Ischemic stroke volume is a strong predictor of functional outcome and may play a role in decision making of reperfusion therapy in the late time window (< 6hr of stroke onset to MRI time) when it is obtained along with penumbra volume. Automatic diffusion lesion segmentation can be performed using a commercial software package and is typically based on a fixed apparent diffusion coefficient (ADC) threshold. ADC values alone may not be guaranteed to be highly accurate in the identification of diffusion lesions. Deep learning has the potential to improve the accuracy of diffusion lesion segmentation, provided that a large set of correctly labeled lesion mask data is used for training. The purpose of this study is to evaluate deep learning-based segmentation methods and compare them with three fixed ADC threshold-based methods. U-net was adopted to train a segmentation model. Two U-net models were developed: a model “U-net (DWI+ADC)” trained from DWI and ADC data, and a model “U-net (DWI)” trained from DWI data only. 296 subjects were used for training, and 134 subjects were used for testing. An expert neurologist manually delineated infarct masks on DWI, which served as ground-truth reference. Lesion volume measurements from the two U-net methods and three fixed ADC threshold-based methods were compared against lesion volume measurements from manual segmentation. In testing, the “U-net (DWI+ADC)” method outperformed other methods in lesion volume measurement, with the smallest root-mean-square error of 2.96 ml and the highest Pearson correlation coefficient of 0.997. The proposed method has the potential to automatically measure diffusion lesion volume in a fast and accurate manner, in patients with acute ischemic stroke.
KEYWORDS: Real time imaging, Brain mapping, Neuroimaging, Hemodynamics, Monte Carlo methods, Near infrared spectroscopy, Photon transport, Brain, Oxygen, Tissues
Accurate and efficient reconstruction of hemodynamic changes is an important step towards the implementation of NIRS as an enhanced clinical tool for understanding oxygenation changes at various depths within the brain. Depth information could provide insight on how oxygen transported to the tissue. For this work, we ran Monte Carlo simulations to develop sensitivity profiles for various source-detector separations. The source-detector separations were based on our custom built 108 channel NIRS probe and consisted of separations of 15 mm, 30 mm, 36 mm, and 45 mm. We used the mesh-based Monte Carlo program MMCLAB (Fang et al. 2010) to acquire the sensitivity profiles. The sensitivity profiles consisted of a tetrahedral mesh which was converted to a regular grid in three-dimensional space. Then, the structural tensor was calculated for each voxel and the Hamilton-Jacobi equation was solved anisotropically for the tensor volume. As the result, the distance map was in same space as the calculated tensor volume. Using this distance map, we modeled the probabilistic path of photons. We then weighted the hemodynamic changes acquired by our NIRS probe according to the probabilistic path to reconstruct hemodynamic changes in the prefrontal area of the brain.
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.