Mr-ResNeXt: A Multi-resolution Network Architecture for Detection of Obstructive Sleep Apnea

Qiren Chen, Huijun Yue, Xiongwen Pang, Wenbin Lei, Gansen Zhao, Enhong Liao, Yongquan Wang

Abstract: Obstructive sleep apnea (OSA) is the most common sleep related breathing disorder causing sleepiness and several chronic medical conditions, for which the gold-standard diagnostic test is polysomnography (PSG), however the analysis of PSG is a time-consuming and labor-intensive procedure. To address these issues, we use deep learning as a new method to detect sleep respiratory events which can provide effective and accurate OSA diagnosis. We present a network named Mr-ResNeXt improved from ResNeXt, in which the 3 × 3 filters was replaced by a new block containing multi-level group convolution. The first level group convolution is used to exchange information between groups and the second level group convolution contains filters of different sizes which are used to extract features of different resolutions. All group convolutions involve residual-like connections. All the above changes help to extract multi-resolution image features more easily. Firstly, the experimental results show that our network can achieve a nearly 3% improvement (from 91.02% to 94.23%) comparing with the excellent networks in this field. Secondly, our network achieves nearly 1% accuracy improvement while comparing with ResNet and ResNetXt. Thus, we confirm that our method can improve the efficiency of detecting respiratory events.