We proposed a method for automatic detection of cervical cancer cells in images captured from thin liquid based cytology slides.\nWe selected 20,000 cells in images derived from 120 different thin liquid based cytology slides, which include 5000 epithelial cells\n(normal 2500, abnormal 2500), lymphoid cells, neutrophils, and junk cells.We first proposed 28 features, including 20 morphologic\nfeatures and 8 texture features, based on the characteristics of each cell type.We then used a two-level cascade integration system\nof two classifiers to classify the cervical cells into normal and abnormal epithelial cells. The results showed that the recognition\nrates for abnormal cervical epithelial cells were 92.7% and 93.2%, respectively, when C4.5 classifier or LR (LR: logical regression)\nclassifier was used individually; while the recognition rate was significantly higher (95.642%) when our two-level cascade integrated\nclassifier system was used.The false negative rate and false positive rate (both 1.44%) of the proposed automatic two-level cascade\nclassification system are also much lower than those of traditional Pap smear review.
Loading....