Analysis of Digital Noise And Reduction Methods On Classifiers Used In Automated Visual Evaluation In Cervical Cancer Screening.
Xue Z, Angara S, Levitz D, Antani S
Proceedings of SPIE Photonics West 2022.
Abstract:
Cervical cancer disproportionately hurts underserved women from disadvantaged communities. Automated visual evaluation (AVE), which analyzes white light cervical images using machine learning, is being considered for management of screen-positive patients. Gaussian noise was identified as degrading AVE performance. Two noise correction approaches were tested on images from historic data with added Gaussian noise. One denoising method (VDNet) was based on neural networks; the other used conventional Gaussian blur filtering. Images were evaluated by an object detection network (RetinaNet), and by a binary pathology ResNeSt classifier. VDNet filtering limited AVE performance degradation at higher noise levels, while Guassian blur only worked on low noise levels.
Xue Z, Angara S, Levitz D, Antani S. Analysis of Digital Noise And Reduction Methods On Classifiers Used In Automated Visual Evaluation In Cervical Cancer Screening.
Proceedings of SPIE Photonics West 2022.