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.
SPIE publishes accepted journal articles as soon as they are approved for publication. Journal issues are considered In Progress until all articles for an issue have been published. Articles published ahead of the completed issue are fully citable.
Cerebral oximeters have the potential to detect abnormal cerebral blood oxygenation to allow for early intervention. However, current commercial systems have two major limitations: (1) spatial coverage of only the frontal region, assuming that surgery-related hemodynamic effects are global and (2) susceptibility to extracerebral signal contamination inherent to continuous-wave near-infrared spectroscopy (NIRS).
Aim
This work aimed to assess the feasibility of a high-density, time-resolved (tr) NIRS device (Kernel Flow) to monitor regional oxygenation changes across the cerebral cortex during surgery.
Approach
The Flow system was assessed using two protocols. First, digital carotid compression was applied to healthy volunteers to cause a rapid oxygenation decrease across the ipsilateral hemisphere without affecting the contralateral side. Next, the system was used on patients undergoing shoulder surgery to provide continuous monitoring of cerebral oxygenation. In both protocols, the improved depth sensitivity of trNIRS was investigated by applying moment analysis. A dynamic wavelet filtering approach was also developed to remove observed temperature-induced signal drifts.
Results
In the first protocol (28±5 years; five females, five males), hair significantly impacted regional sensitivity; however, the enhanced depth sensitivity of trNIRS was able to separate brain and scalp responses in the frontal region. Regional sensitivity was improved in the clinical study given the age-related reduction in hair density of the patients (65±15 years; 14 females, 13 males). In five patients who received phenylephrine to treat hypotension, different scalp and brain oxygenation responses were apparent, although no regional differences were observed.
Conclusions
The Kernel Flow has promise as an intraoperative neuromonitoring device. Although regional sensitivity was affected by hair color and density, enhanced depth sensitivity of trNIRS was able to resolve differences in scalp and brain oxygenation responses in both protocols.
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.
Photoacoustic imaging (PAI) promises to measure spatially resolved blood oxygen saturation but suffers from a lack of accurate and robust spectral unmixing methods to deliver on this promise. Accurate blood oxygenation estimation could have important clinical applications from cancer detection to quantifying inflammation.
Aim
We address the inflexibility of existing data-driven methods for estimating blood oxygenation in PAI by introducing a recurrent neural network architecture.
Approach
We created 25 simulated training dataset variations to assess neural network performance. We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen–Shannon divergence to predict the most suitable training dataset.
Results
The network architecture can flexibly handle the input wavelengths and outperforms linear unmixing and the previously proposed learned spectral decoloring method. Small changes in the training data significantly affect the accuracy of our method, but we find that the Jensen–Shannon divergence correlates with the estimation error and is thus suitable for predicting the most appropriate training datasets for any given application.
Conclusions
A flexible data-driven network architecture combined with the Jensen–Shannon divergence to predict the best training data set provides a promising direction that might enable robust data-driven photoacoustic oximetry for clinical use cases.
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.