Related Experiment Video
Updated: Jun 16, 2025
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
Baseline Radiomics as a Prognostic Tool for Clinical Benefit from Immune Checkpoint Inhibition in Inoperable NSCLC
Fedor Moiseenko1,2, Marko Radulovic3, Nadezhda Tsvetkova1
1N.P Napalkov Saint Petersburg Clinical Research and Practical Centre for Specialized Types of Medical Care (Oncological), Leningradskaya Str. 68A, 197758 Saint Petersburg, Russia.
Abstract:
Background/Objectives: Checkpoint inhibitors (ICIs) are key therapies for NSCLC, but current selection criteria, such as excluding mutation carriers and assessing PD-L1, lack sensitivity. As a result, many patients receive costly treatments with limited benefit. Therefore, this study aimed to predict which NSCLC patients would achieve durable survival (≥24 months) with immunotherapy. Methods: A comprehensive ensemble radiomics approach was applied to pretreatment CT scans to prognosticate overall survival (OS) and predict progression-free survival (PFS) in a cohort of 220 consecutive patients with inoperable NSCLC treated with first-line ICIs (pembrolizumab or atezolizumab, nivolumab or prolgolimab) as monotherapy or in combination. The radiomics pipeline evaluated four normalization methods (none, min-max, Z-score, mean), four feature selection techniques (ANOVA, RFE, Kruskal-Wallis, Relief), and ten classifiers (e.g., SVM, random forest). Using two to eight radiomics features, 1680 models were built in the Feature Explorer (FAE) Python package. Results: Three feature sets were evaluated: clinicopathological (CP) only, radiomics only, and a combined set, using 6- and 12-month PFS and 24-month OS endpoints. The top 15 models were ensembled by averaging their probability scores. The best performance was achieved at 24-month OS with the combined CP and radiomics ensemble (AUC = 0.863, accuracy = 85%), followed by radiomics-only (AUC = 0.796, accuracy = 82%) and CP-only (AUC = 0.671, accuracy = 76%). Predictive performance was lower for 6-month (AUC = 0.719) and 12-month PFS (AUC = 0.739) endpoints. Conclusions: Our radiomics pipeline improved selection of NSCLC patients for immunotherapy and could spare non-responders unnecessary toxicity while enhancing cost-effectiveness.
Insights
This study developed a radiomics approach to predict durable survival in non-small cell lung cancer (NSCLC) patients receiving immunotherapy. The method accurately identifies patients likely to benefit, improving treatment selection and reducing costs.
Area of Science:
- Radiology
- Oncology
- Artificial Intelligence
Background:
- Checkpoint inhibitors (ICIs) are vital for non-small cell lung cancer (NSCLC) but current selection methods are insensitive.
- Many NSCLC patients incur costs from ineffective immunotherapy treatments.
Purpose of the Study:
- To predict durable survival (≥24 months) in NSCLC patients undergoing immunotherapy.
- To enhance patient selection for immunotherapy and improve treatment outcomes.
Main Methods:
- A comprehensive ensemble radiomics approach was applied to pretreatment CT scans of 220 NSCLC patients.
- 1680 models were built using various normalization, feature selection, and classification techniques.
- Clinicopathological (CP) and radiomics features were evaluated for predicting overall survival (OS) and progression-free survival (PFS).
Main Results:
- The combined CP and radiomics ensemble model achieved the highest accuracy (85%) for predicting 24-month OS (AUC = 0.863).
- Radiomics-only models showed strong performance (82% accuracy, AUC = 0.796) for 24-month OS.
- Predictive performance for shorter PFS endpoints was lower.
Conclusions:
- The developed radiomics pipeline significantly improves patient selection for NSCLC immunotherapy.
- This approach can help avoid unnecessary toxicity and costs for non-responders.
- Radiomics offers a promising tool for personalized NSCLC treatment strategies.
