Optimized Transfer Learning With Hybrid Feature Extraction for Uterine Tissue Classification Using Histopathological Images

Abstract

Endometrial cancer, termed uterine cancer, seriously affects female reproductive organs, and the analysis of histopathological images formed a golden standard for diagnosing this cancer. Sometimes, early detection of this disease is difficult because of the limited capability of modeling complicated relationships among histopathological images and their interpretations. Moreover, many previous methods do not effectively handle the cell appearance variations. Hence, this study develops a novel classification technique called transfer learning convolution neural network with artificial bald eagle optimization (TL-CNN with ABEO) for the classification of uterine tissue. Here, preprocessing is done by the median filter, followed by image enhancement by the multiple identities representation network (MIRNet). Moreover, pelican crow search optimization (PCSO) is used for adapting weights in MIRNet, where PCSO is generated by combining the crow search algorithm (CSA) and pelican optimization algorithm (POA). Then, segmentation quality assessment (SQA) helps in tissue segmentation, and deep convolutional neural network (DCNN) helps in parameter selection that is trained by fractional PCSO (FPCSO). Furthermore, feature extraction is done and, finally, cell classification is done by TL with CNN, which is trained by the proposed ABEO algorithm. Here, ABEO is newly developed by the integration of the bald eagle search (BES) algorithm and artificial hummingbird algorithm (AHA). Furthermore, ABEO + TL-CNN achieved a high accuracy of 89.59%, a sensitivity of 90.25%, and a specificity of 89.89% by utilizing the cancer image archive dataset.