Article
Individual prediction of response to radiosurgery for brain metastases – radiomics outperforms visual semantic features
Vorhersage des individuellen Ansprechens von Hirnmetastasen auf die Radiochirurgie: Radiomics übertrifft visuell-semantische Merkmale
Search Medline for
Authors
Published: | May 25, 2022 |
---|
Outline
Text
Objective: In brain metastases, hypoxic and necrotic tumor cells may prevent response to radiosurgery due to their reduced radiosensitivity and absence of reoxygenation during single dose irradiation. Tumors containing these resistant cells can potentially be identified from contrast-enhanced MR images both by human expert visual inspection or radiomics analysis. Therefore, we here determined the performance of MR-based radiomics features compared to visually assessed semantic features for their ability to predict early response to stereotactic radiosurgery in patients with brain metastases.
Methods: In a retrospective study, 150 patients with 308 brain metastases from solid tumors (NSCLC in 53% of patients) treated by stereotactic radiosurgery (single dose of 17-20 Gy) were evaluated. The response of each metastasis (partial or complete remission vs. stabilization or progression) was assessed within 180 days after radiosurgery. Patterns of contrast enhancement in the pre-treatment T1-weighted MR images were either visually classified (homogenous, heterogeneous, necrotic ring-like) or subjected to a radiomics analysis. Random forest models including radiomics features, semantic features, or both were optimized by cross-validation and evaluated in a hold-out test data set (30% of metastases).
Results: In total, 221/308 metastases (72%) responded to radiosurgery. The optimal radiomics model comprised 10 features and outperformed the model solely based on semantic features in the test data set (AUC, 0.71 vs. 0.56; accuracy, 69% vs. 54%). The diagnostic performance could be further improved by combining semantic and radiomics features resulting in an AUC of 0.74 and an accuracy of 75% in the test data set.
Conclusion: The developed radiomics model allowed prediction of early response to radiosurgery in patients with brain metastases and outperformed the visual assessment of patterns of contrast enhancement.