Applying machine learning to optical coherence tomography images for automated tissue classification in brain metastases.

PURPOSE: A precise resection of the entire tumor tissue during surgery for brain metastases is essential to reduce local recurrence. Conventional intraoperative imaging techniques all have limitations in detecting tumor remnants. Therefore, there is a need for innovative new imaging methods such as optical coherence tomography (OCT). The purpose of this study is to discriminate brain metastases from healthy brain tissue in an ex vivo setting by applying texture analysis and machine learning algorithms for tissue classification to OCT images. METHODS: Tumor and healthy tissue samples were collected during resection of brain metastases. Samples were imaged using OCT. Texture features were extracted from B-scans. Then, a machine learning algorithm using principal component analysis (PCA) and support vector machines (SVM) was applied to the OCT scans for classification. As a gold standard, an experienced pathologist examined the tissue samples histologically and determined the percentage of vital tumor, necrosis and healthy tissue of each sample. A total of 14.336 B-scans from 14 tissue samples were included in the classification analysis. RESULTS: We were able to discriminate vital tumor from healthy brain tissue with an accuracy of 95.75%. By comparing necrotic tissue and healthy tissue, a classification accuracy of 99.10% was obtained. A generalized classification between brain metastases (vital tumor and necrosis) and healthy tissue was achieved with an accuracy of 96.83%. CONCLUSIONS: An automated classification of brain metastases and healthy brain tissue is feasible using OCT imaging, extracted texture features and machine learning with PCA and SVM. The established approach can prospectively provide the surgeon with additional information about the tissue, thus optimizing the extent of tumor resection and minimizing the risk of local recurrences.

High-resolution in vivo imaging of peripheral nerves using optical coherence tomography: a feasibility study.

OBJECTIVE: Because of their complex topography, long courses, and small diameters, peripheral nerves are challenging structures for radiological diagnostics. However, imaging techniques in the area of peripheral nerve diseases have undergone unexpected development in recent decades. They include MRI and high-resolution sonography (HRS). Yet none of those imaging techniques reaches a resolution comparable to that of histological sections. Fascicles are the smallest discernable structure. Optical coherence tomography (OCT) is the first imaging technique that is able to depict a nerve's ultrastructure at micrometer resolution. In the current study, the authors present an in vivo assessment of human peripheral nerves using OCT. METHODS: OCT measurement was performed in 34 patients with different peripheral nerve pathologies, i.e., nerve compression syndromes. The nerves were examined during surgery after their exposure. Only the sural nerve was twice examined ex vivo. The Thorlabs OCT systems Callisto and Ganymede were used. For intraoperative use, a hand probe was covered with a sterile foil. Different postprocessing imaging techniques were applied and evaluated. In order to highlight certain structures, five texture parameters based on gray-level co-occurrence matrices were calculated according to Haralick. RESULTS: The intraoperative use of OCT is easy and intuitive. Image artifacts are mainly caused by motion and the sterile foil. If the artifacts are kept at a low level, the hyporeflecting bundles of nerve fascicles and their inner parts can be displayed. In the Haralick evaluation, the second angular moment is most suitable to depict the connective tissue. CONCLUSIONS: OCT is a new imaging technique that has shown promise in peripheral nerve surgery for particular questions. Its resolution exceeds that provided by recent radiological possibilities such as MRI and HRS. Since its field of view is relatively small, faster acquisition times would be highly desirable and have already been demonstrated by other groups. Currently, the method resembles an optical biopsy and can be a supplement to intraoperative sonography, giving high-resolution insight into a suspect area that has been located by sonography in advance.

Automated differentiation between meningioma and healthy brain tissue based on optical coherence tomography ex vivo images using texture features.

Brain tissue analysis is highly desired in neurosurgery, such as tumor resection. To guarantee best life quality afterward, exact navigation within the brain during the surgery is essential. So far, no method has been established that perfectly fulfills this need. Optical coherence tomography (OCT) is a promising three-dimensional imaging tool to support neurosurgical resections. We perform a preliminary study toward in vivo brain tumor removal assistance by investigating meningioma, healthy white, and healthy gray matter. For that purpose, we utilized a commercially available OCT device (Thorlabs Callisto) and measured eight samples of meningioma, three samples of healthy white, and two samples of healthy gray matter ex vivo directly after removal. Structural variations of different tissue types, especially meningioma, can already be seen in the raw OCT images. Nevertheless, an automated differentiation approach is desired, so that neurosurgical guidance can be delivered without a-priori knowledge of the surgeon. Therefore, we employ different algorithms to extract texture features and apply pattern recognition methods for their classification. With these postprocessing steps, an accuracy of nearly 98% was found.