Spectroscopic photoacoustic (sPA) imaging can be used to map blood oxygen saturation (sO2) within tissue. Its accuracy, however, is degraded deep in tissue by wavelength-dependent optical attenuation. We have developed a convolutional neural network to simultaneously estimate the sO2 and segment blood vessels from sPA data. The network was trained on Monte Carlo simulated sPA data and predicted sO2 with 9.31% median pixel error. The network was then retrained on experimental photoacoustic images of cow blood with median prediction error of 4.38%. These results suggest that precise quantitative measurements of sO2 deep in tissue are attainable using machine learning approaches.
Using spectroscopic photoacoustic imaging to quantitatively measure blood oxygenation saturation (sO2) is a difficult problem which requires prior tissue knowledge and costly computational methods. We have developed a convolutional neural network with a U-Net architecture to estimate the sO2 from spectroscopic photoacoustic data. The network was trained on Monte Carlo simulated spectroscopic PA data and predicted sO2 with only 4.49% error, an accuracy much higher than that of a linear spectral unmixing baseline. These results suggest that precise quantitative measurements of sO2 deep in tissue is attainable using machine learning approaches.
Photodynamic therapy is a promising alternative treatment modality that uses a photosensitizer to kill cancer cells through oxidative damage. However, many tumors contain regions of hypoxia, limiting the overall effectiveness of the technique. Therefore, an image-guided approach to improve tumor oxygenation during photodynamic therapy could result in better, more-reliable outcomes.
We have developed nanoparticles that act as ultrasound/photoacoustic imaging contrast agents while also delivering oxygen to these hypoxic tumor sites. The particles contain a perfluorocarbon (PFC) core which, when vaporized, creates an acoustic impedance difference between the particles and surround tissues, allowing the particles to be visualized with ultrasound imaging. In addition to its contrast enhancement, the PFC core is also a great carrier of oxygen, capable of delivering the payload to tumors. Hydrophobically modified indocyanine green dye (IGC) is added as the photosensitizer to absorb the optical energy from the nanosecond pulsed laser that is used to activate the particles and nucleate vaporization. Upon activation of the particles, a bolus of oxygen is released into the surrounding tissue. The release of oxygen can be quantified by imaging the tumor with spectroscopic photoacoustic imaging in real time. Finally, the encapsulated ICG dye can be leveraged to act as a photosensitizer for photodynamic therapy. Experiments show that physiologically relevant payloads of oxygen can be released from the particles on demand. Furthermore, we are able to visualize the vaporized particles with single-particle sensitivity. These results pave the way for improved image-guided photodynamic therapy.
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.