In this work we configure Haralick's texture parameter contrast to match the dimensions of characteristic structural features in ex vivo samples from glioblastoma (GBM) resection imaged with optical coherence tomography (OCT). The aim is to find and tune different texture features in a way that they enable the best possible basis for tissue classification using support vector machines (SVM). We used a sample collective including 18 tissue samples comprising 9 samples with at least 90% vital tumor and no healthy tissue, as well as 9 samples with 100% healthy tissue. All samples were imaged ex vivo immediately after resection. As a reference all samples were then examined professionally in the department of histopathology to determine tissue percentages. Based on the acquired 3D OCT images, texture features were extracted and optimized supported by the knowledge of medical professionals. Relations between the size of characteristic structures in healthy tissue as well as in GBM and different texture features were examined and evaluated. We focused on texture parameters as proposed by Haralick, relying on gray-level co-occurrence matrices (GLCMs). The displacement vector for the determination of those GLCMs was matched with size and direction of the characteristic structural tissue features of healthy and tumorous tissue. The results serve as a starting point to optimize the classification process of GBM against healthy tissue using SVM.
In this work, we compare five deep learning solutions to automatically segment the resection cavity in postoperative MRI. The proposed methods are based on the same 3D U-Net architecture. We use a dataset of postoperative MRI volumes, each including four MRI sequences and the ground truth of the corresponding resection cavity. Four solutions are trained with a different MRI sequence. Besides, a method designed with all the available sequences is also presented. Our experiments show that the method trained only with the T1 weighted contrast-enhanced MRI sequence achieves the best results, with a median DICE index of 0.81.
Segmentation of anatomical structures in intraoperative ultrasound (iUS) images during image-guided interventions is challenging. Anatomical variances and the uniqueness of each procedure impede robust automatic image analysis. In addition, ultrasound image acquisition itself, especially acquired freehand by multiple physicians, is subject to major variability. In this paper we present a robust and fully automatic neural-network-based segmentation of central structures of the brain on B-mode ultrasound images. For our study we used iUS data sets from 18 patients, containing sweeps before, during, and after tumor resection, acquired at the University Hospital Essen, Germany. Different machine learning approaches are compared and discussed in order to achieve results of highest quality without overfitting. We evaluate our results on the same data sets as in a previous publication in which the segmentations were used to improve iUS and preoperative MRI registration. Despite the smaller amount of data compared to other studies, we could efficiently train a U-net model for our purpose. Segmentations for this demanding task were performed with an average Dice coefficient of 0.88 and an average Hausdorff distance of 5.21 mm. Compared with a prior method for which a Random Forest classifier was trained with handcrafted features, the Dice coefficient could be increased by 0.14 and the Hausdorff distance is reduced by 7 mm.
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.