Diffuse Optical Tomography (DOT) is a promising non-invasive optical imaging technology that can provide structural and functional information of biological tissues. Since the diffused light undergoes multiple scattering in biological tissues, and the boundary measurements are limited, the reverse problem of DOT is ill-posed and ill-conditioned. In order to overcome these limitations, two types of neural networks, back-propagation neural network (BPNN) and stacked autoencoder (SAE) were applied in DOT image reconstruction, which use the internal optical properties distribution and the boundary measurement of biological tissues as the input and output data sets respectively to adjust the neural network parameters, and directly establish a nonlinear mapping of the input and output. To verify the effectiveness of the methods, a series of numerical simulation experiments were conducted, and the experimental results were quantitatively assessed, which demonstrated that both methods can accurately predict the position and size of the inclusion, especially in the case of higher absorption contrast. As a whole, SAE can get better reconstructed image results than BPNN and the training time was only a quarter of BPNN.
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.