Automatic Sleep Stage Classification Using Deep Learning Algorithm for Multi-Institutional Database

Abstract

Recent deep learning studies for sleep stage classification with polysomnography (PSG) data show two directions, either using 1-dimensional (1-D) raw PSG data or spectrogram images time-frequency domain. We propose a novel approach using images generated from time-signal display of a PSG dataset for 5 class sleep stage classification. The motivation of our approach is not only to imitate the way used by human sleep-scoring experts but also to make use of various methods developed in image classification in Deep Learning, such as augmentation techniques, EfficientNet and LSTM. In addition an explainable AI technique such as Class Activation Map (CAM) can be employed for interpreting how a model makes a decision. We, also, work on ''inconsistency'' problems occurring among multiple institutions/hospitals where different capturing sensors are used and the labelling mismatch by human experts in different organizations. To solve the problem, we experiment three different approaches in the network design with data of two institutes and 5 sleep stage classification; (i) 5 class classification, (ii) 10-class classification and then post-processing to 5 classes (iii) 10-to-5 class classification. The 10-to-5 class classification is a network where information of two institutes are embedded inside the network. When information of multi institution is inside the network, the results show higher performance. Our experimental results show that all of three proposed methods based on time-signal images achieves higher accuracy performance compared to state-of-the-art models. INDEX TERMSDeep learning, image classification, sleep, rapid eye movement sleep. DONGYOUNG KIM received the B.E. and M.E. degrees in computer engineering from Hallym University, in 2019 and 2021, respectively, where he is currently pursuing the Ph.D. degree with the Department of Computer Engineering. His research interests include deep learning for medical applications and deep learning based domain adaption for multi-institutional dataset. JAEMIN JEONG received the B.E. and M.E. degrees in computer engineering from Hallym University, in 2019 and 2021, respectively, where he is currently pursuing the Ph.D. degree with the Department of Computer Engineering. He is also a Software Engineer with Mirroroid, where he develops deep learning models for hair and head segmentation. His research interests include deep learning based vision (GAN, segmentation, and object detection) and deep learning model compression for edge computing.

Reviewing CAM-Based Deep Explainable Methods in Healthcare

“…Figure 7. The accuracy of each study[16][17][18][20][21][22][23][24][25][26][27][28][29][30][31][32][33][35][36][37][38][39][40][41][42][43]45,47,48,[50][51][52][53][54][55][56]58,59]. …”