Block-Fused Attention-Driven Adaptively-Pooled ResNet Model for Improved Cervical Cancer Classification
This work addresses the problem of limited performance in CAD systems for cervical cancer classification, which is critical for women's health, and while it introduces new components, it builds on existing ResNet architectures, making it somewhat incremental.
The paper tackled cervical cancer classification by proposing a novel CAD system that integrates dual-level feature extraction, attention modules, and adaptive pooling, achieving 98.63% accuracy on the IARC dataset and 93.39% on AnnoCerv, with a 14.55% improvement over prior methods on IARC.
Cervical cancer is the second most common cancer among women and a leading cause of mortality. Many attempts have been made to develop an effective Computer Aided Diagnosis (CAD) system; however, their performance remains limited. Using pretrained ResNet-50/101/152, we propose a novel CAD system that significantly outperforms prior approaches. Our novel model has three key components. First, we extract detailed features (color, edges, and texture) from early convolution blocks and the abstract features (shapes and objects) from later blocks, as both are equally important. This dual-level feature extraction is a new paradigm in cancer classification. Second, a non-parametric 3D attention module is uniquely embedded within each block for feature enhancement. Third, we design a theoretically motivated innovative adaptive pooling strategy for feature selection that applies Global Max Pooling to detailed features and Global Average Pooling to abstract features. These components form our Proposed Block-Fused Attention-Driven Adaptively-Pooled ResNet (BF-AD-AP-ResNet) model. To further strengthen learning, we introduce a Tri-Stream model, which unifies the enhanced features from three BF-AD-AP-ResNets. An SVM classifier is employed for final classification. We evaluate our models on two public datasets, IARC and AnnoCerv. On IARC, the base ResNets achieve an average performance of 90.91%, while our model achieves an excellent performance of 98.63%. On AnnoCerv, the base ResNets reach to 87.68%, and our model improves this significantly, reaching 93.39%. Our approach outperforms the best existing method on IARC by an average of 14.55%. For AnnoCerv, no prior competitive works are available. Additionally, we introduce a novel SHAP+LIME explainability method, accurately identifying the cancerous region in 97% of cases, ensuring model reliability for real-world use.