Differentiating true progression from pseudoprogression in glioblastomas: Dynamic contrast-enhanced MRI habitat analysis with parsimonious pharmacokinetic model
Abstract
Background: Distinguishing true progression (TP) from pseudoprogression (PsP) in glioblastoma (GBM) remains a clinical challenge as both often manifest as indeterminate contrast-enhancing lesions on post-treatment MRIs. However, integrating dynamic contrast-enhanced (DCE)-MRI with analytical methods such as clustering and machine learning offers a promising approach for distinguishing TP from PsP.
Methods: Quantitative analysis of DCE-MRI data from 82 patients with TP (n = 53) and PsP (n = 29) was performed using 5 pharmacokinetic models. Subsequently, a parsimonious selection method was used to identify the best fit for each voxel. In the next step, clustering analysis using K-means++ was performed to classify pixels into low-, medium-, and high-intensity regions. Tumors were segmented into enhancing, non-enhancing, and edema regions using automated nnU-Net algorithm, and clusters were extracted from these regions. Significant features derived from clustering analysis and descriptive statistics (mean, median, and skewness) of DCE-MRI parameters and tumor volume were incorporated as input variables for classifier development. Finally, 5 machine learning classifiers were employed to differentiate between TP and PsP.
Results: Univariable clustering analysis of DCE-MRI data identified Ktrans, Ve, Vp, τi, and tumor volumes as significant parameters for distinguishing TP from PsP. Multivariable clustering revealed that combined high-Ktrans-high-Ve is a key distinctive variable. Among machine learning classifiers tested using these parameters, Random Forest demonstrated the best diagnostic performance, achieving an accuracy of 83% and an AUC of 0.85.
Conclusion: Parsimonious analysis of DCE-MRI data in conjunction with clustering and machine learning could serve as a valuable method for accurately distinguishing TP from PsP in GBMs.
Related
- Quantitative Pharmacokinetic Analysis of Dynamic Contrast-Enhanced Perfusion in Multiparametric Prostate MRI: An Exploratory Intra-Patient Study Differentiating Malignant Lesions from Normal Tissue
- Qualitative Dynamic Contrast-Enhanced MRI Time–Intensity Curve Analysis for Differentiating Non-Progressive Treatment-Related Changes from Tumor Progression After Stereotactic Radiotherapy for Brain Metastases
- Diagnostic Accuracy of Amino Acid PET for Differentiating Tumor Recurrence or Progression from Treatment-Related Changes in Glioma Patients: A Systematic Review and Meta-Analysis.
- Explaining and predicting pseudoprogression in immunotherapythrough joint modeling of immune infiltration and ctDNA dynamics
- Development and Validation of a Parsimonious Financial Well-Being Index in the Health and Retirement Study
BibTeX
@article{basak2026differentiating,
title = {{Differentiating true progression from pseudoprogression in glioblastomas: Dynamic contrast-enhanced MRI habitat analysis with parsimonious pharmacokinetic model}},
author = {Sourav Basak and Subhanon Bera and Sankar Narayan Misra and Archith Rajan and Harish Poptani and Sanjeev Chawla and Sourav Bhaduri},
journal = {Neuro-Oncology Advances},
year = {2026},
month = oct,
doi = {10.1093/noajnl/vdag254},
url = {https://doi.org/10.1093/noajnl/vdag254},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Differentiating true progression from pseudoprogression in glioblastomas: Dynamic contrast-enhanced MRI habitat analysis with parsimonious pharmacokinetic model
AU - Sourav Basak
AU - Subhanon Bera
AU - Sankar Narayan Misra
AU - Archith Rajan
AU - Harish Poptani
AU - Sanjeev Chawla
AU - Sourav Bhaduri
PY - 2026
DA - 2026/10/29
JO - Neuro-Oncology Advances
DO - 10.1093/noajnl/vdag254
UR - https://doi.org/10.1093/noajnl/vdag254
AB - Background: Distinguishing true progression (TP) from pseudoprogression (PsP) in glioblastoma (GBM) remains a clinical challenge as both often manifest as indeterminate contrast-enhancing lesions on post-treatment MRIs. However, integrating dynamic contrast-enhanced (DCE)-MRI with analytical methods such as clustering and machine learning offers a promising approach for distinguishing TP from PsP. Methods: Quantitative analysis of DCE-MRI data from 82 patients with TP (n = 53) and PsP (n = 29) was performed using 5 pharmacokinetic models. Subsequently, a parsimonious selection method was used to identify the best fit for each voxel. In the next step, clustering analysis using K-means++ was performed to classify pixels into low-, medium-, and high-intensity regions. Tumors were segmented into enhancing, non-enhancing, and edema regions using automated nnU-Net algorithm, and clusters were extracted from these regions. Significant features derived from clustering analysis and descriptive statistics (mean, median, and skewness) of DCE-MRI parameters and tumor volume were incorporated as input variables for classifier development. Finally, 5 machine learning classifiers were employed to differentiate between TP and PsP. Results: Univariable clustering analysis of DCE-MRI data identified Ktrans, Ve, Vp, τi, and tumor volumes as significant parameters for distinguishing TP from PsP. Multivariable clustering revealed that combined high-Ktrans-high-Ve is a key distinctive variable. Among machine learning classifiers tested using these parameters, Random Forest demonstrated the best diagnostic performance, achieving an accuracy of 83% and an AUC of 0.85. Conclusion: Parsimonious analysis of DCE-MRI data in conjunction with clustering and machine learning could serve as a valuable method for accurately distinguishing TP from PsP in GBMs.
SN - 2632-2498
ER -