Radiomics outperforms semantic features for prediction of response to stereotactic radiosurgery in brain metastases.
Artificial intelligence (AI)
Brain tumor
MRI
Machine learning
Response assessment
Journal
Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
ISSN: 1879-0887
Titre abrégé: Radiother Oncol
Pays: Ireland
ID NLM: 8407192
Informations de publication
Date de publication:
01 2022
01 2022
Historique:
received:
25
08
2021
revised:
03
11
2021
accepted:
10
11
2021
pubmed:
22
11
2021
medline:
20
4
2022
entrez:
21
11
2021
Statut:
ppublish
Résumé
Brain metastases show different patterns of contrast enhancement, potentially reflecting hypoxic and necrotic tumor regions with reduced radiosensitivity. An objective evaluation of these patterns might allow a prediction of response to radiotherapy. We therefore investigated the potential of MRI radiomics in comparison with the visual assessment of semantic features to predict early response to stereotactic radiosurgery in patients with brain metastases. In this 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 were optimized by cross-validation and evaluated in a hold-out test data set (30% of metastases). 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. 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.
Sections du résumé
BACKGROUND
Brain metastases show different patterns of contrast enhancement, potentially reflecting hypoxic and necrotic tumor regions with reduced radiosensitivity. An objective evaluation of these patterns might allow a prediction of response to radiotherapy. We therefore investigated the potential of MRI radiomics in comparison with the visual assessment of semantic features to predict early response to stereotactic radiosurgery in patients with brain metastases.
PATIENTS AND METHODS
In this 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 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.
Identifiants
pubmed: 34801629
pii: S0167-8140(21)08998-2
doi: 10.1016/j.radonc.2021.11.010
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
37-43Informations de copyright
Copyright © 2021 Elsevier B.V. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest None.