Multi-class Cervical Cancer Classification using Transfer Learning-based Optimized SE-ResNet152 model in Pap Smear Whole Slide Images

Among the main factors contributing to death globally is cervical cancer, regardless of whether it can be avoided and treated if the afflicted tissues are removed early. Cervical screening programs must be made accessible to everyone and effectively, which is a difficult task that necessitates, among other things, identifying the population's most vulnerable members. Therefore, we present an effective deep-learning method for classifying the multi-class cervical cancer disease using Pap smear images in this research. The transfer learning-based optimized SE-ResNet152 model is used for effective multi-class Pap smear image classification. The reliable significant image features are accurately extracted by the proposed network model. The network's hyper-parameters are optimized using the Deer Hunting Optimization (DHO) algorithm. Five SIPaKMeD dataset categories and six CRIC dataset categories constitute the 11 classes for cervical cancer diseases. A Pap smear image dataset with 8838 images and various class distributions is used to evaluate the proposed method. The introduction of the cost-sensitive loss function throughout the classifier's learning process rectifies the dataset's imbalance. When compared to prior existing approaches on multi-class Pap smear image classification, 99.68% accuracy, 98.82% precision, 97.86% recall, and 98.64% F1-Score are achieved by the proposed method on the test set. For automated preliminary diagnosis of cervical cancer diseases, the proposed method produces better identification results in hospitals and cervical cancer clinics due to the positive classification results.