This article requires a subscription to view the full text. If you have a subscription you may use the login form below to view the article. Access to this article can also be purchased.
Abstract
BACKGROUND AND PURPOSE: Existing neuroradiology reference materials do not cover the full range of primary brain tumor presentations, and text-based medical image search engines are limited by the lack of consistent structure in radiology reports. To address this, an image-based search approach is introduced here, leveraging an institutional database to find reference MRIs visually similar to presented query cases.
MATERIALS AND METHODS: Two hundred ninety-five patients (mean age and standard deviation, 51 ± 20 years) with primary brain tumors who underwent surgical and/or radiotherapeutic treatment between 2000 and 2021 were included in this retrospective study. Semiautomated convolutional neural network–based tumor segmentation was performed, and radiomic features were extracted. The data set was split into reference and query subsets, and dimensionality reduction was applied to cluster reference cases. Radiomic features extracted from each query case were projected onto the clustered reference cases, and nearest neighbors were retrieved. Retrieval performance was evaluated by using mean average precision at k, and the best-performing dimensionality reduction technique was identified. Expert readers independently rated visual similarity by using a 5-point Likert scale.
RESULTS: t-Distributed stochastic neighbor embedding with 6 components was the highest-performing dimensionality reduction technique, with mean average precision at 5 ranging from 78%–100% by tumor type. The top 5 retrieved reference cases showed high visual similarity Likert scores with corresponding query cases (76% ‘similar’ or ‘very similar’).
CONCLUSIONS: We introduce an image-based search method for exploring historical MR images of primary brain tumors and fetching reference cases closely resembling queried ones. Assessment involving comparison of tumor types and visual similarity Likert scoring by expert neuroradiologists validates the effectiveness of this method.
ABBREVIATIONS:
- A/O
- astrocytoma and oligodendroglioma WHO CNS grades 2–3
- CNN
- convolutional neural network
- G/A
- glioblastoma and astrocytoma WHO CNS grade 4
- ICC
- intraclass correlation coefficient
- mAP@k
- mean average precision at k
- MEN
- meningioma
- PA
- pilocytic astrocytoma
- PCA
- principal component analysis
- PHATE
- potential of heat-diffusion for affinity-based trajectory embedding
- t-SNE
- t-distributed stochastic neighbor embedding
- T1CE
- T1 contrast-enhanced
- UMAP
- uniform manifold approximation and projection
- WHO
- World Health Organization
Footnotes
Marc von Reppert and Saahil Chadha contributed equally.
A complete list of the authors in the IBSR Consortium appears at the end of this article.
This work was supported in part by a KL2 TR00186 grant from the National Center for Advancing Translational Sciences.
Disclosure forms provided by the authors are available with the full text and PDF of this article at www.ajnr.org.
- © 2025 by American Journal of Neuroradiology