U-SEANNet: A Simple, Efficient and Applied U-Shaped Network for Diagnosis of Nasal Diseases on Nasal Endoscopic Images

TL;DR

U-SEANNet is a novel, lightweight U-shaped neural network that, combined with a large-scale nasal endoscopy dataset, achieves high accuracy in diagnosing nasal diseases efficiently, suitable for real-world applications.

Contribution

The paper introduces U-SEANNet, a new efficient U-shaped network architecture with a large nasal endoscopy dataset, advancing nasal disease diagnosis in endoscopic images.

Findings

Achieved 93.58% accuracy on nasal disease diagnosis

Model parameters are only 0.78M, GFLOPs 0.21

Outperforms seventeen modern architectures in benchmarks

Abstract

Numerous studies have affirmed that deep learning models can facilitate early diagnosis of lesions in endoscopic images. However, the lack of available datasets stymies advancements in research on nasal endoscopy, and existing models fail to strike a good trade-off between model diagnosis performance, model complexity and parameters size, rendering them unsuitable for real-world application. To bridge these gaps, we created the first large-scale nasal endoscopy dataset, named 7-NasalEID, comprising 11,352 images that contain six common nasal diseases and normal samples. Subsequently, we proposed U-SEANNet, an innovative U-shaped architecture, underpinned by depth-wise separable convolution. Moreover, to enhance its capacity for detecting nuanced discrepancies in input images, U-SEANNet employs the Global-Local Channel Feature Fusion module, enabling it to utilize salient channel features from both global and local contexts. To demonstrate U-SEANNet's potential, we benchmarked U-SEANNet against seventeen modern architectures through five-fold cross-validation. The experimental results show that U-SEANNet achieves a commendable accuracy of 93.58%. Notably, U-SEANNet's parameters size and GFLOPs are only 0.78M and 0.21, respectively. Our findings suggest U-SEANNet is the state-of-the-art model for nasal diseases diagnosis in endoscopic images.