AGGRNet: Selective Feature Extraction and Aggregation for Enhanced Medical Image Classification
This work addresses the problem of incorrect diagnosis in medical imaging for clinicians by improving classification accuracy for complex tasks like severity grading and disease subtype classification, representing an incremental advancement over existing attention-based models.
The paper tackles the challenge of distinguishing subtle classes in medical image classification by proposing AGGRNet, which extracts and aggregates informative and non-informative features, achieving up to a 5% improvement over state-of-the-art models on the Kvasir dataset.
Medical image analysis for complex tasks such as severity grading and disease subtype classification poses significant challenges due to intricate and similar visual patterns among classes, scarcity of labeled data, and variability in expert interpretations. Despite the usefulness of existing attention-based models in capturing complex visual patterns for medical image classification, underlying architectures often face challenges in effectively distinguishing subtle classes since they struggle to capture inter-class similarity and intra-class variability, resulting in incorrect diagnosis. To address this, we propose AGGRNet framework to extract informative and non-informative features to effectively understand fine-grained visual patterns and improve classification for complex medical image analysis tasks. Experimental results show that our model achieves state-of-the-art performance on various medical imaging datasets, with the best improvement up to 5% over SOTA models on the Kvasir dataset.