FUSECAPS: Investigating Feature Fusion Based Framework for Capsule Endoscopy Image Classification

TL;DR

This paper introduces FUSECAPS, a hybrid feature fusion framework combining CNNs, MLPs, and radiomics for improved capsule endoscopy image classification, achieving higher accuracy and generalization.

Contribution

It proposes a novel hybrid feature extraction method that integrates deep and handcrafted features for better endoscopic image classification.

Findings

Validation accuracy of 76.2% on capsule endoscopy frames

Enhanced model generalization and accuracy

Effective handling of class imbalance issues

Abstract

In order to improve model accuracy, generalization, and class imbalance issues, this work offers a strong methodology for classifying endoscopic images. We suggest a hybrid feature extraction method that combines convolutional neural networks (CNNs), multi-layer perceptrons (MLPs), and radiomics. Rich, multi-scale feature extraction is made possible by this combination, which captures both deep and handmade representations. These features are then used by a classification head to classify diseases, producing a model with higher generalization and accuracy. In this framework we have achieved a validation accuracy of 76.2% in the capsule endoscopy video frame classification task.