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.
We present a machine learning method for the detection and staging of cervical dysplasia tissue using a convolutional neural network (CNN)-based architecture. Depth-resolved angular scattering measurements collected from two clinical trials consisting of 6660 and 1600 depth scans were used as training and validation sets separately. Our results demonstrated high sensitivity and specificity for classifying cervical dysplasia at a hundredfold faster processing time compared with the traditional Mie-theory inverse light scattering analysis (ILSA) method, offering a promising approach for a/LCI in the clinic for assessing cervical dysplasia.
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.
The alert did not successfully save. Please try again later.
Haoran Zhang, Wesley Y. Kendall, Evan T. Jelly, Adam Wax, "Detection of cervical dysplasia from depth-resolved light scattering profiles using deep learning," Proc. SPIE 11657, Biomedical Applications of Light Scattering XI, 116570I (5 March 2021); https://doi.org/10.1117/12.2579912