Rupture Status Classification of Intracranial Aneurysms Using Morphological Parameters

Abstract

Intracranial aneurysms are pathologic dilations of the vessel wall, which bear the risk of rupture and of fatal consequences for the patient. Since treatment may be accompanied by severe complications as well, rupture risk assessment and thus rupture risk prediction plays an important role in clinical research. In this work, we investigate the potential of morphological features for rupture risk status classification in 100 intracranial aneurysms. We propose a pipeline for morphological feature extraction and rupture status classification with subsequent feature ranking and inspection. Our classification setup involves training separate models for each aneurysm type (sidewall or bifurcation) with multiple learning algorithms. We report on the classification performance of our pipeline and examine the predictive power of each morphological parameter towards rupture status classification. Further, we identify the most important features for the best models and study their marginal prediction.

Important figure

Figure 2. Illustration of the extracted morphological features \(H_{max}\), \(W_{max}\), \(H_{ortho}\), \(W_{ortho}\) and \(D_{max}\) (A). The angles α, β and γ are extracted based on \(B_1\), \(B_2\) and the dome point \(D\) (B). Separating the aneurysm from the parent vessel based on the neck curve yields \(A_A\) and \(V_A\) (C). The area of the ostium and the projected ostium, i.e., \(A_{O1}\) and \(A_{O2}\), are shown in (D), where \(C_{NC}\) denotes the center of the neck curve.

BibTeX citation

@InProceedings{Niemann:CBMS2018,
  author    = {Niemann, Uli and Berg, Philipp and Niemann, Annika and Beuing,
               Oliver and Preim, Bernhard and Spiliopoulou, Myra and Saalfeld,
               Sylvia},
  booktitle = {Computer-Based Medical Systems (CBMS)},
  title     = {{Rupture Status Classification of Intracranial Aneurysms Using
                Morphological Parameters}},
  year      = {2018},
  pages     = {48--53},
  doi       = {10.1109/CBMS.2018.00016},
}