iDDCS: Cervical intraepithelial neoplasia severity detection during vagina birth using artificial intelligence approach

Abstract

To diagnose cervical cancer, this paper uses patient Pap tests to look for abnormal tissue growth in the cervix region of pregnant women. By undergoing routine tests to identify any precancers and treating them, cervical cancer can be avoided. The Pap test scans the cells at the cervix for any unusual or dysplasia-related alterations. However, the traditional manual examination of Pap smears under the microscope is vulnerable to error. To effectively categorize the cervical cells, a brand-new framework built on powerful features Support vector machines using convolutional neural network (SVM) models are proposed in this paper. The performance of the algorithms was assessed based on various evaluation metrics, including accuracy, sensitivity, specificity, false positive rate, false negative rate, positive predictive value, F score, error rate, and training time. Among the three CNN algorithms tested, Faster R-CNN achieved an accuracy of 93.7%, SSD reached 95.9%, and YOLOv8 had the highest accuracy at 96.6% for image detection. For the SVM algorithm’s classification and detection capabilities, the average accuracy rates for CIN1, CIN2, and CIN3 were 90%, 89%, and 81%, respectively, as per the evaluation dataset. The results suggested that the CNN-SVM model with robust features might be used to categorize CIN cells for CIN-C detection in the early stages. This novel method is the most effective among other unsupervised methods for CIN-C diagnosis. We recommend a revolutionary approach that combines NLP technology with iDDCS for CIN detection. Another goal of this research is to use NLP algorithms to extract relevant information from medical records, pathology reports, and clinical patient statistics. Another goal of this research is to use NLP algorithms to extract relevant information from medical records, pathology reports, and clinical patient statistics.

Ähnliche Arbeiten