Deep reinforcement learning for cerebral anterior vessel tree extraction from 3D CTA images
| Autor: | Aad Van der Lugt, Wim Van Zwam, Shuai Li, Shuaib Lwasa, Jiahang Su, Theo Van Walsum, Lennard Wolff |
|---|---|
| Přispěvatelé: | Radiology & Nuclear Medicine, Beeldvorming, MUMC+: DA BV Medisch Specialisten Radiologie (9), RS: Carim - B05 Cerebral small vessel disease, RS: Carim - B06 Imaging |
| Rok vydání: | 2023 |
| Předmět: |
Neural Networks
Computed Tomography Angiography Tomography X-Ray Computed/methods Health Informatics Brain vessel Brain/blood supply Imaging Computer Imaging Three-Dimensional Humans Radiology Nuclear Medicine and imaging Tomography Deep reinforcement learning Computed Tomography Angiography/methods Radiological and Ultrasound Technology Tracking 3D CTA Angiography Brain Computer Graphics and Computer-Aided Design X-Ray Computed/methods Three-Dimensional Neural Networks Computer Computer Vision and Pattern Recognition Tomography X-Ray Computed Bifurcation detection CNN |
| Zdroj: | Medical Image Analysis, 84 Medical Image Analysis, 84:102724. Elsevier |
| ISSN: | 1361-8415 |
| Popis: | Extracting the cerebral anterior vessel tree of patients with an intracranial large vessel occlusion (LVO) is relevant to investigate potential biomarkers that can contribute to treatment decision making. The purpose of our work is to develop a method that can achieve this from routinely acquired computed tomography angiography (CTA) and computed tomography perfusion (CTP) images. To this end, we regard the anterior vessel tree as a set of bifurcations and connected centerlines. The method consists of a proximal policy optimization (PPO) based deep reinforcement learning (DRL) approach for tracking centerlines, a convolutional neural network based bifurcation detector, and a breadth-first vessel tree construction approach taking the tracking and bifurcation detection results as input. We experimentally determine the added values of various components of the tracker. Both DRL vessel tracking and CNN bifurcation detection were assessed in a cross validation experiment using 115 subjects. The anterior vessel tree formation was evaluated on an independent test set of 25 subjects, and compared to interobserver variation on a small subset of images. The DRL tracking result achieves a median overlapping rate until the first error (1.8 mm off the reference standard) of 100, [46, 100] % on 8032 vessels over 115 subjects. The bifurcation detector reaches an average recall and precision of 76% and 87% respectively during the vessel tree formation process. The final vessel tree formation achieves a median recall of 68% and precision of 70%, which is in line with the interobserver agreement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect