AGGRNet: Selective Feature Extraction and Aggregation for Enhanced Medical Image Classification

TL;DR

AGGRNet introduces a novel feature extraction and aggregation framework that enhances medical image classification by effectively capturing fine-grained visual patterns, leading to improved accuracy on challenging datasets.

Contribution

The paper proposes AGGRNet, a new architecture that selectively extracts and aggregates features to better distinguish subtle differences in medical images.

Findings

Achieves up to 5% improvement over state-of-the-art models on Kvasir dataset.

Effectively captures inter-class similarity and intra-class variability.

Outperforms existing attention-based models in medical image classification.

Abstract

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.