Mode
Text Size
Log in / Sign up

Radiomics models predict progression in lung oligometastases after SABR in phase II trialRadiomics models show promise for predicting outcomes after lung metastasis radiation

AI-generated summary of the cited source, checked by automated accuracy review. How we work

Key Takeaway
Consider radiomics models for lung oligometastases as investigational tools requiring validation.

In a population-based, single-arm phase II trial (SABR-5), researchers analyzed 126 patients with lung oligometastases treated with stereotactic ablative radiotherapy (SABR). The study aimed to develop radiomics models to predict progression-free survival and early polymetastatic progression, defined as progression within 6.0 months. No comparator treatment was evaluated.

For predicting progression-free survival, radiomics-only and combined models achieved a concordance index of 0.72 in the test set, compared to 0.52 for the clinical-only model. The radiomics model significantly stratified patients into high- and low-risk groups in both training (P < 0.001) and test sets (P = 0.041). For predicting early polymetastatic progression, the radiomics-only model achieved an area under the curve of 0.85 across cross-validation folds, with a true-positive rate of 0.73 and true-negative rate of 0.78. The clinical-only model performed poorly, with an AUC of 0.47.

Safety and tolerability data for SABR were not reported. The study has several key limitations: it is a predictive modeling analysis from a single-arm trial, demonstrating association rather than causation. The models require external validation, and their clinical utility for improving patient selection or outcomes was not tested. The funding source and potential conflicts of interest were not reported.

Practice relevance is restrained. The findings suggest radiomics models could potentially assist with patient selection and treatment strategies for pulmonary oligometastases, but they are not ready for clinical use. The study does not compare SABR to alternative treatments, and using these models to guide therapy remains hypothetical without prospective validation.

Researchers studied whether computer analysis of medical scans could help predict outcomes for patients with a small number of lung metastases. They looked at 126 patients from a trial who received stereotactic ablative radiotherapy (SABR), a precise form of radiation. The team developed 'radiomics' models that analyze patterns in CT scans that the human eye can't easily see.

The study found these imaging-based models were better at predicting progression-free survival and early widespread progression than models using only basic clinical information. For example, one model successfully separated patients into higher and lower risk groups. The models showed good accuracy in identifying patients at risk of their cancer spreading more widely within six months.

This research is from a phase II trial, which is an early stage of testing. The study did not compare SABR to other treatments, and the models were not tested in actual clinical decision-making. The main reason for caution is that these promising results come from one group of patients and need to be confirmed in different settings before doctors could use them to guide care. Readers should understand this is a step toward better prediction tools, not a ready-to-use test.

What this means for you:
Early study shows imaging analysis may help predict cancer progression, but models need more validation.

Study Details

Study typePhase2
Sample sizen = 134
EvidenceLevel 3
Follow-up6.0 mo
PublishedApr 2026
View Original Abstract ↓
AIMS: Despite the increasing use of stereotactic ablative radiotherapy (SABR) for oligometastatic cancer, at present, accurate models to predict the time until disease progression are lacking. The study developed radiomics models to predict progression-free survival (PFS) and early polymetastatic progression (PMP) in order to improve upon basic clinical prognostic models in lung oligometastatic patients treated in the population-based single-arm SABR-5 trial. MATERIALS AND METHODS: Among 134 patients treated for lung oligometastases in the SABR-5 trial, pretreatment computed tomography images were available for 126 patients for inclusion in this study. In total, 1116 radiomic features were extracted from the original, wavelet-filtered, and Laplacian of Gaussian (LoG)-filtered images using PyRadiomics. Analyses were developed to predict (1) PFS and (2) early PMP, defined as progression of more than 5 lesions within 6 months of SABR. Clinical-only (ECOG score, primary tumour type, oligoprogression, and gross tumour volume [GTV]), radiomics-only, and combined models were developed. Feature selection was performed using the Pearson correlation coefficient. Cox proportional hazards regression was used to predict PFS and stratify patients into high- and low-risk groups. For the early PMP model, a support vector machine was evaluated using 10-, 5-, and 3-fold cross-validation. RESULTS: The radiomics-only and combined models achieved a concordance index of 0.72 in the test set, versus 0.52 for the clinical-only model. The radiomics model stratified patients into high- and low-risk groups in both the training and test sets (P < 0.001 and 0.041, respectively). In the early PMP model, area under the receiver operating characteristic curve (AUC), true-positive rate, and true-negative rate across all folds (10, 5, and 3) were 0.85, 0.73, and 0.78 for the radiomics-only model and 0.47, 0.45, and 0.62 for the clinical-only model, respectively. CONCLUSION: Radiomics models outperformed clinical models for predicting PFS and early PMP. These radiomics models could potentially assist with optimal patient selection and treatment strategies for patients with pulmonary oligometastases.
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.