Light scattering pattern specific convolutional network static cytometry for label‐free classification of cervical cells

Cervical cancer is a major gynecological malignant tumor that threatens women's health. Current cytological methods have certain limitations for cervical early screening. Light scattering patterns can reflect small differences in the internal structure of cells. In this study, we develop light pattern specific convolutional network (LSPS-net) based on deep learning algorithm and integrate it into 2D static cytometry automatic, label-free analysis single An accuracy rate 95.46% classification normal cells cancerous ones (mixed C-33A CaSki cells) obtained. When applied subtyping cell lines, obtain an 93.31% with our LSPS-net cytometric technique. Furthermore, three-way above different types has overall 90.90%, comparisons other feature descriptors algorithms show superiority automatic extraction. The may potentially be used screening, which rapid, label-free.