Differentiation of Pseudoprogression from True Progressionin Glioblastoma Patients after Standard Treatment: A Machine Learning Strategy Combinedwith Radiomics Features from T1-weighted Contrast-enhanced Imaging

Abstract

Background Based on conventional MRI images, it is difficult to differentiatepseudoprogression from true progressionin GBM patients after standard treatment, which isa critical issue associated with survival. The aim of this study was to evaluate the diagnostic performance of machine learning using radiomics modelfrom T1-weighted contrast enhanced imaging(T1CE) in differentiating pseudoprogression from true progression after standard treatment for GBM. Methods Seventy-sevenGBM patients, including 51 with true progression and 26 with pseudoprogression,who underwent standard treatment and T1CE, were retrospectively enrolled.Clinical information, including sex, age, KPS score, resection extent, neurological deficit and mean radiation dose, were also recorded collected for each patient. The whole tumor enhancementwas manually drawn on the T1CE image, and a total of texture 9675 features were extracted and fed to a two-step feature selection scheme. A random forest (RF) classifier was trained to separate the patients by their outcomes.The diagnostic efficacies of the radiomics modeland radiologist assessment were further compared by using theaccuracy (ACC), sensitivity and specificity. Results No clinical features showed statistically significant differences between true progression and pseudoprogression.The radiomic classifier demonstrated ACC, sensitivity, and specificity of 72.78%(95% confidence interval [CI]: 0.45,0.91), 78.36%(95%CI: 0.56,1.00) and 61.33%(95%CI: 0.20,0.82).The accuracy, sensitivity and specificity of three radiologists’ assessment were66.23%(95% CI: 0.55,0.76), 61.50%(95% CI: 0.43,0.78) and 68.62%(95% CI: 0.55,0.80); 55.84%(95% CI: 0.45,0.66),69.25%(95% CI: 0.50,0.84) and 49.13%(95% CI: 0.36,0.62); 55.84%(95% CI: 0.45,0.66), 69.23%(95% CI: 0.50,0.84) and 47.06%(95% CI: 0.34,0.61), respectively. Conclusion T1CE–based radiomics showed better classification performance compared with radiologists’ assessment.The radiomics modelwas promising in differentiating pseudoprogression from true progression.

Longitudinal structural and perfusion MRI enhanced by machine learning outperforms standalone modalities and radiological expertise in high-grade glioma surveillance

“…Another important finding with potential clinical implication is that the SVM outperformed radiologists’ classification performance up to 27% in terms of classification accuracy, more profoundly in the multiple time point group. A similar observation is described in a recent study employing radiomic features derived from structural MRI [ 45 ]. However, any generalisation of such comparisons would require confirmation by studies based on larger patient cohorts, prospective design and use of external validation.…”

“…Indeed, the bestperforming features included differences in rCBV, rCBF, T2 kurtosis and subtracted signal intensity on post-contrast T1 sequences on longitudinal MRI studies. Similar features have been identified by previous studies as promising for the differentiation of PsP from PD [44][45][46][47]. Employing machine learning, Akbari et al further demonstrated a correlation between such features, namely enhancement on post-contrast T1 and rCBV, with histologically validated tissue characteristics related to PsP and PD [48].…”

5-Aminolevulinic Acid False-Positive Rates in Newly Diagnosed and Recurrent Glioblastoma: Do Pseudoprogression and Radionecrosis Play a Role? A Meta-Analysis

“…PP is defined as peritumoral inflammatory tissue that may be erroneously reported as tumor progression or recurrence on MRI images ( 18 ). The PP phenomenon is well documented, and its MRI aspect is justified by its histological findings, consisting of inflammation, neutrophil and macrophage infiltration, reactive astrocytes, high mitotic rate, and neoangiogenesis ( 19 ).…”

Robustness of radiomic features in magnetic resonance imaging for patients with glioblastoma: Multi-center study

“…Numerous studies have shown that these characteristics known as radiomic features have the potential to decode tumor phenotypes and predict treatment outcome [4] . Magnetic resonance imaging (MRI)-based radiomics have already demonstrated their promising abilities to predict disease progression [5] , [6] , methylation status [7] , tumor grade [8] and overall survival [9] , [10] for patients with central nervous system malignancies. Magnetic resonance (MR) images are routinely acquired for patients with GBM at baseline and for follow-up.…”