In recent years, the use of convolutional neural networks has been rapidly increasing in computer vision related tasks, thanks to its versatility and flexibility in its ability to be trained with large swaths of data. In the biomedical field, neural networks have great potential to streamline and perform tasks on the level of human ability without the drawbacks of human error potentially tainting the results. This study evaluates the efficiency and accuracy of a trained neural network in segmenting the trachea of rats before and after exposure to methyl isocyanate (MIC) and a drug candidate, nitro-oleic acid (NO2OA) . The images of the trachea were gathered using optical coherence tomography. The neural network was modeled after the U-net convolutional network model for biomedical image segmentation. Accuracy was evaluated by taking cross-sectional areas of the trachea and using the Sørensen-Dice similarity coefficient comparing the neural network’s prediction of segmentation to manual segmentation of the trachea. The trained neural network showed an accuracy similar, but not perfect, to human analysis of the trachea.
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.