The simulation of realistic ultrasound (US) images has many applications in image-guided surgery such as image registration, data augmentation, or education. We simulated intraoperative US images of the brain after tumor resection surgery. A Generative Adversarial Networks first generated an US image with resection from a resection cavity map. This generated cavity texture was then blended into a real pre-resection patient-specific US image. A validation study showed that two neurosurgeons correctly labelled only 56% and 53% of the simulated images, which indicate that these synthesized images are hardly distinguishable from real post-resection US images.
During tumor resection surgery, intraoperative ultrasound images of the brain show anatomical structures, the tumor, and the resection cavity (after resection started). These elements help with the localization and tumor resection, and can be used to register the preoperative MRI to intraoperative images, to compensate for the tissue deformation occurring during surgery. We evaluate a multi-class segmentation model for the sulci, falx cerebri, tumor, resection cavity and ventricle. We present strategies to overcome the severe class imbalance in the training data. We show that a multi-class model may leverage inter-class spatial relationships and produce more accurate results than single-class models.
To compensate for the intraoperative brain tissue deformation, computer-assisted intervention methods have been used to register preoperative magnetic resonance images with intraoperative images. In order to model the deformation due to tissue resection, the resection cavity needs to be segmented in intraoperative images. We present an automatic method to segment the resection cavity in intraoperative ultrasound (iUS) images. We trained and evaluated two-dimensional (2-D) and three-dimensional (3-D) U-Net networks on two datasets of 37 and 13 cases that contain images acquired from different ultrasound systems. The best overall performing method was the 3-D network, which resulted in a 0.72 mean and 0.88 median Dice score over the whole dataset. The 2-D network also had good results with less computation time, with a median Dice score over 0.8. We also evaluated the sensitivity of network performance to training and testing with images from different ultrasound systems and image field of view. In this application, we found specialized networks to be more accurate for processing similar images than a general network trained with all the data. Overall, promising results were obtained for both datasets using specialized networks. This motivates further studies with additional clinical data, to enable training and validation of a clinically viable deep-learning model for automated delineation of the tumor resection cavity in iUS images.
Most brain-shift compensation methods address the problem of updating preoperative images to reflect brain deformations following the craniotomy and dura opening. However, fewer enable to take into account the resection-induced deformations occuring all along the tumor removal procedure. This paper evaluates the use of two existing methods to tackle that problem. Both techniques rely on blood vessels segmented then skeletonized from preoperative MR Angiography and navigated Doppler Ultrasound images acquired during resection. While the first one proposes to register the vascular trees using a rigid modified ICP algorithm, the second method relies on a non-rigid constrained-based biomechanical approach. Quantitative results are provided, based on distances between paired landmarks set on blood vessels then anatomical structures delineated on medical images. A qualitative evaluation of the compensation is also presented using initial and updated images. An analysis on three cases of surface tumor shows both methods, especially the biomechanical one, can compensate up to 63% of the brain-shift, with an error in the range of 2 mm. However, these results are not reproduced on a more complex case of deep tumor. While more patients must be included, these preliminary results show that vesselbased methods are well suited to compensate for resection-induced brain-shift, but better outcomes in complex cases still require to improve the methods to take the resection into account.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.