KEYWORDS: Feature extraction, Magnetic resonance imaging, Image segmentation, Deep learning, Education and training, Visualization, Brain, Decision making, Cross validation, Surgery
Vestibular Schwannoma is a benign brain tumour that grows from one of the balance nerves. Patients may be treated by surgery, radiosurgery or with a conservative ”wait-and-scan” strategy. Clinicians typically use manually extracted linear measurements to aid clinical decision making. This work aims to automate and improve this process by using deep learning based segmentation to extract relevant clinical features through computational algorithms. To the best of our knowledge, our study is the first to propose an automated approach to replicate local clinical guidelines. Our deep learning based segmentation provided Dice-scores of 0.8124 ± 0.2343 and 0.8969 ± 0.0521 for extrameatal and whole tumour regions respectively for T2 weighted MRI, whereas 0.8222 ± 0.2108 and 0.9049 ± 0.0646 were obtained for T1 weighted MRI. We propose a novel algorithm to choose and extract the most appropriate maximum linear measurement from the segmented regions based on the size of the extrameatal portion of the tumour. Using this tool, clinicians will be provided with a visual guide and related metrics relating to tumour progression that will function as a clinical decision aid. In this study, we utilize 187 scans obtained from 50 patients referred to a tertiary specialist neurosurgical service in the United Kingdom. The measurements extracted manually by an expert neuroradiologist indicated a significant correlation with the automated measurements (p < 0.0001). Our code is publicly available at https: //github.com/navodini/AutomatedReportGenerationVS.
We present a novel pipeline for robust optical analysis of fresh human brain tissue. We capture fluorescence signal and characterize optical properties with high sensitivity and high spectral resolution. These in turn allow for quantitative analysis of protoporphyrin IX (PpIX) accumulation in various types of tumor tissue. Our ex vivo protocol for tissue handling was designed to promote high-fidelity replication of in vivo conditions. The on-going consolidation of a fresh ex vivo quantitative dataset from a cohort of 20 patients plus a control cohort lays foundation for the development of imaging devices for intraoperative fluorescence guided resection.
Three major one layer tissue models (Modified Beer-Lambert,1 Jacques 1999,2 Pilon 20093) are compared to Monte Carlo simulated diffuse reflectance spectra and measured tissue phantom spectra with known ground truth. These ground truth values were obtained using inverse adding doubling and absorbance measurements and validated using a phantom with known ground truth (BioPixs). Finally, a two layer model (Pilon 2009) was evaluated against Monte Carlo simulations and used to analyse skin reflectance data (NIST4). These models were compared on goodness of fit and parameter extraction accuracy. It was found that the Pilon 2009 one layer model performed best against Monte Carlo simulations and phantom measurements, however the Pilon 2009 two layer model had significant regions of inaccuracy. These inaccurate regions correspond to circumstances where the epidermal layer has significant thickness and melanin content, while the dermal layer has low fraction of blood meaning that the haemoglobin impact is “masked”. The extraction of parameters from the NIST skin dataset using this model returns values that do not correspond well to literature values suggesting that many of these spectra lie within an inaccurate region or indicates oversimplification of the tissue modelling. This suggests both Pilon 2009 and Jacques 1999 are suitable for modelling tissue that can be approximated as a single, homogeneous, semi-infinite slab, however the Pilon 2009 two layer model is not yet effective when encountering empirical data.
PurposeHyperspectral imaging shows promise for surgical applications to non-invasively provide spatially resolved, spectral information. For calibration purposes, a white reference image of a highly reflective Lambertian surface should be obtained under the same imaging conditions. Standard white references are not sterilizable and so are unsuitable for surgical environments. We demonstrate the necessity for in situ white references and address this by proposing a novel, sterile, synthetic reference construction algorithm.ApproachThe use of references obtained at different distances and lighting conditions to the subject were examined. Spectral and color reconstructions were compared with standard measurements qualitatively and quantitatively, using ΔE and normalized RMSE, respectively. The algorithm forms a composite image from a video of a standard sterile ruler, whose imperfect reflectivity is compensated for. The reference is modeled as the product of independent spatial and spectral components, and a scalar factor accounting for gain, exposure, and light intensity. Evaluation of synthetic references against ideal but non-sterile references is performed using the same metrics alongside pixel-by-pixel errors. Finally, intraoperative integration is assessed though cadaveric experiments.ResultsImproper white balancing leads to increases in all quantitative and qualitative errors. Synthetic references achieve median pixel-by-pixel errors lower than 6.5% and produce similar reconstructions and errors to an ideal reference. The algorithm integrated well into surgical workflow, achieving median pixel-by-pixel errors of 4.77% while maintaining good spectral and color reconstruction.ConclusionsWe demonstrate the importance of in situ white referencing and present a novel synthetic referencing algorithm. This algorithm is suitable for surgery while maintaining the quality of classical data reconstruction.
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.