Image updating for brain deformation compensation: cross-validation with intraoperative ultrasound

2018 ◽  
Author(s):  
Xiaoyao Fan ◽  
David W. Roberts ◽  
Jonathan D. Olson ◽  
Chen Li ◽  
Keith D. Paulsen
Keyword(s):  
Cross Validation ◽  
Intraoperative Ultrasound ◽  
Brain Deformation ◽  
Deformation Compensation

scholarly journals Towards automated correction of brain shift using deep deformable magnetic resonance imaging-intraoperative ultrasound (MRI-iUS) registration

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Ramy A. Zeineldin ◽  
Mohamed E. Karar ◽  
Jan Coburger ◽  
Christian R. Wirtz ◽  
Franziska Mathis-Ullrich ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Mean Squared Error ◽  
Intraoperative Ultrasound ◽  
Brain Shift ◽  
Resonance Imaging ◽  
Registration Method ◽  
Brain Deformation ◽  
Preoperative Magnetic Resonance ◽  
Magnetic Resonance Imaging Mri

AbstractIntraoperative brain deformation, so-called brain shift, affects the applicability of preoperative magnetic resonance imaging (MRI) data to assist the procedures of intraoperative ultrasound (iUS) guidance during neurosurgery. This paper proposes a deep learning-based approach for fast and accurate deformable registration of preoperative MRI to iUS images to correct brain shift. Based on the architecture of 3D convolutional neural networks, the proposed deep MRI-iUS registration method has been successfully tested and evaluated on the retrospective evaluation of cerebral tumors (RESECT) dataset. This study showed that our proposed method outperforms other registration methods in previous studies with an average mean squared error (MSE) of 85. Moreover, this method can register three 3D MRI-US pair in less than a second, improving the expected outcomes of brain surgery.

Image updating for brain deformation compensation in tumor resection

2016 ◽  
Author(s):  
Xiaoyao Fan ◽  
Songbai Ji ◽  
Jonathan D. Olson ◽  
David W. Roberts ◽  
Alex Hartov ◽  
...  
Keyword(s):  
Tumor Resection ◽  
Brain Deformation ◽  
Deformation Compensation

scholarly journals Volumetric Intraoperative Brain Deformation Compensation: Model Development and Phantom Validation

2012 ◽  
Vol 31 (8) ◽  
pp. 1607-1619 ◽  
Author(s):  
Christine DeLorenzo ◽  
Xenophon Papademetris ◽  
Lawrence H. Staib ◽  
Kenneth P. Vives ◽  
Dennis D. Spencer ◽  
...  
Keyword(s):  
Model Development ◽  
Compensation Model ◽  
Brain Deformation ◽  
Deformation Compensation ◽  
Phantom Validation

Advantages and limitations of intraoperative ultrasound strain elastography applied in brain tumor surgery: a single-center experience

2021 ◽  
Author(s):  
Santiago Cepeda ◽  
Sergio García-García ◽  
Ignacio Arrese ◽  
María Velasco-Casares ◽  
Rosario Sarabia
Keyword(s):  
Brain Tumor ◽  
Decision Tree ◽  
Cross Validation ◽  
Intraoperative Ultrasound ◽  
Classification Model ◽  
Histopathological Diagnosis ◽  
Low Grade ◽  
Tissue Elasticity ◽  
Strain Elastography ◽  
Tree Classifier

Abstract Objective Strain elastography is an intraoperative ultrasound (ioUS) modality currently under development with various potential applications in neurosurgery. However, certain technical aspects and limitations have not yet been adequately explained. The objective of our work is to share the experience of our center in a case series of operated brain tumors in which we have applied strain elastography.Methods We retrospectively analyzed patients who underwent craniotomy for a brain tumor between March 2018 to March 2021. Cases with an ioUS strain elastography study were included. The elastograms were processed semi-quantitatively by decomposing the image in HSB (Hue, Saturation, Brightness) format. Subsequently, the mean tissue elasticity (MTE) values were calculated from the histogram of intensities of the pixels of the hue images. The tumor was manually segmented, and regions of interest (ROIs) were placed in the peritumoral area. An analysis was performed to correlate the histopathological groups and the tumor and peritumoral MTE values using the Kruskal-Wallis test. In addition, a classification model was developed using an algorithm based on a decision tree. Then, model predictive capacity was evaluated through 10-folds cross-validation. Finally, elastogram’s quality was assessed to discuss possible sources of artifacts and weaknesses of the ultrasound technique.Results One hundred two patients with the following histopathological diagnosis were analyzed: 43 high-grade gliomas, 11 low-grade gliomas, 28 meningiomas, and 20 metastases. The tumor MTE values ​​were significantly different between the histopathological groups, p <.001, c2 = 46.34, e2 = .45. There were also significant differences for the MTE values ​​concerning the peritumor, p<.001, c2 = 25.47, e2 = .25. The decision tree classifier showed an area under the curve (AUC) of the average over classes of 0.97, and the classification accuracy (CA) was 86%. After 10-folds cross-validation, the AUC was 0.73, and the CA was 72%. The main technical limitations found in our series were: the presence of artifacts after dural opening, the variability of the frequency and amplitude of the mechanical pulsations, and the challenge in evaluating deep lesions.Conclusion ioUS strain elastography is a fast and versatile technique that provides relevant information to adapt the surgical strategy. Furthermore, the stiffness of the tissues has a plausible histopathological correlation. For these reasons, this technique has enormous potential to be exploited in the coming years.

Sign in / Sign up

Export Citation Format

Share Document