Morphology-based radiomics signature: a novel determinant to identify multiple intracranial aneurysms rupture

Abstract

We aimed to develop and validate a morphology-based radiomics signature nomogram for assessing the risk of intracranial aneurysm (IA) rupture. A total of 254 aneurysms in 105 patients with subarachnoid hemorrhage and multiple intracranial aneurysms from three centers were retrospectively reviewed and randomly divided into the derivation and validation cohorts. Radiomics morphological features were automatically extracted from digital subtraction angiography and selected by the least absolute shrinkage and selection operator algorithm to develop a radiomics signature. A radiomics signature-based nomogram was developed by incorporating the signature and traditional morphological features. The performance of calibration, discrimination, and clinical usefulness of the nomogram was assessed. Ten radiomics morphological features were selected to build the radiomics signature model, which showed better discrimination with an area under the curve (AUC) equal to 0.814 and 0.835 in the derivation and validation cohorts compared with 0.747 and 0.666 in the traditional model, which only include traditional morphological features. When radiomics signature and traditional morphological features were combined, the AUC increased to 0.842 and 0.849 in the derivation and validation cohorts, thus showing better performance in assessing aneurysm rupture risk. This novel model could be useful for decision-making and risk stratification for patients with IAs.

Keywords: intracranial aneurysm; nomogram; radiomics features; radiomics signature; risk prediction.

Figure 1

Definitive hemorrhage pattern to confirm the ruptured aneurysm for patients who underwent endovascular or no treatment. A 67-year-old woman presented with subarachnoid hemorrhage (A) was found to have left and right internal carotid aneurysms (B–D). The ruptured aneurysm is the right internal carotid aneurysm.

Figure 2

Flow chart of the study. The aneurysm was reconstructed from DSA images and using 3D slicer. The segmentation was performed by threshold and checked layer by layer. Then, the segmented label map and volume files were entered in the Pyradiomics package in the Python platform, and 17 radiomics morphological features were extracted for each aneurysm. The least absolute shrinkage and selection operator binary logistic were used to select the potential assessment factors and develop a radiomics signature. Along the radiomics morphological features, 16 traditional morphological features were combined and entered in the model construction analysis. Finally, the optimal model was performed in the nomogram.

Figure 3

Measurements of the traditional morphological features. (II-A) schematically shows the aneurysm size and diameters of parent and branch vessels measurements, with the height (a), width (b), neck width (c), the diameter of the parent vessel (d), diameters of the branching vessel (e and f). (II-B) shows the angle measurements. The outflow angle (A) was defined as the angle at which the aneurysm flows outward to the distal parent artery in the sidewall aneurysm or to the daughter branch most approaching 180° in the bifurcation aneurysm. The inflow angle (B) was defined as the angle from the parent artery into the aneurysm. The main branching angle (C) was defined as the angle of the parent artery in the sidewall aneurysm or the angle between the parent artery and the daughter branch most approaching 180° in bifurcation aneurysm. In addition, several indicators were calculated: aspect ratio (AR) was defined as the ratio of aneurysm height (a) to the neck width (c); size ratio (SR) was defined as the ratio of aneurysm height (a) to the parent vessel diameter (d); WH ratio was defined as the ratio of aneurysm width (b) to the height (a); branching to parent ratio (BPR) was defined as the ratio of the sum of the diameters of the branch vessels (e + f) to the diameter of the parent artery (d) (in case of a sidewall aneurysm, the BPR was set to 1); neck to parent ratio (NPR) was defined as the ratio of the aneurysm neck width (c) to the parent artery diameter (d).

Figure 4

Radiomics signature score (rad-score) calculation. (A) Radiomic features ranked by coefficients of the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. The flatness was the most correlated indicator with IA rupture. (B) Radiomics signature (rad-score) was constructed from a linear combination of selected features that were weighted based on their respective LASSO coefficients.

Figure 5

Violin plots of the radiomics signature score (rad-score). There was a significant difference in the rad-score between unruptured IA and ruptured IA in the derivation cohort (p < 0.001, III-A), which was then confirmed in the validation cohort (p < 0.001, III-B).

Figure 6

Rad-score for every aneurysm in each in the derivation (A) and validation cohort (B).

Figure 7

The area under the curves (AUCs) shows that the morphology-based radiomics signature model (A) has better discrimination compared with the morphology-based radiomics features model (B) and morphology-based radiomics features model (C). Radiomics morphological feature selection used the LASSO binary logistic regression model (D).

Figure 8

The morphology-based radiomics signature model was developed into nomogram (A). Calibration curves suggest that our nomogram performed well in both the derivation (B) and validation (C) cohorts.

Figure 9

The decision curve analysis demonstrates the morphology-based radiomics signature model (MRS model) has a larger net benefit compared with the morphology-based radiomics features model (MRF model) and morphology-based traditional features model (MTF model) for the assessment of aneurysm rupture risk.