Video Capsule Endoscopy Classification using Focal Modulation Guided Convolutional Neural Network

TL;DR

This paper introduces FocalConvNet, a novel deep learning model combining focal modulation and lightweight convolutional layers for efficient and accurate classification of anomalies in video capsule endoscopy, demonstrating superior performance and real-time capability.

Contribution

FocalConvNet integrates focal modulation with lightweight convolutional layers to enhance global context understanding and hierarchical feature extraction for endoscopy image classification.

Findings

Achieves higher weighted F1-score, recall, and MCC than state-of-the-art methods.

Reports the highest throughput of 148.02 images/second for real-time application.

Outperforms existing models on the large-scale Kvasir-Capsule dataset.

Abstract

Video capsule endoscopy is a hot topic in computer vision and medicine. Deep learning can have a positive impact on the future of video capsule endoscopy technology. It can improve the anomaly detection rate, reduce physicians' time for screening, and aid in real-world clinical analysis. CADx classification system for video capsule endoscopy has shown a great promise for further improvement. For example, detection of cancerous polyp and bleeding can lead to swift medical response and improve the survival rate of the patients. To this end, an automated CADx system must have high throughput and decent accuracy. In this paper, we propose FocalConvNet, a focal modulation network integrated with lightweight convolutional layers for the classification of small bowel anatomical landmarks and luminal findings. FocalConvNet leverages focal modulation to attain global context and allows global-local spatial interactions throughout the forward pass. Moreover, the convolutional block with its intrinsic inductive/learning bias and capacity to extract hierarchical features allows our FocalConvNet to achieve favourable results with high throughput. We compare our FocalConvNet with other SOTA on Kvasir-Capsule, a large-scale VCE dataset with 44,228 frames with 13 classes of different anomalies. Our proposed method achieves the weighted F1-score, recall and MCC} of 0.6734, 0.6373 and 0.2974, respectively outperforming other SOTA methodologies. Furthermore, we report the highest throughput of 148.02 images/second rate to establish the potential of FocalConvNet in a real-time clinical environment. The code of the proposed FocalConvNet is available at https://github.com/NoviceMAn-prog/FocalConvNet.