* If you want to update the article please login/register
Cervical dysplasia is a cancerous disease, and it is vital to correctly distinguish them from Pap smear images using machine intelligence. However, the laboratory analysis of Papanicolaou's test under microscope is a lengthy, subjective, and time-consuming process. The novel filter to feature map approach is used in the cell segmentation stage. From each original cell image, total 112 filtered photos were created. Using filtered images, the feature vector was then created for every original pixel. The 163 features including the edge detector, texture, noise, membrane detector, and color measurements are considered in the Dysplasia cancer classification process. The RF reported accuracy of 99. 07% on cell segmentation analysis, surpassing ANN and SVM classifiers in terms of accuracy. Eventually, the cervical dysplasia is precisely diagnosed with 97. 5% precision using ANN as compared to SVM and RF.
Source link: https://doi.org/10.1007/s00371-022-02463-9
* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions