Predicting early response to ablative radiotherapy in oligometastatic disease: a scoping review of radiomics-based machine learning and deep learning models - Summary - MDSpire
Advertisement
Predicting early response to ablative radiotherapy in oligometastatic disease: a scoping review of radiomics-based machine learning and deep learning models
To systematically assess the predictive performance of ML and DL models using radiomic data for evaluating early treatment response in metastatic lesions of oligometastatic disease (OMD) patients treated with ART and to evaluate methodological quality.
Key Findings:
ART failure rates can reach up to 30-40% in metastatic lesions, highlighting the need for effective predictive models.
Radiomics and AI techniques show promise in predicting treatment outcomes, which could guide personalized treatment strategies.
Most studies are single-center and methodologically heterogeneous, limiting generalizability and applicability in diverse clinical settings.
Interpretation:
The integration of radiomics and machine learning offers potential for improving early treatment response predictions in oligometastatic cancer, but further standardization and multi-center studies are needed to enhance clinical applicability.
Limitations:
Heterogeneity in study methodologies and data sources.
Limited generalizability due to single-center studies.
Potential biases in reporting and data extraction that may affect study outcomes.
Conclusion:
This review highlights the potential of radiomics and machine learning in enhancing treatment response predictions in oligometastatic cancer, emphasizing the need for improved methodological rigor and multi-center validation.
by Raquel García-Pablo, Marta Canela-Capdevila, Alberto Martínez-Caballero, Rocío Benavides-Villareal, Albert Moragas-Fernández, Andrea Jiménez-Franco, Berta Piqué-Smith, Camila Montesinos-Guevara, Jordi Camps, Jorge Joven, Angel Torrado-Carvajal, Meritxell Arenas
