2022 · Hemodynamics & imaging
Enhanced Radiomics for Prediction of Rupture Status in Cerebral Aneurysms
Lauric A, Ludwig CG, Malek AM.
World Neurosurg 159:e8-e22, 2022.
PMID 34823040 · DOI 10.1016/j.wneu.2021.11.038
In plain language
Radiomics is a computer method that automatically measures shape and texture features in medical images. When applied to brain aneurysms, it has done worse than standard size and shape measures at telling ruptured from unruptured aneurysms, partly because it ignores the direction of the aneurysm neck and the size of the artery it grows from.

The authors rotated each 3D angiogram so the aneurysm neck was aligned in the same way and added an estimate of the parent artery size. They tested this "enhanced radiomics" on 135 sidewall aneurysms (32 ruptured) and 216 bifurcation aneurysms (90 ruptured). It matched or beat both standard measures and conventional radiomics, with areas under the curve of 0.85 for sidewall and 0.78 for bifurcation aneurysms.
This automatic method deserves testing in larger, multicenter studies.
A plain-language summary for patients and families. It is not medical advice, and individual results vary.
Abstract
Background
Radiomics is a powerful tool for automatic extraction of morphological features, but when applied to cerebral aneurysms, it is inferior to established descriptors in classifying rupture status. We sought a strategy to recover neck orientation and parent vessel caliber to enhance Radiomics performance and facilitate its adoption for aneurysm risk stratification.
Methods
We analyzed 135 sidewall (32 ruptured) and 216 bifurcation (90 ruptured) aneurysms from three-dimensional rotational catheter angiography datasets. Clinical three-dimensional rotational catheter angiography defined in arbitrary orientation underwent affine transformations enabling aneurysm neck alignment to XY plane before analysis in PyRadiomics, facilitating automatic extraction of aneurysm height and width, previously not possible with random alignment. Additionally, parent vessel size was estimated from aneurysm location and incorporated into enhanced Radiomics (height, width, height/width, size ratio). Rupture status classification was compared across methodologies for 31 automatically computed conventional Radiomics, enhanced Radiomics, and established size/shape descriptors using univariate, multivariate, and area under the curve (AUC) statistics.
Results
Enhanced Radiomics-derived height/width and size ratio were significantly higher in both ruptured subsets. Using multivariate analysis in sidewall lesions, enhanced Radiomics (AUC = 0.85) matched established features (AUC = 0.86) and outperformed conventional Radiomics (AUC = 0.82); in bifurcation lesions, enhanced Radiomics (AUC = 0.78) outperformed both established features (AUC = 0.76) and conventional Radiomics (AUC = 0.74).
Conclusions
Enhanced Radiomics incorporating neck orientation and parent vessel estimate is an efficient operator-independent methodology that offers superior rupture status classification for both sidewall and bifurcation aneurysms and should be considered a strong candidate for larger-scale multicenter and multimodality validation.
Abstract as indexed in PubMed (PMID 34823040). Copyright the publisher.
Cite this paper
Lauric A, Ludwig CG, Malek AM. Enhanced Radiomics for Prediction of Rupture Status in Cerebral Aneurysms. World Neurosurg 159:e8-e22. 2022. doi:10.1016/j.wneu.2021.11.038 PMID: 34823040.