Block-Fused Attention-Driven Adaptively-Pooled ResNet Model for Improved Cervical Cancer Classification

TL;DR

This paper introduces a novel ResNet-based CAD system with dual-level feature extraction, attention modules, and adaptive pooling, significantly improving cervical cancer classification accuracy and explainability on public datasets.

Contribution

The paper proposes a new multi-component ResNet model with dual-level features, attention, and adaptive pooling, plus a Tri-Stream ensemble and explainability methods, advancing cervical cancer diagnosis technology.

Findings

Achieved 98.63% accuracy on IARC dataset.

Outperformed existing methods by 14.55% on IARC.

Accurately identified cancer regions in 97% of cases with explainability methods.

Abstract

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.