Limited capability of MRI radiomics to predict primary tumor histology of brain metastases in external validation.

Autor:	Strotzer QD; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany.; Division of Neuroradiology, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA., Wagner T; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Angstwurm P; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Hense K; Department of Neurosurgery, University Medical Center Regensburg, Regensburg, Germany., Scheuermeyer L; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Noeva E; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Dinkel J; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Stroszczynski C; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Fellner C; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany., Riemenschneider MJ; Department of Neuropathology, University Medical Center Regensburg, Regensburg, Germany., Rosengarth K; Department of Neurosurgery, University Medical Center Regensburg, Regensburg, Germany., Pukrop T; Department of Internal Medicine III-Hematology and Oncology, University Medical Center Regensburg, Regensburg, Germany., Wiesinger I; Center of Neuroradiology, medbo District Hospital and University Medical Center Regensburg, Regensburg, Germany., Wendl C; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany.; Center of Neuroradiology, medbo District Hospital and University Medical Center Regensburg, Regensburg, Germany., Schicho A; Department of Radiology, University Medical Center Regensburg, Regensburg, Germany.
Jazyk:	angličtina
Zdroj:	Neuro-oncology advances [Neurooncol Adv] 2024 Apr 20; Vol. 6 (1), pp. vdae060. Date of Electronic Publication: 2024 Apr 20 (Print Publication: 2024).
DOI:	10.1093/noajnl/vdae060
Abstrakt:	Background: Growing research demonstrates the ability to predict histology or genetic information of various malignancies using radiomic features extracted from imaging data. This study aimed to investigate MRI-based radiomics in predicting the primary tumor of brain metastases through internal and external validation, using oversampling techniques to address the class imbalance. Methods: This IRB-approved retrospective multicenter study included brain metastases from lung cancer, melanoma, breast cancer, colorectal cancer, and a combined heterogenous group of other primary entities (5-class classification). Local data were acquired between 2003 and 2021 from 231 patients (545 metastases). External validation was performed with 82 patients (280 metastases) and 258 patients (809 metastases) from the publicly available Stanford BrainMetShare and the University of California San Francisco Brain Metastases Stereotactic Radiosurgery datasets, respectively. Preprocessing included brain extraction, bias correction, coregistration, intensity normalization, and semi-manual binary tumor segmentation. Two-thousand five hundred and twenty-eight radiomic features were extracted from T1w (± contrast), fluid-attenuated inversion recovery (FLAIR), and wavelet transforms for each sequence (8 decompositions). Random forest classifiers were trained with selected features on original and oversampled data (5-fold cross-validation) and evaluated on internal/external holdout test sets using accuracy, precision, recall, F1 score, and area under the receiver-operating characteristic curve (AUC). Results: Oversampling did not improve the overall unsatisfactory performance on the internal and external test sets. Incorrect data partitioning (oversampling before train/validation/test split) leads to a massive overestimation of model performance. Conclusions: Radiomics models' capability to predict histologic or genomic data from imaging should be critically assessed; external validation is essential. Competing Interests: None declared. (© The Author(s) 2024. Published by Oxford University Press, the Society for Neuro-Oncology and the European Association of Neuro-Oncology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu