Cervical cancer classification based on a bilinear convolutional neural network approach and random projection

Abstract

Cervical cancer (CC) is one of the most prevalent malignancies affecting women globally, with a particularly notable impact and high mortality in regions with limited economic resources. This underscores the imperative for the expeditious development of techniques that facilitate timely and precise detection, thereby augmenting treatment efficacy, enhancing survival rates, and mitigating the burden of healthcare expenditure. The intricacies of cervical cancer detection are inherently aligned with the challenges of fine-grained visual classification. This study focuses on the integration of bilinear pooling within convolutional neural networks (CNNs) and addresses the problem of the computational complexity of bilinear features with the fortification of the bilinear CNN with a random projection paradigm (RP-BCNN). The aim is the simultaneous achievement of improved classification precision and streamlined processing temporalities. The proposed methodology entails the introduction of a dyadic feature extraction protocol in which the input cellular image is subjected to twin feature extraction modalities. The feature maps obtained from this process undergo element-wise multiplication via an outer-product operation, thereby engendering composite feature representations. Subsequently, a judiciously designed random projection procedure is invoked to reduce dimensionality, yielding a more succinct yet informative image descriptor. Empirical evaluations of the introduced model predicted on the RP-BCNN framework yielded commendable outcomes. Notably, an accuracy of 0.9983 was achieved for the dual-label classification scenarios, and an accuracy of 0.9530 was realized in the context of multiclass classification encompassing seven distinct labels. The proposed model achieves an optimal equilibrium between classification accuracy and processing efficiency, thus constituting a potent instrument for the classification of cervical cancer. Further, it holds promise for the refinement of diagnostic accuracy, thereby providing a vantage point for embracing sophisticated techniques in the realm of medical image analysis.