"We extract 3D geometries of Intracranial aneurysms from medical imaging data and describe their shapes by various radiomic, morphometric and psychometric methods. Using statistical analysis and machine learning, we seek to assess the clinical significance of Intracranial aneurysms morphology"
Title: Shape-based analysis of intracranial aneurysms
Date of Defense: 27.8.2020
Keywords: medical data science, statistical analysis, machine learning, 3D medical imaging, radiomics, morphometry, psychometry
Abstract: Intracranial aneurysms (IAs) are focal deformations of brain arteries that occur in 2-5% of the population. Although mostly stable and symptom free, IAs may continue to grow and eventually rupture (incidence rate of about 1% per year). IA rupture is the principal cause for non-traumatic subarachnoid hemorrhage, known for its potentially devastating effects on the patient. Shape plays an important role in the assessment of unruptured IAs. When weighing the risks of rupture against the risks of treatment, radiologists are taking into account IA morphology, but only very qualitatively. In our work, we focus on identifying clinically relevant morphological characteristics with the aim of establishing quantitative shape predictors for IA disease status. We extract 3D geometries of IAs from medical imaging data and describe their shapes by various radiomic, morphometric and psychometric methods. Using statistical analysis and machine learning, we seek to assess the clinical significance of IA morphology.
Juchler, N., Schilling, S., Glüge, S., Bijlenga, P., Rüfenacht, D., Kurtcuoglu, V., Hirsch, S. (2020): Radiomics approach to quantify shape irregularity from crowd-based qualitative assessment of intracranial aneurysms. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Juchler, N., Schilling, S., Bijlenga, P., Morel, S., Rüfenacht, D., Kurtcuoglu,V., Hirsch, S. (2020): Shape irregularity of the intracranial aneurysm lumen exhibits diagnostic value. Acta Neurochirurgica 162, 2261–2270
Detmer, F.J., Fajardo-Jiménez, D., Mut, F., Juchler, N., Hirsch, S., Mendes Pereira, V., Bijlenga, P., Cebral, J.R. (2018): External validation of cerebral aneurysm rupture probability model with data from two patient cohorts. Acta Neurochirurgica 160, 2425–2434
Detmer, F.J., Hadad, Sara, Chung, B.J., Mut, F., Slawski, M., Juchler, N., Kurtcuoglu, V., Hirsch, S., Bijlenga, P., Uchiyama, Y.. Fujimura, S., Yamamoto, M., Murayama, Y., Takao, H., Koivisto, T., Frösen, J., Cebral, J.R. (2019): Extending statistical learning for aneurysm rupture assessment to Finnish and Japanese populations using morphology, hemodynamics, and patient characteristics. Neurosurgical Focus 47 (1):E16, 2019
Watanabe, K., Anzai, H., Juchler, N., Hirsch, S., Bijlenga, P., Ohta, M. (2019): Influence of Input Image Configurations on Output of a Convolutional Neural Network to Detect Cerebral Aneurysms. Proceedings of the ASME 2019 International Mechanical Engineering Congress and Exposition. Volume 3: Biomedical and Biotechnology Engineering. Salt Lake City, Utah, USA. November 11–14, 2019. V003T04A023