuvant therapy. Median OS for methylated patients treated with CT + RT was 11.46m (IC95%7.6-15.9) vs 9.6 months with only RT(IC95%3.67-7.26) and 2.1m with no treatment (IC95%2.03-3.76) p = 0,00. Unmethylated patients median OS was 9.36m (IC95%3.67-7.26) for RT-CT, 5.4 m (IC95%2.37-8.42) for RT only and 2.76 (IC95% 1.37-4.15) for no treatment p = 0.00. Conclusions: Elderly GBM patients have similar treatment options than young patients and comprise surgical resection, RT and alkylating CT with temozolomide. Comorbidities and performance status have relevant implications in elderly population treatment decisions. The MGMT promoter status has been described as a prognostic and predictive marker of response to temozolomide. In our series both methylated and unmethylated patients can benefit with systemic treatment.

scholarly journals NIMG-38. NON-INVASIVE PREDICTION OF MGMT PROMOTER METHYLATION USING COMBINED FET PET/MRI RADIOMICS

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii156-ii156
Author(s):  
Philipp Lohmann ◽  
Anna-Katharina Meissner ◽  
Jan-Michael Werner ◽  
Gabriele Stoffels ◽  
Martin Kocher ◽  
...  
Keyword(s):  
Promoter Methylation ◽  
Methylation Status ◽  
Mgmt Promoter Methylation ◽  
Test Dataset ◽  
Fet Pet ◽  
Promoter Methylation Status ◽  
Non Invasive ◽  
Mgmt Promoter ◽  
Amino Acid Pet ◽  
Mgmt Promoter Methylation Status

Abstract BACKGROUND Recently, the Response Assessment in Neuro-Oncology (RANO) Working Group emphasized the additional diagnostic value of amino acid PET in addition to MRI. However, the number of studies using amino acid PET/MRI radiomics is still low. We investigated the potential of combined O-(2-[18F]fluoroethyl)-L-tyrosine (FET) PET/MRI radiomics for the non-invasive prediction of the O6-methylguanine-DNA methyl-transferase (MGMT) promoter methylation status in glioma patients. METHODS Seventy-one patients with newly diagnosed glioma (predominantly WHO grade III and IV glioma, 82%) underwent a hybrid FET PET/MRI scan. Forty-six patients (65%) had a methylated MGMT promoter. The tumor and tumor subregions were manually segmented on conventional MRI. In total, 199 standardized features were obtained from FET PET, contrast-enhanced T1-weighted, T2-weighted, and fluid attenuated inversion recovery (FLAIR) MRI. After feature extraction and data normalization, patients were randomly assigned to a training and a test dataset for final model evaluation in a ratio of 70/30, with a balanced distribution of the MGMT promoter methylation status. Feature selection was performed by recursive feature elimination using random forest regressors. For the final model generation, the number of features was limited to seven to avoid data overfitting. Different algorithms for model generation were compared, and the model performance in the training data was assessed by 5-fold cross-validation. Finally, the best performing models were applied to the test dataset to evaluate the robustness of the models. RESULTS In the test dataset, the best radiomics signatures obtained from MRI or FET PET alone achieved diagnostic accuracies for the prediction of the MGMT promoter methylation of 64% and 70%, respectively. In contrast, the highest diagnostic accuracy of 83% was obtained by combining FET PET and MRI features. CONCLUSION Combined FET PET/MRI radiomics allows the non-invasive prediction of the MGMT promoter methylation status in patients with gliomas, providing more diagnostic information than either modality alone.

Sign in / Sign up

Export Citation Format

Share Document