The sudden rupture of a cerebral aneurysm can result in severe disability or death and is treatable with neurosurgical clipping or minimally invasive endovascular procedures (coiling or flow diverters) guided by angio...
详细信息
ISBN:
(数字)9798350388152
ISBN:
(纸本)9798350388169
The sudden rupture of a cerebral aneurysm can result in severe disability or death and is treatable with neurosurgical clipping or minimally invasive endovascular procedures (coiling or flow diverters) guided by angiography. However, the need for retreatment is relatively common. Clinicians rely on experience and 2D image techniques to lead and guide endovascular procedures. Cerebral vasculature is highly three-dimensional, with complex 3D curvature and tortuosity. Current imaging techniques are used during procedures to ‘flatten’ the complex vasculature. In this study, we developed a method for using 3 uniquely oriented angiographic images to reconstruct the 3D aneurysm *** used open-source datasets of 149 aneurysm geometries consisting of patient-specific cerebral aneurysms and surrounding vasculature with a range of complex morphologies and sizes. After leaving 30 for unseen testing, we augmented the remaining dataset by orientation and scaling, yielding a dataset of over 24,000 unique geometries. We restructured the irregular point clouds into a regular grid. This 3D data functioned as the output to the neural network. Simulated angiographic images were obtained by using 2D projections of the gridded data in the XY, YZ, and XZ planes. These three projections were used as the input to the *** developed a 3D convolutional neural network with a customized dice loss function to account for the surrounding padding. Initial results are promising, showing that complex vasculature can be identified in 3D; however, DARNN has trouble distinguishing multiple outlet vessels in a small region. Predictions are made in 0.1 s.
Robust tracking of deformable object like catheter or vascular structures in X-ray images is an important technique used in imageguidedmedicalinterventions for effective motion compensation and dynamic multi-modali...
详细信息
ISBN:
(纸本)9781479951192
Robust tracking of deformable object like catheter or vascular structures in X-ray images is an important technique used in imageguidedmedicalinterventions for effective motion compensation and dynamic multi-modality image fusion. Tracking of such anatomical structures and devices is very challenging due to large degrees of appearance changes, low visibility of X-ray images and the deformable nature of the underlying motion field as a result of complex 3D anatomical movements projected into 2D images. To address these issues, we propose a new deformable tracking method using the tensor-based algorithm with model propagation. Specifically, the deformable tracking is formulated as a multi-dimensional assignment problem which is solved by rank-1 l_1 tensor approximation. The model prior is propagated in the course of deformable tracking. Both the higher order information and the model prior provide powerful discriminative cues for reducing ambiguity arising from the complex background, and consequently improve the tracking robustness. To validate the proposed approach, we applied it to catheter and vascular structures tracking and tested on X-ray fluoroscopic sequences obtained from 17 clinical cases. The results show, both quantitatively and qualitatively, that our approach achieves a mean tracking error of 1.4 pixels for vascular structure and 1.3 pixels for catheter tracking.
A novel MR-compatible manually-actuated robotic manipulation device has been developed. It is a general-purpose system that provides access to the patient inside a closed-cylindrical MRI scanner. It allows the perform...
详细信息
ISBN:
(纸本)9781457711992
A novel MR-compatible manually-actuated robotic manipulation device has been developed. It is a general-purpose system that provides access to the patient inside a closed-cylindrical MRI scanner. It allows the performance of various minimally-invasive interventions, such as biopsies and local drug deliveries, using real-time images for guidance and monitoring. The design of the system is described and the prototype constructed is presented together with initial MRI phantom testing on needle targeting. The characteristics and potential of manual actuation in MR-compatible robotic systems are examined.
暂无评论