Development and validation of a MRI-radiomics-based machine learning approach in High Grade Glioma to detect early recurrence

被引：0

作者：

Pignotti, Fabrizio ^{[1
,2
]}

Ius, Tamara ^{[3
]}

Russo, Rosellina ^{[4
]}

Bagatto, Daniele ^{[5
]}

Bartoli, Francesco Beghella ^{[6
]}

Boccia, Edda ^{[6
]}

Boldrini, Luca ^{[6
]}

Chiesa, Silvia ^{[6
]}

Ciardi, Chiara ^{[5
]}

Cusumano, Davide ^{[7
]}

Giordano, Carolina ^{[4
]}

La Rocca, Giuseppe ^{[8
]}

Mazzarella, Ciro ^{[6
]}

Mazzucchi, Edoardo ^{[1
,2
]}

Olivi, Alessandro ^{[2
,8
]}

Skrap, Miran ^{[3
]}

Tran, Houng Elena ^{[6
]}

Varcasia, Giuseppe ^{[4
]}

Gaudino, Simona ^{[2
,4
]}

Sabatino, Giovanni ^{[1
,2
,8
]}

机构：

[1] Mater Olbia Hosp, Dept Neurosurg, Olbia, Italy

[2] Catholic Univ, Inst Neurosurg, Fdn Policlin Univ A Gemelli IRCCS, Rome, Italy

[3] Univ Hosp Udine, Head Neck & NeuroSci Dept, Neurosurg Unit, Udine, Italy

[4] Fdn Policlin Univ Agostino Gemelli IRCS, Adv Radiodiagnost Ctr, Unita Operat Semplice Dipartimentale UOSD Neuradi, Rome, Italy

[5] Azienda Sanit Univ Friuli Cent ASUFC Santa Maria, Dept Neuroradiol, Udine, Italy

[6] Fdn Policlin Univ Agostino Gemelli IRCSS, Dept Radiol Radiat Oncol & Hematol, Rome, Italy

[7] Mater Olbia Hosp, Med Phys Unit, Olbia, Italy

[8] Fdn Policlin Univ Agostino Gemelli IRCSS, Inst Neurosurg, Rome, Italy

来源：

FRONTIERS IN ONCOLOGY | 2024年 / 14卷

关键词：

machine learning; recurrence; high grade glioma; radiomics; prognosis; GLIOBLASTOMA-MULTIFORME; RESECTION; FLUORESCENCE; EXTENT; SURVIVAL; NEUROONCOLOGY; HARMONIZATION; PREDICTION; PROGNOSIS; SURGERY;

D O I：

10.3389/fonc.2024.1449235

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Purpose: Patients diagnosed with High Grade Gliomas (HGG) generally tend to have a relatively negative prognosis with a high risk of early tumor recurrence (TR) after post-operative radio-chemotherapy. The assessment of the pre-operative risk of early versus delayed TR can be crucial to develop a personalized surgical approach. The purpose of this article is to predict TR using MRI radiomic analysis. Methods: Data were retrospectively collected from a database. A total of 248 patients were included based on the availability of 6-month TR results: 188 were used to train the model, the others to externally validate it. After manual segmentation of the tumor, Radiomic features were extracted and different machine learning models were implemented considering a combination of T1 and T2 weighted MR sequences. Receiver Operating Characteristic (ROC) curve was calculated with relative model performance metrics (accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV)) at the best threshold based on the Youden Index. Results: Models performance were evaluated based on test set results. The best model resulted to be the XGBoost, with an area under ROC curve of 0.72 (95% CI: 0.56 - 0.87). At the best threshold, the model exhibits 0.75 (95% CI: 0.63 - 0.75) as accuracy, 0.62 (95% CI: 0.38 - 0.83) as sensitivity 0.80 (95% CI: 0.66 - 0.89 as specificity, 0.53 (95% CI: 0.31 - 0.73) as PPV, 0.88 (95% CI: 0.72 - 0.94) as NPV. Conclusion: MRI radiomic analysis represents a powerful tool to predict late HGG recurrence, which can be useful to plan personalized surgical treatments and to offer pertinent patient pre-operative counseling.

引用

页数：11