MRI Radiomic Features to Predict IDH1 Mutation Status in Gliomas: A Machine Learning Approach using Gradient Tree Boosting

Sakai, Yu; Yang, Chen; Kihira, Shingo; Tsankova, Nadejda M.; Khan, Fahad; Hormigo, Adı́lia; Lai, Albert; Cloughesy, Timothy F.; Nael, Kambiz

doi:10.3390/ijms21218004

Cited by 31 publications

(21 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IDH1 Arg132His (R132H) mutation can affect the proliferation of glioma cells, which is slower than the corresponding wild-type IDH1 cells ( 8 , 9 ). Clinical studies ( 10 , 11 ) have shown that mutations in IDH1 were found to be associated with younger age, secondary GBMs (grade IV tumors that arise from biopsy-proven lower-grade predecessors), and increased overall survival (OS) ( 12 ). Further studies ( 13 , 14 ) have revealed that IDH1/2 mutations as good prognostic markers are universally present in grade II and III glioma and secondary glioblastoma, and serve an important role in the occurrence, development and evolution of glioma ( 15 ).…”

Section: Introductionmentioning

confidence: 99%

IDH1 gene mutation activates Smad signaling molecules to regulate the expression levels of cell cycle and biological rhythm genes in human glioma U87‑MG cells

Gao

Zhang

et al. 2021

Mol Med Rep

View full text Add to dashboard Cite

Isocitrate dehydrogenase1 (IDH1) mutation is the most important genetic change in glioma. The most common IDH1 mutation results in the amino acid substitution of arginine 132 (Arg/R132), which is located at the active site of the enzyme. IDH1 Arg132His (R132H) mutation can reduce the proliferative rate of glioma cells. Numerous diseases follow circadian rhythms, and there is growing evidence that circadian disruption may be a risk factor for cancer in humans. Dysregulation of the circadian clock serves an important role in the development of malignant tumors, including glioma. Brain-Muscle Arnt-Like protein 1 (BMAL1) and Circadian Locomotor Output Cycles Kaput (CLOCK) are the main biological rhythm genes. The present study aimed to further study whether there is an association between IDH1 R132H mutation and biological rhythm in glioma, and whether this affects the occurrence of glioma. The Cancer Genome Atlas (TCGA) database was used to detect the expression levels of the biological rhythm genes BMAL1 and CLOCK in various types of tumor. Additionally, U87-MG cells were infected with wild-type and mutant IDH1 lentiviruses. Colony formation experiments were used to detect cell proliferation in each group, cell cycle distribution was detected by flow cytometry and western blotting was used to detect the expression levels of wild-type and mutant IDH1, cyclins, biological rhythm genes and Smad signaling pathway-associated genes in U87-MG cells. TCGA database results suggested that BMAL1 and CLOCK were abnormally expressed in glioma. Cells were successfully infected with wild-type and mutant IDH1 lentiviruses. Colony formation assay revealed decreased cell proliferation in the IDH1 R132H mutant group. The cell cycle distribution detected by flow cytometry indicated that IDH1 gene mutation increased the G 1 phase ratio and decreased the S phase ratio in U87-MG cells. The western blotting results demonstrated that IDH1 R132H mutation decreased the expression levels of the S phase-associated proteins Cyclin A and CDK2, and increased the expression levels of the G 1 phase-associated proteins Cyclin D3 and CDK4, but did not significantly change the expression levels of the G 2 /M phase-associated protein Cyclin B1. The expression levels of the positive and negative rhythm regulation genes BMAL1, CLOCK, period (PER s (PER1, 2 and 3) and cryptochrom (CRY)s (CRY1 and 2) were significantly decreased, those of the Smad signaling pathway-associated genes Smad2, Smad3 and Smad2-3 were decreased, and those of phosphorylated (p)-Smad2, p-Smad3 and Smad4 were increased. Therefore, the present results suggested that the IDH1 R132H mutation may alter the cell cycle and biological rhythm genes in U87-MG cells through the TGF-β/Smad signaling pathway.

show abstract

Section: Introductionmentioning

confidence: 99%

IDH1 gene mutation activates Smad signaling molecules to regulate the expression levels of cell cycle and biological rhythm genes in human glioma U87‑MG cells

Gao

Zhang

et al. 2021

Mol Med Rep

View full text Add to dashboard Cite

show abstract

“…Compared with the other four algorithms (support vector machine, random forest, naive Bayes, and logistic regression algorithms), this model showed the highest accuracy in ovarian cancer diagnosis [29]. As for gliomas, it improved the classi cation of MGMT promoter methylation status in IDH1 wildtype GBM [30], e ciently classi ed transcriptome subtypes in GBM patients from MRI [31], and predicted IDH1 mutation status in gliomas [32]. In our study, this method classi ed different VEGF expression statuses in GBM with good results.…”

Section: Discussionmentioning

confidence: 98%

Radiogenomic Analysis of Vascular Endothelial Growth Factor in Patients With Glioblastoma

Chen

Zheng

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Purpose Vascular endothelial growth factor (VEGF) is very important for glioblastoma (GBM) angiogenesis. This study is to predict VEGF expression in cerebral GBM by radiomic analysis.Methods We analysed the axial T2WI and T1-weighted contrast-enhancement (T1CE) images of preoperative MRI in 217 patients with pathologically diagnosed GBM. Patients were divided into negative and positive VEGF groups, with the latter group further subdivided into low and high expression and analysed by the machine learning model built by the maximum relevance and minimum redundancy (mRMR) algorithm and the extreme gradient boosting (XGBoost) classifier. The area under the receiver operating curve (AUC) and accuracy were calculated for the training and validation sets. Results Positive VEGF in GBM was 63.1% (137/217), with a high expression ratio of 53.3% (73/137). To predict the positive and negative VEGF expression, seven radiomic features were selected with three features from T1CE and four from T2WI. The accuracy and AUC were 0.83 and 0.81, respectively, in the training set, and were 0.73 and 0.74, respectively, in the validation set. To predict high and low levels, seven radiomic features were selected, with two from T1CE, one from T2WI, and four from the data combinations of T1CE and T2WI. The accuracy and AUC were 0.88 and 0.88, respectively, in the training set, and 0.72, and 0.72, respectively, in the validation set. Conclusion The VEGF expression status in GBM can be predicted using a machine learning model. Radiomic features resulting from data combinations of different MRI sequences could be helpful for analysis.

show abstract

“…The XGBoost algorithm is based on gradient boosting decisionmaking, has low data requirements, fast training speed, and accurate training results. It has been widely used in artificial intelligence and the data analysis fields, and has been increasingly used in clinical research (9,10). This study retrospectively analyzed patients who received surgical treatment for glioma for the first time.…”

Section: Introductionmentioning

confidence: 99%

XGBoost algorithm and logistic regression to predict the postoperative 5-year outcome in patients with glioma

Yan¹,

Wang²,

Dong³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background: Glioma is the most common primary intracranial tumor with poor prognosis. The prediction of glioma prognosis has not been well investigated. XGBoost algorithm has been widely used in and data analysis. The predictive value of XGBoost algorithm in glioma remains unclear. This current study used the XGBoost algorithm to construct a predictive model for postoperative outcomes of glioma patients.Methods: Patients with glioma who underwent surgery from January 2006 to April 2017 were retrospectively included in this study. Clinical and follow-up data were collected. The XGBoost model and multivariate logistic regression analysis model were used to screen the factors related to postoperative outcomes, and the results of the two models were compared. The area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, and Youden index were calculated to evaluate the predictive value of the XGBoost model.Results: A total of 638 patients were included. In total, 336 (52.7%) cases died within 5 years after the operation. Multivariate logistic regression analysis showed that age, gender, World Health Organization (WHO) grade, extent of tumor resection, Karnofsy performance score (KPS), tumor diameter, and whether postoperative radiotherapy and chemotherapy were administered, were the most important risk factors for death within 5 years after surgery in glioma patients. The XGBoost model showed that the top 5 factors related to death of glioma patients within 5 years after surgery were WHO grade (30 points), extent of tumor resection (19 points), postoperative radiotherapy and chemotherapy (16 points), KPS (14 points), and age (11 points). The AUC of the XGBoost model for predicting the death of glioma patients within 5 years after surgery was 0.803 [95% confidence interval (CI): 0.718-0.832], and the sensitivity and specificity were 0.894 and 0.581, respectively. The Youden index was 0.475. The AUC of the multivariate logistic regression model was 0.738 (95% CI: 0.704-0.781), the sensitivity and specificity were 0.785 and 0.632, respectively, and the Youden index was 0.417. Conclusions:Compared with multivariate logistic regression model, XGBoost model has better performance in predicting the risk of death within 5 years after surgery in patients with glioma.

show abstract

MRI Radiomic Features to Predict IDH1 Mutation Status in Gliomas: A Machine Learning Approach using Gradient Tree Boosting

Cited by 31 publications

References 47 publications

IDH1 gene mutation activates Smad signaling molecules to regulate the expression levels of cell cycle and biological rhythm genes in human glioma U87‑MG cells

IDH1 gene mutation activates Smad signaling molecules to regulate the expression levels of cell cycle and biological rhythm genes in human glioma U87‑MG cells

Radiogenomic Analysis of Vascular Endothelial Growth Factor in Patients With Glioblastoma

XGBoost algorithm and logistic regression to predict the postoperative 5-year outcome in patients with glioma

Contact Info

Product

Resources

About