Explainable Contrastive and Cost-Sensitive Learning for Cervical Cancer Classification
This work addresses cervical cancer diagnosis, a critical medical domain, but is incremental as it combines existing methods like fine-tuning, cost-sensitive learning, and contrastive learning without introducing a fundamentally new approach.
The paper tackled cervical cancer cell classification by fine-tuning pre-trained CNNs with cost-sensitive learning and contrastive learning, achieving 97.29% accuracy on the SIPaKMeD dataset and incorporating explainable AI techniques for interpretability.
This paper proposes an efficient system for classifying cervical cancer cells using pre-trained convolutional neural networks (CNNs). We first fine-tune five pre-trained CNNs and minimize the overall cost of misclassification by prioritizing accuracy for certain classes that have higher associated costs or importance. To further enhance the performance of the models, supervised contrastive learning is included to make the models more adept at capturing important features and patterns. Extensive experimentation are conducted to evaluate the proposed system on the SIPaKMeD dataset. The experimental results demonstrate the effectiveness of the developed system, achieving an accuracy of 97.29%. To make our system more trustworthy, we have employed several explainable AI techniques to interpret how the models reached a specific decision. The implementation of the system can be found at - https://github.com/isha-67/CervicalCancerStudy.