1. Deep shape features for predicting future intracranial aneurysm growth
- Author
-
Žiga Špiclin, Franjo Pernuš, and Žiga Bizjak
- Subjects
medicine.medical_specialty ,žilne bolezni ,intrakranialne anevrizme ,Computer science ,Physiology ,Magnetic resonance angiography ,030218 nuclear medicine & medical imaging ,growth prediction ,03 medical and health sciences ,0302 clinical medicine ,Aneurysm ,Physiology (medical) ,medicine ,QP1-981 ,cardiovascular diseases ,predikcija rasti ,Original Research ,medicine.diagnostic_test ,globoko učenje ,business.industry ,Deep learning ,Univariate ,deep learning ,vascular disease ,medicine.disease ,Thresholding ,intracranial aneurysm ,klasifikacija ,Random forest ,classification ,morphological features ,morphologic features ,Angiography ,udc:004.8:616.13-007.64 ,Radiology ,Artificial intelligence ,business ,morfološke značilnosti ,Feature learning ,030217 neurology & neurosurgery - Abstract
Introduction: Intracranial aneurysms (IAs) are a common vascular pathology and are associated with a risk of rupture, which is often fatal. Aneurysm growth is considered a surrogate of rupture risk; therefore, the study aimed to develop and evaluate prediction models of future artificial intelligence (AI) growth based on baseline aneurysm morphology as a computer-aided treatment decision support.Materials and methods: Follow-up CT angiography (CTA) and magnetic resonance angiography (MRA) angiograms of 39 patients with 44 IAs were classified by an expert as growing and stable (25/19). From the angiograms vascular surface meshes were extracted and the aneurysm shape was characterized by established morphologic features and novel deep shape features. The features corresponding to the baseline aneurysms were used to predict future aneurysm growth using univariate thresholding, multivariate random forest and multi-layer perceptron (MLP) learning, and deep shape learning based on the PointNet++ model.Results: The proposed deep shape feature learning method achieved an accuracy of 0.82 (sensitivity = 0.96, specificity = 0.63), while the multivariate learning and univariate thresholding methods were inferior with an accuracy of up to 0.68 and 0.63, respectively.Conclusion: High-performing classification of future growing IAs renders the proposed deep shape features learning approach as the key enabling tool to manage rupture risk in the “no treatment” paradigm of patient follow-up imaging.
- Published
- 2023