1
|
Fu Z, Zhu H, Zhang Y, Huan R, Chen S, Pan Y. A Spatiotemporal Deep Learning Framework for Scalp EEG-Based Automated Pain Assessment in Children. IEEE Trans Biomed Eng 2024; 71:1889-1900. [PMID: 38231823 DOI: 10.1109/tbme.2024.3355215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/19/2024]
Abstract
OBJECTIVE Common pain assessment approaches such as self-evaluation and observation scales are inappropriate for children as they require patients to have reasonable communication ability. Subjective, inconsistent, and discontinuous pain assessment in children may reduce therapeutic effectiveness and thus affect their later life. METHODS To address the need for suitable assessment measures, this paper proposes a spatiotemporal deep learning framework for scalp electroencephalogram (EEG)-based automated pain assessment in children. The dataset comprises scalp EEG data recorded from 33 pediatric patients with an arterial puncture as a pain stimulus. Two electrode reduction plans in line with clinical findings are proposed. Combining three-dimensional hand-crafted features and preprocessed raw signals, the proposed transformer-based pain assessment network (STPA-Net) integrates both spatial and temporal information. RESULTS STPA-Net achieves superior performance with a subject-independent accuracy of 87.83% for pain recognition, and outperforms other state-of-the-art approaches. The effectiveness of electrode combinations is explored to analyze pain-related cortical activities and correspondingly reduce cost. The two proposed electrode reduction plans both demonstrate competitive pain assessment performance qualitatively and quantitatively. CONCLUSION AND SIGNIFICANCE This study is the first to develop a scalp EEG-based automated pain assessment for children adopting a method that is objective, standardized, and consistent. The findings provide a potential reference for future clinical research.
Collapse
|
2
|
Bechny M, Monachino G, Fiorillo L, van der Meer J, Schmidt MH, Bassetti CLA, Tzovara A, Faraci FD. Bridging AI and Clinical Practice: Integrating Automated Sleep Scoring Algorithm with Uncertainty-Guided Physician Review. Nat Sci Sleep 2024; 16:555-572. [PMID: 38827394 PMCID: PMC11143488 DOI: 10.2147/nss.s455649] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Accepted: 04/18/2024] [Indexed: 06/04/2024] Open
Abstract
Purpose This study aims to enhance the clinical use of automated sleep-scoring algorithms by incorporating an uncertainty estimation approach to efficiently assist clinicians in the manual review of predicted hypnograms, a necessity due to the notable inter-scorer variability inherent in polysomnography (PSG) databases. Our efforts target the extent of review required to achieve predefined agreement levels, examining both in-domain (ID) and out-of-domain (OOD) data, and considering subjects' diagnoses. Patients and Methods A total of 19,578 PSGs from 13 open-access databases were used to train U-Sleep, a state-of-the-art sleep-scoring algorithm. We leveraged a comprehensive clinical database of an additional 8832 PSGs, covering a full spectrum of ages (0-91 years) and sleep-disorders, to refine the U-Sleep, and to evaluate different uncertainty-quantification approaches, including our novel confidence network. The ID data consisted of PSGs scored by over 50 physicians, and the two OOD sets comprised recordings each scored by a unique senior physician. Results U-Sleep demonstrated robust performance, with Cohen's kappa (K) at 76.2% on ID and 73.8-78.8% on OOD data. The confidence network excelled at identifying uncertain predictions, achieving AUROC scores of 85.7% on ID and 82.5-85.6% on OOD data. Independently of sleep-disorder status, statistical evaluations revealed significant differences in confidence scores between aligning vs discording predictions, and significant correlations of confidence scores with classification performance metrics. To achieve κ ≥ 90% with physician intervention, examining less than 29.0% of uncertain epochs was required, substantially reducing physicians' workload, and facilitating near-perfect agreement. Conclusion Inter-scorer variability limits the accuracy of the scoring algorithms to ~80%. By integrating an uncertainty estimation with U-Sleep, we enhance the review of predicted hypnograms, to align with the scoring taste of a responsible physician. Validated across ID and OOD data and various sleep-disorders, our approach offers a strategy to boost automated scoring tools' usability in clinical settings.
Collapse
Affiliation(s)
- Michal Bechny
- Institute of Computer Science, University of Bern, Bern, Switzerland
- Institute of Digital Technologies for Personalized Healthcare (Meditech), University of Applied Sciences and Arts of Southern Switzerland, Lugano, Switzerland
| | - Giuliana Monachino
- Institute of Computer Science, University of Bern, Bern, Switzerland
- Institute of Digital Technologies for Personalized Healthcare (Meditech), University of Applied Sciences and Arts of Southern Switzerland, Lugano, Switzerland
| | - Luigi Fiorillo
- Institute of Digital Technologies for Personalized Healthcare (Meditech), University of Applied Sciences and Arts of Southern Switzerland, Lugano, Switzerland
| | | | - Markus H Schmidt
- Department of Neurology, University Hospital of Bern, Bern, Switzerland
- Ohio Sleep Medicine Institute, Dublin, OH, USA
| | | | - Athina Tzovara
- Institute of Computer Science, University of Bern, Bern, Switzerland
- Department of Neurology, University Hospital of Bern, Bern, Switzerland
| | - Francesca D Faraci
- Institute of Digital Technologies for Personalized Healthcare (Meditech), University of Applied Sciences and Arts of Southern Switzerland, Lugano, Switzerland
| |
Collapse
|
3
|
van Gorp H, van Gilst MM, Overeem S, Dujardin S, Pijpers A, van Wetten B, Fonseca P, van Sloun RJG. Single-channel EOG sleep staging on a heterogeneous cohort of subjects with sleep disorders. Physiol Meas 2024; 45:055007. [PMID: 38653318 DOI: 10.1088/1361-6579/ad4251] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Accepted: 04/23/2024] [Indexed: 04/25/2024]
Abstract
Objective.Sleep staging based on full polysomnography is the gold standard in the diagnosis of many sleep disorders. It is however costly, complex, and obtrusive due to the use of multiple electrodes. Automatic sleep staging based on single-channel electro-oculography (EOG) is a promising alternative, requiring fewer electrodes which could be self-applied below the hairline. EOG sleep staging algorithms are however yet to be validated in clinical populations with sleep disorders.Approach.We utilized the SOMNIA dataset, comprising 774 recordings from subjects with various sleep disorders, including insomnia, sleep-disordered breathing, hypersomnolence, circadian rhythm disorders, parasomnias, and movement disorders. The recordings were divided into train (574), validation (100), and test (100) groups. We trained a neural network that integrated transformers within a U-Net backbone. This design facilitated learning of arbitrary-distance temporal relationships within and between the EOG and hypnogram.Main results.For 5-class sleep staging, we achieved median accuracies of 85.0% and 85.2% and Cohen's kappas of 0.781 and 0.796 for left and right EOG, respectively. The performance using the right EOG was significantly better than using the left EOG, possibly because in the recommended AASM setup, this electrode is located closer to the scalp. The proposed model is robust to the presence of a variety of sleep disorders, displaying no significant difference in performance for subjects with a certain sleep disorder compared to those without.Significance.The results show that accurate sleep staging using single-channel EOG can be done reliably for subjects with a variety of sleep disorders.
Collapse
Affiliation(s)
- Hans van Gorp
- Department of Electrical Engineering, Eindhoven University of Technology, The Netherlands
- Philips Sleep and Respiratory Care, Eindhoven, The Netherlands
| | - Merel M van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, The Netherlands
- Sleep Medicine Centre Kempenhaeghe, Heeze, The Netherlands
| | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, The Netherlands
- Sleep Medicine Centre Kempenhaeghe, Heeze, The Netherlands
| | | | | | | | - Pedro Fonseca
- Department of Electrical Engineering, Eindhoven University of Technology, The Netherlands
- Philips Sleep and Respiratory Care, Eindhoven, The Netherlands
| | - Ruud J G van Sloun
- Department of Electrical Engineering, Eindhoven University of Technology, The Netherlands
| |
Collapse
|
4
|
Oh S, Kweon YS, Shin GH, Lee SW. Association Between Sleep Quality and Deep Learning-Based Sleep Onset Latency Distribution Using an Electroencephalogram. IEEE Trans Neural Syst Rehabil Eng 2024; 32:1806-1816. [PMID: 38696294 DOI: 10.1109/tnsre.2024.3396169] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/04/2024]
Abstract
To evaluate sleep quality, it is necessary to monitor overnight sleep duration. However, sleep monitoring typically requires more than 7 hours, which can be inefficient in termxs of data size and analysis. Therefore, we proposed to develop a deep learning-based model using a 30 sec sleep electroencephalogram (EEG) early in the sleep cycle to predict sleep onset latency (SOL) distribution and explore associations with sleep quality (SQ). We propose a deep learning model composed of a structure that decomposes and restores the signal in epoch units and a structure that predicts the SOL distribution. We used the Sleep Heart Health Study public dataset, which includes a large number of study subjects, to estimate and evaluate the proposed model. The proposed model estimated the SOL distribution and divided it into four clusters. The advantage of the proposed model is that it shows the process of falling asleep for individual participants as a probability graph over time. Furthermore, we compared the baseline of good SQ and SOL and showed that less than 10 minutes SOL correlated better with good SQ. Moreover, it was the most suitable sleep feature that could be predicted using early EEG, compared with the total sleep time, sleep efficiency, and actual sleep time. Our study showed the feasibility of estimating SOL distribution using deep learning with an early EEG and showed that SOL distribution within 10 minutes was associated with good SQ.
Collapse
|
5
|
Zaman A, Kumar S, Shatabda S, Dehzangi I, Sharma A. SleepBoost: a multi-level tree-based ensemble model for automatic sleep stage classification. Med Biol Eng Comput 2024:10.1007/s11517-024-03096-x. [PMID: 38700613 DOI: 10.1007/s11517-024-03096-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Accepted: 04/14/2024] [Indexed: 05/16/2024]
Abstract
Neurodegenerative diseases often exhibit a strong link with sleep disruption, highlighting the importance of effective sleep stage monitoring. In this light, automatic sleep stage classification (ASSC) plays a pivotal role, now more streamlined than ever due to the advancements in deep learning (DL). However, the opaque nature of DL models can be a barrier in their clinical adoption, due to trust concerns among medical practitioners. To bridge this gap, we introduce SleepBoost, a transparent multi-level tree-based ensemble model specifically designed for ASSC. Our approach includes a crafted feature engineering block (FEB) that extracts 41 time and frequency domain features, out of which 23 are selected based on their high mutual information score (> 0.23). Uniquely, SleepBoost integrates three fundamental linear models into a cohesive multi-level tree structure, further enhanced by a novel reward-based adaptive weight allocation mechanism. Tested on the Sleep-EDF-20 dataset, SleepBoost demonstrates superior performance with an accuracy of 86.3%, F1-score of 80.9%, and Cohen kappa score of 0.807, outperforming leading DL models in ASSC. An ablation study underscores the critical role of our selective feature extraction in enhancing model accuracy and interpretability, crucial for clinical settings. This innovative approach not only offers a more transparent alternative to traditional DL models but also extends potential implications for monitoring and understanding sleep patterns in the context of neurodegenerative disorders. The open-source availability of SleepBoost's implementation at https://github.com/akibzaman/SleepBoost can further facilitate its accessibility and potential for widespread clinical adoption.
Collapse
Affiliation(s)
- Akib Zaman
- Computer Science and Artificial Intelligence Laboratory (CSAIL), Electrical Engineering and Computer Science Department, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Shiu Kumar
- School of Electrical & Electronics Engineering, Fiji National University, Suva, Fiji.
| | - Swakkhar Shatabda
- Centre for Artificial Intelligence and Robotics (CAIR), United International University, Dhaka, Bangladesh
| | - Iman Dehzangi
- Department of Computer Science, Rutgers University, Camden, NJ, USA
- Center for Computational and Integrative Biology, Rutgers University, Camden, USA
| | - Alok Sharma
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, 230-0045, Japan
- Institute for Integrated and Intelligent Systems, Griffith University, Nathan, Brisbane, QLD, Australia
| |
Collapse
|
6
|
An P, Zhao J, Du B, Zhao W, Zhang T, Yuan Z. Amplitude-Time Dual-View Fused EEG Temporal Feature Learning for Automatic Sleep Staging. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:6492-6506. [PMID: 36215384 DOI: 10.1109/tnnls.2022.3210384] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Electroencephalogram (EEG) plays an important role in studying brain function and human cognitive performance, and the recognition of EEG signals is vital to develop an automatic sleep staging system. However, due to the complex nonstationary characteristics and the individual difference between subjects, how to obtain the effective signal features of the EEG for practical application is still a challenging task. In this article, we investigate the EEG feature learning problem and propose a novel temporal feature learning method based on amplitude-time dual-view fusion for automatic sleep staging. First, we explore the feature extraction ability of convolutional neural networks for the EEG signal from the perspective of interpretability and construct two new representation signals for the raw EEG from the views of amplitude and time. Then, we extract the amplitude-time signal features that reflect the transformation between different sleep stages from the obtained representation signals by using conventional 1-D CNNs. Furthermore, a hybrid dilation convolution module is used to learn the long-term temporal dependency features of EEG signals, which can overcome the shortcoming that the small-scale convolution kernel can only learn the local signal variation information. Finally, we conduct attention-based feature fusion for the learned dual-view signal features to further improve sleep staging performance. To evaluate the performance of the proposed method, we test 30-s-epoch EEG signal samples for healthy subjects and subjects with mild sleep disorders. The experimental results from the most commonly used datasets show that the proposed method has better sleep staging performance and has the potential for the development and application of an EEG-based automatic sleep staging system.
Collapse
|
7
|
Radke FA, da Silva Souto CF, Pätzold W, Wolf KI. Transfer Learning for Automatic Sleep Staging Using a Pre-Gelled Electrode Grid. Diagnostics (Basel) 2024; 14:909. [PMID: 38732323 PMCID: PMC11083934 DOI: 10.3390/diagnostics14090909] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/29/2024] [Revised: 04/18/2024] [Accepted: 04/24/2024] [Indexed: 05/13/2024] Open
Abstract
Novel sensor solutions for sleep monitoring at home could alleviate bottlenecks in sleep medical care as well as enable selective or continuous observation over long periods of time and contribute to new insights in sleep medicine and beyond. Since especially in the latter case the sensor data differ strongly in signal, number and extent of sensors from the classical polysomnography (PSG) sensor technology, an automatic evaluation is essential for the application. However, the training of an automatic algorithm is complicated by the fact that the development phase of the new sensor technology, extensive comparative measurements with standardized reference systems, is often not possible and therefore only small datasets are available. In order to circumvent high system-specific training data requirements, we employ pre-training on large datasets with finetuning on small datasets of new sensor technology to enable automatic sleep phase detection for small test series. By pre-training on publicly available PSG datasets and finetuning on 12 nights recorded with new sensor technology based on a pre-gelled electrode grid to capture electroencephalography (EEG), electrooculography (EOG) and electromyography (EMG), an F1 score across all sleep phases of 0.81 is achieved (wake 0.84, N1 0.62, N2 0.81, N3 0.87, REM 0.88), using only EEG and EOG. The analysis additionally considers the spatial distribution of the channels and an approach to approximate classical electrode positions based on specific linear combinations of the new sensor grid channels.
Collapse
Affiliation(s)
- Fabian A. Radke
- Fraunhofer Institute for Digital Media Technology IDMT, Oldenburg Branch for Hearing, Speech and Audio Technology HSA, 26129 Oldenburg, Germany
| | | | | | | |
Collapse
|
8
|
Baumert M, Phan H. A perspective on automated rapid eye movement sleep assessment. J Sleep Res 2024:e14223. [PMID: 38650539 DOI: 10.1111/jsr.14223] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2023] [Revised: 02/18/2024] [Accepted: 04/08/2024] [Indexed: 04/25/2024]
Abstract
Rapid eye movement sleep is associated with distinct changes in various biomedical signals that can be easily captured during sleep, lending themselves to automated sleep staging using machine learning systems. Here, we provide a perspective on the critical characteristics of biomedical signals associated with rapid eye movement sleep and how they can be exploited for automated sleep assessment. We summarise key historical developments in automated sleep staging systems, having now achieved classification accuracy on par with human expert scorers and their role in the clinical setting. We also discuss rapid eye movement sleep assessment with consumer sleep trackers and its potential for unprecedented sleep assessment on a global scale. We conclude by providing a future outlook of computerised rapid eye movement sleep assessment and the role AI systems may play.
Collapse
Affiliation(s)
- Mathias Baumert
- Discipline of Biomedical Engineering, School of Electrical and Mechanical Engineering, The University of Adelaide, Adelaide, Australia
| | - Huy Phan
- Amazon, Cambridge, Massachusetts, USA
| |
Collapse
|
9
|
Ahrens E, Jennum P, Duun-Henriksen J, Borregaard HWS, Nielsen SS, Taptiklis N, Cormack F, Djurhuus BD, Homøe P, Kjær TW, Hemmsen MC. The Ultra-Long-Term Sleep study: Design, rationale, data stability and user perspective. J Sleep Res 2024:e14197. [PMID: 38572813 DOI: 10.1111/jsr.14197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2023] [Revised: 02/26/2024] [Accepted: 03/04/2024] [Indexed: 04/05/2024]
Abstract
Sleep deprivation and poor sleep quality are significant societal challenges that negatively impact individuals' health. The interaction between subjective sleep quality, objective sleep measures, physical and cognitive performance, and their day-to-day variations remains poorly understood. Our year-long study of 20 healthy individuals, using subcutaneous electroencephalography, aimed to elucidate these interactions, assessing data stability and participant satisfaction, usability, well-being and adherence. In the study, 25 participants were fitted with a minimally invasive subcutaneous electroencephalography lead, with 20 completing the year of subcutaneous electroencephalography recording. Signal stability was measured using covariance of variation. Participant satisfaction, usability and well-being were measured with questionnaires: Perceived Ease of Use questionnaire, System Usability Scale, Headache questionnaire, Major Depression Inventory, World Health Organization 5-item Well-Being Index, and interviews. The subcutaneous electroencephalography signals remained stable for the entire year, with an average participant adherence rate of 91%. Participants rated their satisfaction with the subcutaneous electroencephalography device as easy to use with minimal or no discomfort. The System Usability Scale score was high at 86.3 ± 10.1, and interviews highlighted that participants understood how to use the subcutaneous electroencephalography device and described a period of acclimatization to sleeping with the device. This study provides compelling evidence for the feasibility of longitudinal sleep monitoring during everyday life utilizing subcutaneous electroencephalography in healthy subjects, showcasing excellent signal stability, adherence and user experience. The amassed subcutaneous electroencephalography data constitutes the largest dataset of its kind, and is poised to significantly advance our understanding of day-to-day variations in normal sleep and provide key insights into subjective and objective sleep quality.
Collapse
Affiliation(s)
- Esben Ahrens
- T&W Engineering A/S, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Poul Jennum
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Danish Center for Sleep Medicine, Department of Clinical Neurophysiology, Glostrup, Denmark
| | | | | | | | | | - Francesca Cormack
- Cambridge Cognition Ltd, Cambridge, UK
- Department of Psychiatry, University of Cambridge, Cambridge, UK
| | - Bjarki Ditlev Djurhuus
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Department of Otorhinolaryngology and Maxillofacial Surgery, Zealand University Hospital, Køge, Denmark
| | - Preben Homøe
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
- Department of Otorhinolaryngology and Maxillofacial Surgery, Zealand University Hospital, Køge, Denmark
| | - Troels W Kjær
- T&W Engineering A/S, Denmark
- UNEEG medical A/S, Lillerød, Lillerød, Denmark
| | | |
Collapse
|
10
|
Heremans ERM, Seedat N, Buyse B, Testelmans D, van der Schaar M, De Vos M. U-PASS: An uncertainty-guided deep learning pipeline for automated sleep staging. Comput Biol Med 2024; 171:108205. [PMID: 38401452 DOI: 10.1016/j.compbiomed.2024.108205] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 02/16/2024] [Accepted: 02/20/2024] [Indexed: 02/26/2024]
Abstract
With the increasing prevalence of machine learning in critical fields like healthcare, ensuring the safety and reliability of these systems is crucial. Estimating uncertainty plays a vital role in enhancing reliability by identifying areas of high and low confidence and reducing the risk of errors. This study introduces U-PASS, a specialized human-centered machine learning pipeline tailored for clinical applications, which effectively communicates uncertainty to clinical experts and collaborates with them to improve predictions. U-PASS incorporates uncertainty estimation at every stage of the process, including data acquisition, training, and model deployment. Training is divided into a supervised pre-training step and a semi-supervised recording-wise finetuning step. We apply U-PASS to the challenging task of sleep staging and demonstrate that it systematically improves performance at every stage. By optimizing the training dataset, actively seeking feedback from domain experts for informative samples, and deferring the most uncertain samples to experts, U-PASS achieves an impressive expert-level accuracy of 85% on a challenging clinical dataset of elderly sleep apnea patients. This represents a significant improvement over the starting point at 75% accuracy. The largest improvement gain is due to the deferral of uncertain epochs to a sleep expert. U-PASS presents a promising AI approach to incorporating uncertainty estimation in machine learning pipelines, improving their reliability and unlocking their potential in clinical settings.
Collapse
Affiliation(s)
- Elisabeth R M Heremans
- KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium.
| | | | - Bertien Buyse
- UZ Leuven, Department of Pneumology, Herestraat 49, B-3000 Leuven, Belgium
| | - Dries Testelmans
- UZ Leuven, Department of Pneumology, Herestraat 49, B-3000 Leuven, Belgium
| | | | - Maarten De Vos
- KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium.
| |
Collapse
|
11
|
Nam B, Bark B, Lee J, Kim IY. InsightSleepNet: the interpretable and uncertainty-aware deep learning network for sleep staging using continuous Photoplethysmography. BMC Med Inform Decis Mak 2024; 24:50. [PMID: 38355559 PMCID: PMC10865603 DOI: 10.1186/s12911-024-02437-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Accepted: 01/23/2024] [Indexed: 02/16/2024] Open
Abstract
BACKGROUND This study was conducted to address the existing drawbacks of inconvenience and high costs associated with sleep monitoring. In this research, we performed sleep staging using continuous photoplethysmography (PPG) signals for sleep monitoring with wearable devices. Furthermore, our aim was to develop a more efficient sleep monitoring method by considering both the interpretability and uncertainty of the model's prediction results, with the goal of providing support to medical professionals in their decision-making process. METHOD The developed 4-class sleep staging model based on continuous PPG data incorporates several key components: a local attention module, an InceptionTime module, a time-distributed dense layer, a temporal convolutional network (TCN), and a 1D convolutional network (CNN). This model prioritizes both interpretability and uncertainty estimation in its prediction results. The local attention module is introduced to provide insights into the impact of each epoch within the continuous PPG data. It achieves this by leveraging the TCN structure. To quantify the uncertainty of prediction results and facilitate selective predictions, an energy score estimation is employed. By enhancing both the performance and interpretability of the model and taking into consideration the reliability of its predictions, we developed the InsightSleepNet for accurate sleep staging. RESULT InsightSleepNet was evaluated using three distinct datasets: MESA, CFS, and CAP. Initially, we assessed the model's classification performance both before and after applying an energy score threshold. We observed a significant improvement in the model's performance with the implementation of the energy score threshold. On the MESA dataset, prior to applying the energy score threshold, the accuracy was 84.2% with a Cohen's kappa of 0.742 and weighted F1 score of 0.842. After implementing the energy score threshold, the accuracy increased to a range of 84.8-86.1%, Cohen's kappa values ranged from 0.75 to 0.78 and weighted F1 scores ranged from 0.848 to 0.861. In the case of the CFS dataset, we also noted enhanced performance. Before the application of the energy score threshold, the accuracy stood at 80.6% with a Cohen's kappa of 0.72 and weighted F1 score of 0.808. After thresholding, the accuracy improved to a range of 81.9-85.6%, Cohen's kappa values ranged from 0.74 to 0.79 and weighted F1 scores ranged from 0.821 to 0.857. Similarly, on the CAP dataset, the initial accuracy was 80.6%, accompanied by a Cohen's kappa of 0.73 and weighted F1 score was 0.805. Following the application of the threshold, the accuracy increased to a range of 81.4-84.3%, Cohen's kappa values ranged from 0.74 to 0.79 and weighted F1 scores ranged from 0.813 to 0.842. Additionally, by interpreting the model's predictions, we obtained results indicating a correlation between the peak of the PPG signal and sleep stage classification. CONCLUSION InsightSleepNet is a 4-class sleep staging model that utilizes continuous PPG data, serves the purpose of continuous sleep monitoring with wearable devices. Beyond its primary function, it might facilitate in-depth sleep analysis by medical professionals and empower them with interpretability for intervention-based predictions. This capability can also support well-informed clinical decision-making, providing valuable insights and serving as a reliable second opinion in medical settings.
Collapse
Affiliation(s)
- Borum Nam
- Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea
| | - Beomjun Bark
- Department of Biomedical Engineering, Hanyang University, 222, Wangsimni-ro, Seoul, 04763, Republic of Korea
| | - Jeyeon Lee
- Department of Biomedical Engineering, Hanyang University, 222, Wangsimni-ro, Seoul, 04763, Republic of Korea
| | - In Young Kim
- Department of Biomedical Engineering, Hanyang University, 222, Wangsimni-ro, Seoul, 04763, Republic of Korea.
| |
Collapse
|
12
|
Pei W, Li Y, Wen P, Yang F, Ji X. An automatic method using MFCC features for sleep stage classification. Brain Inform 2024; 11:6. [PMID: 38340211 DOI: 10.1186/s40708-024-00219-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Accepted: 01/19/2024] [Indexed: 02/12/2024] Open
Abstract
Sleep stage classification is a necessary step for diagnosing sleep disorders. Generally, experts use traditional methods based on every 30 seconds (s) of the biological signals, such as electrooculograms (EOGs), electrocardiograms (ECGs), electromyograms (EMGs), and electroencephalograms (EEGs), to classify sleep stages. Recently, various state-of-the-art approaches based on a deep learning model have been demonstrated to have efficient and accurate outcomes in sleep stage classification. In this paper, a novel deep convolutional neural network (CNN) combined with a long short-time memory (LSTM) model is proposed for sleep scoring tasks. A key frequency domain feature named Mel-frequency Cepstral Coefficient (MFCC) is extracted from EEG and EMG signals. The proposed method can learn features from frequency domains on different bio-signal channels. It firstly extracts the MFCC features from multi-channel signals, and then inputs them to several convolutional layers and an LSTM layer. Secondly, the learned representations are fed to a fully connected layer and a softmax classifier for sleep stage classification. The experiments are conducted on two widely used sleep datasets, Sleep Heart Health Study (SHHS) and Vincent's University Hospital/University College Dublin Sleep Apnoea (UCDDB) to test the effectiveness of the method. The results of this study indicate that the model can perform well in the classification of sleep stages using the features of the 2-dimensional (2D) MFCC feature. The advantage of using the feature is that it can be used to input a two-dimensional data stream, which can be used to retain information about each sleep stage. Using 2D data streams can reduce the time it takes to retrieve the data from the one-dimensional stream. Another advantage of this method is that it eliminates the need for deep layers, which can help improve the performance of the model. For instance, by reducing the number of layers, our seven layers of the model structure takes around 400 s to train and test 100 subjects in the SHHS1 dataset. Its best accuracy and Cohen's kappa are 82.35% and 0.75 for the SHHS dataset, and 73.07% and 0.63 for the UCDDB dataset, respectively.
Collapse
Affiliation(s)
- Wei Pei
- School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, 4350, Australia.
| | - Yan Li
- School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, 4350, Australia
| | - Peng Wen
- School of Engineering, University of Southern Queensland, Toowoomba, QLD, 4350, Australia
| | - Fuwen Yang
- School of Engineering and Built Environment, Griffith University, Gold Coast, QLD, 4222, Australia
| | - Xiaopeng Ji
- School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, 4350, Australia
| |
Collapse
|
13
|
Chen Z, Pan X, Xu Z, Li K, Lv Y, Zhang Y, Sun H. A Semi-Supervised Multi-Scale Arbitrary Dilated Convolution Neural Network for Pediatric Sleep Staging. IEEE J Biomed Health Inform 2024; 28:1043-1053. [PMID: 37930925 DOI: 10.1109/jbhi.2023.3330345] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2023]
Abstract
Sleep staging is essential for assessing sleep quality and diagnosing sleep disorders. However, sleep staging is a labor-intensive process, making it arduous to obtain large quantities of high-quality labeled data for automatic sleep staging. Meanwhile, most of the research on automatic sleep staging pays little attention to pediatric sleep staging. To address these challenges, we propose a semi-supervised multi-scale arbitrary dilated convolution neural network (SMADNet) for pediatric sleep staging using the scalogram with a high height-to-width ratio generated by the continuous wavelet transform (CWT) as input. To extract more extended time dimensional feature representations and adapt to scalograms with a high height-to-width ratio in SMADNet, we introduce a multi-scale arbitrary dilation convolution block (MADBlock) based on our proposed arbitrary dilated convolution (ADConv). Finally, we also utilize semi-supervised learning as the training scheme for our network in order to alleviate the reliance on labeled data. Our proposed model has achieved performance comparable to state-of-the-art supervised learning methods with 30% labels. Our model is tested on a private pediatric dataset and achieved 79% accuracy, 72% kappa, and 75% MF1. Therefore, our model demonstrates a powerful feature extraction capability and has achieved performance comparable to state-of-the-art supervised learning methods with a small number of labels.
Collapse
|
14
|
Brodersen PJN, Alfonsa H, Krone LB, Blanco-Duque C, Fisk AS, Flaherty SJ, Guillaumin MCC, Huang YG, Kahn MC, McKillop LE, Milinski L, Taylor L, Thomas CW, Yamagata T, Foster RG, Vyazovskiy VV, Akerman CJ. Somnotate: A probabilistic sleep stage classifier for studying vigilance state transitions. PLoS Comput Biol 2024; 20:e1011793. [PMID: 38232122 PMCID: PMC10824458 DOI: 10.1371/journal.pcbi.1011793] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2023] [Revised: 01/29/2024] [Accepted: 01/02/2024] [Indexed: 01/19/2024] Open
Abstract
Electrophysiological recordings from freely behaving animals are a widespread and powerful mode of investigation in sleep research. These recordings generate large amounts of data that require sleep stage annotation (polysomnography), in which the data is parcellated according to three vigilance states: awake, rapid eye movement (REM) sleep, and non-REM (NREM) sleep. Manual and current computational annotation methods ignore intermediate states because the classification features become ambiguous, even though intermediate states contain important information regarding vigilance state dynamics. To address this problem, we have developed "Somnotate"-a probabilistic classifier based on a combination of linear discriminant analysis (LDA) with a hidden Markov model (HMM). First we demonstrate that Somnotate sets new standards in polysomnography, exhibiting annotation accuracies that exceed human experts on mouse electrophysiological data, remarkable robustness to errors in the training data, compatibility with different recording configurations, and an ability to maintain high accuracy during experimental interventions. However, the key feature of Somnotate is that it quantifies and reports the certainty of its annotations. We leverage this feature to reveal that many intermediate vigilance states cluster around state transitions, whereas others correspond to failed attempts to transition. This enables us to show for the first time that the success rates of different types of transition are differentially affected by experimental manipulations and can explain previously observed sleep patterns. Somnotate is open-source and has the potential to both facilitate the study of sleep stage transitions and offer new insights into the mechanisms underlying sleep-wake dynamics.
Collapse
Affiliation(s)
- Paul J. N. Brodersen
- Department of Pharmacology, University of Oxford; Mansfield Road, Oxford, United Kingdom
| | - Hannah Alfonsa
- Department of Pharmacology, University of Oxford; Mansfield Road, Oxford, United Kingdom
| | - Lukas B. Krone
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Cristina Blanco-Duque
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Angus S. Fisk
- Nuffield Department of Clinical Neurosciences, University of Oxford; John Radcliffe Hospital, Oxford, United Kingdom
| | - Sarah J. Flaherty
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Mathilde C. C. Guillaumin
- Nuffield Department of Clinical Neurosciences, University of Oxford; John Radcliffe Hospital, Oxford, United Kingdom
- Sleep and Circadian Neuroscience Institute, University of Oxford; Oxford, United Kingdom
- Institute for Neuroscience, Department of Health Sciences and Technology, ETH Zurich; Schwerzenbach, Switzerland
| | - Yi-Ge Huang
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Martin C. Kahn
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Laura E. McKillop
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Linus Milinski
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Lewis Taylor
- Nuffield Department of Clinical Neurosciences, University of Oxford; John Radcliffe Hospital, Oxford, United Kingdom
| | - Christopher W. Thomas
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Tomoko Yamagata
- Nuffield Department of Clinical Neurosciences, University of Oxford; John Radcliffe Hospital, Oxford, United Kingdom
| | - Russell G. Foster
- Sleep and Circadian Neuroscience Institute, University of Oxford; Oxford, United Kingdom
| | - Vladyslav V. Vyazovskiy
- Department of Physiology, Anatomy and Genetics, University of Oxford; Parks Road, United Kingdom
| | - Colin J. Akerman
- Department of Pharmacology, University of Oxford; Mansfield Road, Oxford, United Kingdom
| |
Collapse
|
15
|
van Gorp H, van Gilst MM, Fonseca P, Overeem S, van Sloun RJG. Modeling the Impact of Inter-Rater Disagreement on Sleep Statistics Using Deep Generative Learning. IEEE J Biomed Health Inform 2023; 27:5599-5609. [PMID: 37561616 DOI: 10.1109/jbhi.2023.3304010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/12/2023]
Abstract
Sleep staging is the process by which an overnight polysomnographic measurement is segmented into epochs of 30 seconds, each of which is annotated as belonging to one of five discrete sleep stages. The resulting scoring is graphically depicted as a hypnogram, and several overnight sleep statistics are derived, such as total sleep time and sleep onset latency. Gold standard sleep staging as performed by human technicians is time-consuming, costly, and comes with imperfect inter-scorer agreement, which also results in inter-scorer disagreement about the overnight statistics. Deep learning algorithms have shown promise in automating sleep scoring, but struggle to model inter-scorer disagreement in sleep statistics. To that end, we introduce a novel technique using conditional generative models based on Normalizing Flows that permits the modeling of the inter-rater disagreement of overnight sleep statistics, termed U-Flow. We compare U-Flow to other automatic scoring methods on a hold-out test set of 70 subjects, each scored by six independent scorers. The proposed method achieves similar sleep staging performance in terms of accuracy and Cohen's kappa on the majority-voted hypnograms. At the same time, U-Flow outperforms the other methods in terms of modeling the inter-rater disagreement of overnight sleep statistics. The consequences of inter-rater disagreement about overnight sleep statistics may be great, and the disagreement potentially carries diagnostic and scientifically relevant information about sleep structure. U-Flow is able to model this disagreement efficiently and can support further investigations into the impact inter-rater disagreement has on sleep medicine and basic sleep research.
Collapse
|
16
|
Liu Z, Qin M, Lu Y, Luo S, Zhang Q. DenSleepNet: DenseNet based model for sleep staging with two-frequency feature fusion and coordinate attention. Biomed Eng Lett 2023; 13:751-761. [PMID: 37872995 PMCID: PMC10590351 DOI: 10.1007/s13534-023-00301-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2023] [Revised: 06/15/2023] [Accepted: 06/23/2023] [Indexed: 10/25/2023] Open
Abstract
Sleep staging is often applied to assess the quality of sleep and also be used to prevent and monitor psychiatric disorders caused by sleep. However, it remains a challenge to extract the discriminative features of salient waveforms in sleep EEG and enable the network to effectively classify sleep stages by emphasizing these crucial features, thus achieving higher accuracy. In this study, an end-to-end deep learning model based on DenseNet for automatic sleep staging is designed and constructed. In the framework, two convolutional branches are devised to extract the underlying features (Two-Frequency Feature) at various frequencies, which are then fused and input into the DenseNet module to extract salient waveform features. After that, the Coordinate Attention mechanism is employed to enhance the localization of salient waveform features by emphasizing the position of salient waveforms and the spatial relationship across the entire frequency spectrum. Finally, the obtained features are accessed to the fully connected for sleep staging. The model was validated with a 20-fold cross-validation procedure on two public available datasets, and the overall accuracy, kappa coefficient, and MF1 score reached 92.9%, 78.7, 0.86 and 90.0%, 75.8, 0.80 on Sleep-EDF-20 and Sleep-EDFx, respectively. Experimental results show that the proposed model achieves competitive performance for sleep staging compared with the reported approaches under the identical conditions.
Collapse
Affiliation(s)
- Zhi Liu
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
| | - Meiqiao Qin
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
| | - Yunhua Lu
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
| | - Sixin Luo
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
| | - Qinhan Zhang
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
| |
Collapse
|
17
|
Huang X, Schmelter F, Irshad MT, Piet A, Nisar MA, Sina C, Grzegorzek M. Optimizing sleep staging on multimodal time series: Leveraging borderline synthetic minority oversampling technique and supervised convolutional contrastive learning. Comput Biol Med 2023; 166:107501. [PMID: 37742416 DOI: 10.1016/j.compbiomed.2023.107501] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 08/15/2023] [Accepted: 09/15/2023] [Indexed: 09/26/2023]
Abstract
Sleep is an important research area in nutritional medicine that plays a crucial role in human physical and mental health restoration. It can influence diet, metabolism, and hormone regulation, which can affect overall health and well-being. As an essential tool in the sleep study, the sleep stage classification provides a parsing of sleep architecture and a comprehensive understanding of sleep patterns to identify sleep disorders and facilitate the formulation of targeted sleep interventions. However, the class imbalance issue is typically salient in sleep datasets, which severely affects classification performances. To address this issue and to extract optimal multimodal features of EEG, EOG, and EMG that can improve the accuracy of sleep stage classification, a Borderline Synthetic Minority Oversampling Technique (B-SMOTE)-Based Supervised Convolutional Contrastive Learning (BST-SCCL) is proposed, which can avoid the risk of data mismatch between various sleep knowledge domains (varying health conditions and annotation rules) and strengthening learning characteristics of the N1 stage from the pair-wise segments comparison strategy. The lightweight residual network architecture with a novel truncated cross-entropy loss function is designed to accommodate multimodal time series and boost the training speed and performance stability. The proposed model has been validated on four well-known public sleep datasets (Sleep-EDF-20, Sleep-EDF-78, ISRUC-1, and ISRUC-3) and its superior performance (overall accuracy of 91.31-92.34%, MF1 of 88.21-90.08%, and Cohen's Kappa coefficient k of 0.87-0.89) has further demonstrated its effectiveness. It shows the great potential of contrastive learning for cross-domain knowledge interaction in precision medicine.
Collapse
Affiliation(s)
- Xinyu Huang
- Institute of Medical Informatics, University of Lübeck, Germany.
| | - Franziska Schmelter
- Institute of Nutritional Medicine, University of Lübeck and University Medical Center Schleswig-Holstein, Lübeck, Germany.
| | | | - Artur Piet
- Institute of Medical Informatics, University of Lübeck, Germany.
| | | | - Christian Sina
- Institute of Nutritional Medicine, University of Lübeck and University Medical Center Schleswig-Holstein, Lübeck, Germany; Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering (IMTE), Lübeck, Germany.
| | - Marcin Grzegorzek
- Institute of Medical Informatics, University of Lübeck, Germany; Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering (IMTE), Lübeck, Germany.
| |
Collapse
|
18
|
Zan H, Yildiz A. Multi-task learning for arousal and sleep stage detection using fully convolutional networks. J Neural Eng 2023; 20:056034. [PMID: 37769664 DOI: 10.1088/1741-2552/acfe3a] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2023] [Accepted: 09/28/2023] [Indexed: 10/03/2023]
Abstract
Objective.Sleep is a critical physiological process that plays a vital role in maintaining physical and mental health. Accurate detection of arousals and sleep stages is essential for the diagnosis of sleep disorders, as frequent and excessive occurrences of arousals disrupt sleep stage patterns and lead to poor sleep quality, negatively impacting physical and mental health. Polysomnography is a traditional method for arousal and sleep stage detection that is time-consuming and prone to high variability among experts.Approach. In this paper, we propose a novel multi-task learning approach for arousal and sleep stage detection using fully convolutional neural networks. Our model, FullSleepNet, accepts a full-night single-channel EEG signal as input and produces segmentation masks for arousal and sleep stage labels. FullSleepNet comprises four modules: a convolutional module to extract local features, a recurrent module to capture long-range dependencies, an attention mechanism to focus on relevant parts of the input, and a segmentation module to output final predictions.Main results.By unifying the two interrelated tasks as segmentation problems and employing a multi-task learning approach, FullSleepNet achieves state-of-the-art performance for arousal detection with an area under the precision-recall curve of 0.70 on Sleep Heart Health Study and Multi-Ethnic Study of Atherosclerosis datasets. For sleep stage classification, FullSleepNet obtains comparable performance on both datasets, achieving an accuracy of 0.88 and an F1-score of 0.80 on the former and an accuracy of 0.83 and an F1-score of 0.76 on the latter.Significance. Our results demonstrate that FullSleepNet offers improved practicality, efficiency, and accuracy for the detection of arousal and classification of sleep stages using raw EEG signals as input.
Collapse
Affiliation(s)
- Hasan Zan
- Vocational School, Mardin Artuklu University, Mardin, Turkey
| | - Abdulnasır Yildiz
- Department of Electrical and Electronics Engineering, Dicle University, Diyarbakir, Turkey
| |
Collapse
|
19
|
Vaquerizo-Villar F, Gutiérrez-Tobal GC, Calvo E, Álvarez D, Kheirandish-Gozal L, Del Campo F, Gozal D, Hornero R. An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea. Comput Biol Med 2023; 165:107419. [PMID: 37703716 DOI: 10.1016/j.compbiomed.2023.107419] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2023] [Revised: 07/26/2023] [Accepted: 08/28/2023] [Indexed: 09/15/2023]
Abstract
Automatic deep-learning models used for sleep scoring in children with obstructive sleep apnea (OSA) are perceived as black boxes, limiting their implementation in clinical settings. Accordingly, we aimed to develop an accurate and interpretable deep-learning model for sleep staging in children using single-channel electroencephalogram (EEG) recordings. We used EEG signals from the Childhood Adenotonsillectomy Trial (CHAT) dataset (n = 1637) and a clinical sleep database (n = 980). Three distinct deep-learning architectures were explored to automatically classify sleep stages from a single-channel EEG data. Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable artificial intelligence (XAI) algorithm, was then applied to provide an interpretation of the singular EEG patterns contributing to each predicted sleep stage. Among the tested architectures, a standard convolutional neural network (CNN) demonstrated the highest performance for automated sleep stage detection in the CHAT test set (accuracy = 86.9% and five-class kappa = 0.827). Furthermore, the CNN-based estimation of total sleep time exhibited strong agreement in the clinical dataset (intra-class correlation coefficient = 0.772). Our XAI approach using Grad-CAM effectively highlighted the EEG features associated with each sleep stage, emphasizing their influence on the CNN's decision-making process in both datasets. Grad-CAM heatmaps also allowed to identify and analyze epochs within a recording with a highly likelihood to be misclassified, revealing mixed features from different sleep stages within these epochs. Finally, Grad-CAM heatmaps unveiled novel features contributing to sleep scoring using a single EEG channel. Consequently, integrating an explainable CNN-based deep-learning model in the clinical environment could enable automatic sleep staging in pediatric sleep apnea tests.
Collapse
Affiliation(s)
- Fernando Vaquerizo-Villar
- Biomedical Engineering Group, University of Valladolid, Valladolid, Spain; CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, Valladolid, Spain.
| | - Gonzalo C Gutiérrez-Tobal
- Biomedical Engineering Group, University of Valladolid, Valladolid, Spain; CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, Valladolid, Spain
| | - Eva Calvo
- Biomedical Engineering Group, University of Valladolid, Valladolid, Spain
| | - Daniel Álvarez
- Biomedical Engineering Group, University of Valladolid, Valladolid, Spain; CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, Valladolid, Spain; Sleep-Ventilation Unit, Pneumology Department, Río Hortega University Hospital, Valladolid, Spain
| | - Leila Kheirandish-Gozal
- Departments of Neurology and Child Health and Child Health Research Institute, The University of Missouri School of Medicine, Columbia, MO, USA
| | - Félix Del Campo
- Biomedical Engineering Group, University of Valladolid, Valladolid, Spain; CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, Valladolid, Spain; Sleep-Ventilation Unit, Pneumology Department, Río Hortega University Hospital, Valladolid, Spain
| | - David Gozal
- Office of The Dean, Joan C. Edwards School of Medicine, Marshall University, 1600 Medical Center Dr, Huntington, WV, 25701, USA
| | - Roberto Hornero
- Biomedical Engineering Group, University of Valladolid, Valladolid, Spain; CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, Valladolid, Spain
| |
Collapse
|
20
|
Li T, Gong Y, Lv Y, Wang F, Hu M, Wen Y. GAC-SleepNet: A dual-structured sleep staging method based on graph structure and Euclidean structure. Comput Biol Med 2023; 165:107477. [PMID: 37717528 DOI: 10.1016/j.compbiomed.2023.107477] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 08/16/2023] [Accepted: 09/04/2023] [Indexed: 09/19/2023]
Abstract
Sleep staging is a precondition for the diagnosis and treatment of sleep disorders. However, how to fully exploit the relationship between spatial features of the brain and sleep stages is an important task. Many current classical algorithms only extract the characteristic information of the brain in the Euclidean space without considering other spatial structures. In this study, a sleep staging network named GAC-SleepNet is designed. GAC-SleepNet uses the characteristic information in the dual structure of the graph structure and the Euclidean structure for the classification of sleep stages. In the graph structure, this study uses a graph convolutional neural network to learn the deep features of each sleep stage and converts the features in the topological structure into feature vectors by a multilayer perceptron. In the Euclidean structure, this study uses convolutional neural networks to learn the temporal features of sleep information and combine attention mechanism to portray the connection between different sleep periods and EEG signals, while enhancing the description of global features to avoid local optima. In this study, the performance of the proposed network is evaluated on two public datasets. The experimental results show that the dual spatial structure captures more adequate and comprehensive information about sleep features and shows advancement in terms of different evaluation metrics.
Collapse
Affiliation(s)
- Tianxing Li
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130000, China
| | - Yulin Gong
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130000, China.
| | - Yudan Lv
- The Department of Neurology, First Hospital of Jilin University, Changchun, 130000, China
| | - Fatong Wang
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130000, China
| | - Mingjia Hu
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130000, China
| | - Yinke Wen
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130000, China
| |
Collapse
|
21
|
Phan H, Lorenzen KP, Heremans E, Chen OY, Tran MC, Koch P, Mertins A, Baumert M, Mikkelsen KB, De Vos M. L-SeqSleepNet: Whole-cycle Long Sequence Modeling for Automatic Sleep Staging. IEEE J Biomed Health Inform 2023; 27:4748-4757. [PMID: 37552591 DOI: 10.1109/jbhi.2023.3303197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/10/2023]
Abstract
Human sleep is cyclical with a period of approximately 90 minutes, implying long temporal dependency in the sleep data. Yet, exploring this long-term dependency when developing sleep staging models has remained untouched. In this work, we show that while encoding the logic of a whole sleep cycle is crucial to improve sleep staging performance, the sequential modelling approach in existing state-of-the-art deep learning models are inefficient for that purpose. We thus introduce a method for efficient long sequence modelling and propose a new deep learning model, L-SeqSleepNet, which takes into account whole-cycle sleep information for sleep staging. Evaluating L-SeqSleepNet on four distinct databases of various sizes, we demonstrate state-of-the-art performance obtained by the model over three different EEG setups, including scalp EEG in conventional Polysomnography (PSG), in-ear EEG, and around-the-ear EEG (cEEGrid), even with a single EEG channel input. Our analyses also show that L-SeqSleepNet is able to alleviate the predominance of N2 sleep (the major class in terms of classification) to bring down errors in other sleep stages. Moreover the network becomes much more robust, meaning that for all subjects where the baseline method had exceptionally poor performance, their performance are improved significantly. Finally, the computation time only grows at a sub-linear rate when the sequence length increases.
Collapse
|
22
|
Li W, Gao J. Automatic sleep staging by a hybrid model based on deep 1D-ResNet-SE and LSTM with single-channel raw EEG signals. PeerJ Comput Sci 2023; 9:e1561. [PMID: 37810362 PMCID: PMC10557479 DOI: 10.7717/peerj-cs.1561] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2023] [Accepted: 08/10/2023] [Indexed: 10/10/2023]
Abstract
Sleep staging is crucial for assessing sleep quality and diagnosing sleep disorders. Recent advances in deep learning methods with electroencephalogram (EEG) signals have shown remarkable success in automatic sleep staging. However, the use of deeper neural networks may lead to the issues of gradient disappearance and explosion, while the non-stationary nature and low signal-to-noise ratio of EEG signals can negatively impact feature representation. To overcome these challenges, we proposed a novel lightweight sequence-to-sequence deep learning model, 1D-ResNet-SE-LSTM, to classify sleep stages into five classes using single-channel raw EEG signals. Our proposed model consists of two main components: a one-dimensional residual convolutional neural network with a squeeze-and-excitation module to extract and reweight features from EEG signals, and a long short-term memory network to capture the transition rules among sleep stages. In addition, we applied the weighted cross-entropy loss function to alleviate the class imbalance problem. We evaluated the performance of our model on two publicly available datasets; Sleep-EDF Expanded consists of 153 overnight PSG recordings collected from 78 healthy subjects and ISRUC-Sleep includes 100 PSG recordings collected from 100 subjects diagnosed with various sleep disorders, and obtained an overall accuracy rate of 86.39% and 81.97%, respectively, along with corresponding macro average F1-scores of 81.95% and 79.94%. Our model outperforms existing sleep staging models in terms of overall performance metrics and per-class F1-scores for several sleep stages, particularly for the N1 stage, where it achieves F1-scores of 59.00% and 55.53%. The kappa coefficient is 0.812 and 0.766 for the Sleep-EDF Expanded and ISRUC-Sleep datasets, respectively, indicating strong agreement with certified sleep experts. We also investigated the effect of different weight coefficient combinations and sequence lengths of EEG epochs used as input to the model on its performance. Furthermore, the ablation study was conducted to evaluate the contribution of each component to the model's performance. The results demonstrate the effectiveness and robustness of the proposed model in classifying sleep stages, and highlights its potential to reduce human clinicians' workload, making sleep assessment and diagnosis more effective. However, the proposed model is subject to several limitations. Firstly, the model is a sequence-to-sequence network, which requires input sequences of EEG epochs. Secondly, the weight coefficients in the loss function could be further optimized to balance the classification performance of each sleep stage. Finally, apart from the channel attention mechanism, incorporating more advanced attention mechanisms could enhance the model's effectiveness.
Collapse
Affiliation(s)
- Weiming Li
- Shanghai Nuanhe Brain Technology Co. Ltd., Shanghai, China
| | - Junhui Gao
- Shanghai Nuanhe Brain Technology Co. Ltd., Shanghai, China
| |
Collapse
|
23
|
Wang J, Zhao S, Zhou Y, Jiang H, Yu Z, Li T, Li S, Pan G. Narcolepsy Diagnosis With Sleep Stage Features Using PSG Recordings. IEEE Trans Neural Syst Rehabil Eng 2023; 31:3619-3629. [PMID: 37672382 DOI: 10.1109/tnsre.2023.3312396] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/08/2023]
Abstract
Narcolepsy is a sleep disorder affecting millions of people worldwide and causes serious public health problems. It is hard for doctors to correctly and objectively diagnose narcolepsy. Polysomnography (PSG) recordings, a gold standard for sleep monitoring and quality measurement, can provide abundant and objective cues for the narcolepsy diagnosis. There have been some studies on automatic narcolepsy diagnosis using PSG recordings. However, the sleep stage information, an important cue for narcolepsy diagnosis, has not been fully utilized. For example, some studies have not considered the sleep stage information to diagnose narcolepsy. Although some studies consider the sleep stage information, the stages are manually scored by experts, which is time-consuming and subjective. And the framework using sleep stages scored automatically for narcolepsy diagnosis is designed in a two-phase learning manner, where sleep staging in the first phase and diagnosis in the second phase, causing cumulative error and degrading the performance. To address these challenges, we propose a novel end-to-end framework for automatic narcolepsy diagnosis using PSG recordings. In particular, adopting the idea of multi-task learning, we take the sleep staging as our auxiliary task, and then combine the sleep stage related features with narcolepsy related features for our primary task of narcolepsy diagnosis. We collected a dataset of PSG recordings from 77 participants and evaluated our framework on it. Both of the sleep stage features and the end-to-end fashion contribute to diagnosis performance. Moreover, we do a comprehensive analysis on the relationship between sleep stages and narcolepsy, correlation of different channels, predictive ability of different sensing data, and diagnosis results in subject level.
Collapse
|
24
|
Muto V, Berthomier C. Looking for a balance between visual and automatic sleep scoring. NPJ Digit Med 2023; 6:165. [PMID: 37670135 PMCID: PMC10480143 DOI: 10.1038/s41746-023-00915-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2023] [Accepted: 08/22/2023] [Indexed: 09/07/2023] Open
Affiliation(s)
- Vincenzo Muto
- GIGA CRC In Vivo Imaging, Université de Liège, Liège, Belgium.
| | | |
Collapse
|
25
|
Dai Y, Li X, Liang S, Wang L, Duan Q, Yang H, Zhang C, Chen X, Li L, Li X, Liao X. MultiChannelSleepNet: A Transformer-Based Model for Automatic Sleep Stage Classification With PSG. IEEE J Biomed Health Inform 2023; 27:4204-4215. [PMID: 37289607 DOI: 10.1109/jbhi.2023.3284160] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Automatic sleep stage classification plays an essential role in sleep quality measurement and sleep disorder diagnosis. Although many approaches have been developed, most use only single-channel electroencephalogram signals for classification. Polysomnography (PSG) provides multiple channels of signal recording, enabling the use of the appropriate method to extract and integrate the information from different channels to achieve higher sleep staging performance. We present a transformer encoder-based model, MultiChannelSleepNet, for automatic sleep stage classification with multichannel PSG data, whose architecture is implemented based on the transformer encoder for single-channel feature extraction and multichannel feature fusion. In a single-channel feature extraction block, transformer encoders extract features from time-frequency images of each channel independently. Based on our integration strategy, the feature maps extracted from each channel are fused in the multichannel feature fusion block. Another set of transformer encoders further capture joint features, and a residual connection preserves the original information from each channel in this block. Experimental results on three publicly available datasets demonstrate that our method achieves higher classification performance than state-of-the-art techniques. MultiChannelSleepNet is an efficient method to extract and integrate the information from multichannel PSG data, which facilitates precision sleep staging in clinical applications.
Collapse
|
26
|
Abstract
Automatic polysomnography analysis can be leveraged to shorten scoring times, reduce associated costs, and ultimately improve the overall diagnosis of sleep disorders. Multiple and diverse strategies have been attempted for implementation of this technology at scale in the routine workflow of sleep centers. The field, however, is complex and presents unsolved challenges in a number of areas. Recent developments in computer science and artificial intelligence are nevertheless closing the gap. Technological advances are also opening new pathways for expanding our current understanding of the domain and its analysis.
Collapse
Affiliation(s)
- Diego Alvarez-Estevez
- Center for Information and Communications Technology Research (CITIC), Universidade da Coruña, 15071 A Coruña, Spain.
| |
Collapse
|
27
|
Yao H, Liu T, Zou R, Ding S, Xu Y. A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification. IEEE Trans Neural Syst Rehabil Eng 2023; 31:3353-3362. [PMID: 37578925 DOI: 10.1109/tnsre.2023.3305201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/16/2023]
Abstract
Sleep stage classification is a fundamental task in diagnosing and monitoring sleep diseases. There are 2 challenges that remain open: (1) Since most methods only rely on input from a single channel, the spatial-temporal relationship of sleep signals has not been fully explored. (2) Lack of sleep data makes models hard to train from scratch. Here, we propose a vision Transformer-based architecture to process multi-channel polysomnogram signals. The method is an end-to-end framework that consists of a spatial encoder, a temporal encoder, and an MLP head classifier. The spatial encoder using a pre-trained Vision Transformer captures spatial information from multiple PSG channels. The temporal encoder utilizing the self-attention mechanism understands transitions between nearby epochs. In addition, we introduce a tailored image generation method to extract features within multi-channel and reshape them for transfer learning. We validate our method on 3 datasets and outperform the state-of-the-art algorithms. Our method fully explores the spatial-temporal relationship among different brain regions and addresses the problem of data insufficiency in clinical environments. Benefiting from reformulating the problem as image classification, the method could be applied to other 1D-signal problems in the future.
Collapse
|
28
|
Gaiduk M, Serrano Alarcón Á, Seepold R, Martínez Madrid N. Current status and prospects of automatic sleep stages scoring: Review. Biomed Eng Lett 2023; 13:247-272. [PMID: 37519865 PMCID: PMC10382458 DOI: 10.1007/s13534-023-00299-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Revised: 06/07/2023] [Accepted: 06/18/2023] [Indexed: 08/01/2023] Open
Abstract
The scoring of sleep stages is one of the essential tasks in sleep analysis. Since a manual procedure requires considerable human and financial resources, and incorporates some subjectivity, an automated approach could result in several advantages. There have been many developments in this area, and in order to provide a comprehensive overview, it is essential to review relevant recent works and summarise the characteristics of the approaches, which is the main aim of this article. To achieve it, we examined articles published between 2018 and 2022 that dealt with the automated scoring of sleep stages. In the final selection for in-depth analysis, 125 articles were included after reviewing a total of 515 publications. The results revealed that automatic scoring demonstrates good quality (with Cohen's kappa up to over 0.80 and accuracy up to over 90%) in analysing EEG/EEG + EOG + EMG signals. At the same time, it should be noted that there has been no breakthrough in the quality of results using these signals in recent years. Systems involving other signals that could potentially be acquired more conveniently for the user (e.g. respiratory, cardiac or movement signals) remain more challenging in the implementation with a high level of reliability but have considerable innovation capability. In general, automatic sleep stage scoring has excellent potential to assist medical professionals while providing an objective assessment.
Collapse
Affiliation(s)
- Maksym Gaiduk
- HTWG Konstanz – University of Applied Sciences, Alfred-Wachtel-Str.8, 78462 Konstanz, Germany
| | | | - Ralf Seepold
- HTWG Konstanz – University of Applied Sciences, Alfred-Wachtel-Str.8, 78462 Konstanz, Germany
| | | |
Collapse
|
29
|
Liu G, Wei G, Sun S, Mao D, Zhang J, Zhao D, Tian X, Wang X, Chen N. Micro SleepNet: efficient deep learning model for mobile terminal real-time sleep staging. Front Neurosci 2023; 17:1218072. [PMID: 37575302 PMCID: PMC10416229 DOI: 10.3389/fnins.2023.1218072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2023] [Accepted: 07/07/2023] [Indexed: 08/15/2023] Open
Abstract
The real-time sleep staging algorithm that can perform inference on mobile devices without burden is a prerequisite for closed-loop sleep modulation. However, current deep learning sleep staging models have poor real-time efficiency and redundant parameters. We propose a lightweight and high-performance sleep staging model named Micro SleepNet, which takes a 30-s electroencephalography (EEG) epoch as input, without relying on contextual signals. The model features a one-dimensional group convolution with a kernel size of 1 × 3 and an Efficient Channel and Spatial Attention (ECSA) module for feature extraction and adaptive recalibration. Moreover, the model efficiently performs feature fusion using dilated convolution module and replaces the conventional fully connected layer with Global Average Pooling (GAP). These design choices significantly reduce the total number of model parameters to 48,226, with only approximately 48.95 Million Floating-point Operations per Second (MFLOPs) computation. The proposed model is conducted subject-independent cross-validation on three publicly available datasets, achieving an overall accuracy of up to 83.3%, and the Cohen Kappa is 0.77. Additionally, we introduce Class Activation Mapping (CAM) to visualize the model's attention to EEG waveforms, which demonstrate the model's ability to accurately capture feature waveforms of EEG at different sleep stages. This provides a strong interpretability foundation for practical applications. Furthermore, the Micro SleepNet model occupies approximately 100 KB of memory on the Android smartphone and takes only 2.8 ms to infer one EEG epoch, meeting the real-time requirements of sleep staging tasks on mobile devices. Consequently, our proposed model has the potential to serve as a foundation for accurate closed-loop sleep modulation.
Collapse
Affiliation(s)
- Guisong Liu
- Department of Biomedical Engineering, Bioengineering College, Chongqing University, Chongqing, China
| | - Guoliang Wei
- Department of Biomedical Engineering, Bioengineering College, Chongqing University, Chongqing, China
| | - Shuqing Sun
- Department of Biomedical Engineering, Bioengineering College, Chongqing University, Chongqing, China
| | - Dandan Mao
- Department of Sleep and Psychology, Institute of Surgery Research, Daping Hospital, Third Military Medical University (Army Medical University), Chongqing, China
| | - Jiansong Zhang
- School of Medicine, Huaqiao University, Quanzhou, Fujian, China
| | - Dechun Zhao
- College of Bioinformatics, Chongqing University of Posts and Telecommunications, Chongqing, China
| | - Xuelong Tian
- Department of Biomedical Engineering, Bioengineering College, Chongqing University, Chongqing, China
| | - Xing Wang
- Department of Biomedical Engineering, Bioengineering College, Chongqing University, Chongqing, China
| | - Nanxi Chen
- Department of Biomedical Engineering, Bioengineering College, Chongqing University, Chongqing, China
| |
Collapse
|
30
|
Chen J, Zhang Y, Pan Y, Xu P, Guan C. A transformer-based deep neural network model for SSVEP classification. Neural Netw 2023; 164:521-534. [PMID: 37209444 DOI: 10.1016/j.neunet.2023.04.045] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 03/24/2023] [Accepted: 04/26/2023] [Indexed: 05/22/2023]
Abstract
Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signals in the brain-computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data becomes urgent. In recent years, developing the methods that can work in inter-subject scenario has become a promising new direction. As a popular deep learning model nowadays, Transformer has been used in EEG signal classification tasks owing to its excellent performance. Therefore, in this study, we proposed a deep learning model for SSVEP classification based on Transformer architecture in inter-subject scenario, termed as SSVEPformer, which was the first application of Transformer on the SSVEP classification. Inspired by previous studies, we adopted the complex spectrum features of SSVEP data as the model input, which could enable the model to simultaneously explore the spectral and spatial information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) was proposed to improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12 targets; Dataset 2: 35 subjects, 40 targets). The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate than other baseline methods. The proposed models validate the feasibility of deep learning models based on Transformer architecture for SSVEP data classification, and could serve as potential models to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.
Collapse
Affiliation(s)
- Jianbo Chen
- School of Computer Science and Technology, Laboratory for Brain Science and Medical Artificial Intelligence, Southwest University of Science and Technology, Mianyang, China
| | - Yangsong Zhang
- School of Computer Science and Technology, Laboratory for Brain Science and Medical Artificial Intelligence, Southwest University of Science and Technology, Mianyang, China; MOE Key Laboratory for NeuroInformation, Clinical Hospital of Chengdu Brain Science Institute, and Center for Information in BioMedicine, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China.
| | - Yudong Pan
- School of Computer Science and Technology, Laboratory for Brain Science and Medical Artificial Intelligence, Southwest University of Science and Technology, Mianyang, China
| | - Peng Xu
- MOE Key Laboratory for NeuroInformation, Clinical Hospital of Chengdu Brain Science Institute, and Center for Information in BioMedicine, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China.
| | - Cuntai Guan
- School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore
| |
Collapse
|
31
|
Lin JD, Han YH, Huang PH, Tan J, Chen JC, Tanveer M, Hua KL. DEFAEK: Domain Effective Fast Adaptive Network for Face Anti-Spoofing. Neural Netw 2023; 161:83-91. [PMID: 36736002 DOI: 10.1016/j.neunet.2023.01.018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Revised: 12/24/2022] [Accepted: 01/18/2023] [Indexed: 01/26/2023]
Abstract
Existing deep learning based face anti-spoofing (FAS) or deepfake detection approaches usually rely on large-scale datasets and powerful networks with significant amount of parameters to achieve satisfactory performance. However, these make them resource-heavy and unsuitable for handheld devices. Moreover, they are limited by the types of spoof in the dataset they train on and require considerable training time. To produce a robust FAS model, they need large datasets covering the widest variety of predefined presentation attacks possible. Testing on new or unseen attacks or environments generally results in poor performance. Ideally, the FAS model should learn discriminative features that can generalize well even on unseen spoof types. In this paper, we propose a fast learning approach called Domain Effective Fast Adaptive nEt-worK (DEFAEK), a face anti-spoofing approach based on the optimization-based meta-learning paradigm that effectively and quickly adapts to new tasks. DEFAEK treats differences in an environment as domains and simulates multiple domain shifts during training. To further improve the effectiveness and efficiency of meta-learning, we adopt the metric learning in the inner loop update with careful sample selection. With extensive experiments on the challenging CelebA-Spoof and FaceForensics++ datasets, the evaluation results show that DEFAEK can learn cues independent of the environment with good generalization capability. In addition, the resulting model is lightweight following the design principle of modern lightweight network architecture and still generalizes well on unseen classes. In addition, we also demonstrate our model's capabilities by comparing the numbers of parameters, FLOPS, and model performance with other state-of-the-art methods.
Collapse
Affiliation(s)
- Jiun-Da Lin
- Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, 106335, Taiwan, ROC; Research Center for Information Technology Innovation, Academia Sinica, Taipei, 115201, Taiwan, ROC.
| | - Yue-Hua Han
- Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, 106335, Taiwan, ROC; Research Center for Information Technology Innovation, Academia Sinica, Taipei, 115201, Taiwan, ROC.
| | - Po-Han Huang
- Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, 106335, Taiwan, ROC; Research Center for Information Technology Innovation, Academia Sinica, Taipei, 115201, Taiwan, ROC.
| | - Julianne Tan
- Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, 106335, Taiwan, ROC.
| | - Jun-Cheng Chen
- Research Center for Information Technology Innovation, Academia Sinica, Taipei, 115201, Taiwan, ROC.
| | - M Tanveer
- Department of Mathematics, Indian Institute of Technology Indore, Simrol, 453552, India.
| | - Kai-Lung Hua
- Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, 106335, Taiwan, ROC.
| |
Collapse
|
32
|
Aristimunha B, Bayerlein AJ, Cardoso MJ, Pinaya WHL, De Camargo RY. Sleep-Energy: An Energy Optimization Method to Sleep Stage Scoring. IEEE ACCESS : PRACTICAL INNOVATIONS, OPEN SOLUTIONS 2023; 11:34595-34602. [PMID: 38292346 PMCID: PMC10824396 DOI: 10.1109/access.2023.3263477] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Accepted: 03/17/2023] [Indexed: 02/01/2024]
Abstract
Sleep is essential for physical and mental health. Polysomnography (PSG) procedures are labour-intensive and time-consuming, making diagnosing sleep disorders difficult. Automatic sleep staging using Machine Learning (ML) - based methods has been studied extensively, but frequently provides noisier predictions incompatible with typical manually annotated hypnograms. We propose an energy optimization method to improve the quality of hypnograms generated by automatic sleep staging procedures. The method evaluates the system's total energy based on conditional probabilities for each epoch's stage and employs an energy minimisation procedure. It can be used as a meta-optimisation layer over the sleep stage sequences generated by any classifier that generates prediction probabilities. The method improved the accuracy of state-of-the-art Deep Learning models in the Sleep EDFx dataset by 4.0% and in the DRM-SUB dataset by 2.8%.
Collapse
Affiliation(s)
- Bruno Aristimunha
- Center for Mathematics, Computing and Cognition (CMCC)Federal University of ABC (UFABC)São Paulo09210-580Brazil
- Department of Biomedical EngineeringSchool of Biomedical Engineering and Imaging SciencesKing's College LondonWC2R 2LSLondonU.K
| | - Alexandre Janoni Bayerlein
- Center for Mathematics, Computing and Cognition (CMCC)Federal University of ABC (UFABC)São Paulo09210-580Brazil
| | - M. Jorge Cardoso
- Department of Biomedical EngineeringSchool of Biomedical Engineering and Imaging SciencesKing's College LondonWC2R 2LSLondonU.K
| | - Walter Hugo Lopez Pinaya
- Department of Biomedical EngineeringSchool of Biomedical Engineering and Imaging SciencesKing's College LondonWC2R 2LSLondonU.K
| | | |
Collapse
|
33
|
Do not sleep on traditional machine learning. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104429] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
|
34
|
Chen Z, Yang Z, Wang D, Zhu X, Ono N, Altaf-Ul-Amin MD, Kanaya S, Huang M. Sleep Staging Framework with Physiologically Harmonized Sub-Networks. Methods 2023; 209:18-28. [PMID: 36436760 DOI: 10.1016/j.ymeth.2022.11.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Revised: 11/15/2022] [Accepted: 11/21/2022] [Indexed: 11/26/2022] Open
Abstract
Sleep screening is an important tool for both healthcare and neuroscientific research. Automatic sleep scoring is an alternative to the time-consuming gold-standard manual scoring procedure. Recently there have seen promising results on automatic stage scoring by extracting spatio-temporal features via deep neural networks from electroencephalogram (EEG). However, such methods fail to consistently yield good performance due to a missing piece in data representation: the medical criterion of the sleep scoring task on top of EEG features. We argue that capturing stage-specific features that satisfy the criterion of sleep medicine is non-trivial for automatic sleep scoring. This paper considers two criteria: Transient stage marker and Overall profile of EEG features, then we propose a physiologically meaningful framework for sleep stage scoring via mixed deep neural networks. The framework consists of two sub-networks: feature extraction networks, constructed in consideration of the physiological characteristics of sleep, and an attention-based scoring decision network. Moreover, we quantize the framework for potential use under an IoT setting. For proof-of-concept, the performance of the proposed framework is demonstrated by introducing multiple sleep datasets with the largest comprising 42,560 h recorded from 5,793 subjects. From the experiment results, the proposed method achieves a competitive stage scoring performance, especially for Wake, N2, and N3, with higher F1 scores of 0.92, 0.86, and 0.88, respectively. Moreover, the feasibility analysis of framework quantization provides a potential for future implementation in the edge computing field and clinical settings.
Collapse
Affiliation(s)
- Zheng Chen
- Graduate School of Engineering Science, Osaka University, Japan.
| | - Ziwei Yang
- Graduate School of Science and Technology, Nara Institute of Science and Technology, Japan
| | - Dong Wang
- Graduate School and Faculty of Information Science and Electrical Engineering, Kyushu University, Japan
| | - Xin Zhu
- Biomedical Information Engineering Lab, The University of Aizu, Japan
| | - Naoaki Ono
- Graduate School of Science and Technology, Nara Institute of Science and Technology, Japan; Data Science Center, Nara Insitute of Science and Technology, Japan
| | - M D Altaf-Ul-Amin
- Graduate School of Science and Technology, Nara Institute of Science and Technology, Japan
| | - Shigehiko Kanaya
- Graduate School of Science and Technology, Nara Institute of Science and Technology, Japan; Data Science Center, Nara Insitute of Science and Technology, Japan
| | - Ming Huang
- Graduate School of Science and Technology, Nara Institute of Science and Technology, Japan; Data Science Center, Nara Insitute of Science and Technology, Japan.
| |
Collapse
|
35
|
Somaskandhan P, Leppänen T, Terrill PI, Sigurdardottir S, Arnardottir ES, Ólafsdóttir KA, Serwatko M, Sigurðardóttir SÞ, Clausen M, Töyräs J, Korkalainen H. Deep learning-based algorithm accurately classifies sleep stages in preadolescent children with sleep-disordered breathing symptoms and age-matched controls. Front Neurol 2023; 14:1162998. [PMID: 37122306 PMCID: PMC10140398 DOI: 10.3389/fneur.2023.1162998] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Accepted: 03/23/2023] [Indexed: 05/02/2023] Open
Abstract
Introduction Visual sleep scoring has several shortcomings, including inter-scorer inconsistency, which may adversely affect diagnostic decision-making. Although automatic sleep staging in adults has been extensively studied, it is uncertain whether such sophisticated algorithms generalize well to different pediatric age groups due to distinctive EEG characteristics. The preadolescent age group (10-13-year-olds) is relatively understudied, and thus, we aimed to develop an automatic deep learning-based sleep stage classifier specifically targeting this cohort. Methods A dataset (n = 115) containing polysomnographic recordings of Icelandic preadolescent children with sleep-disordered breathing (SDB) symptoms, and age and sex-matched controls was utilized. We developed a combined convolutional and long short-term memory neural network architecture relying on electroencephalography (F4-M1), electrooculography (E1-M2), and chin electromyography signals. Performance relative to human scoring was further evaluated by analyzing intra- and inter-rater agreements in a subset (n = 10) of data with repeat scoring from two manual scorers. Results The deep learning-based model achieved an overall cross-validated accuracy of 84.1% (Cohen's kappa κ = 0.78). There was no meaningful performance difference between SDB-symptomatic (n = 53) and control subgroups (n = 52) [83.9% (κ = 0.78) vs. 84.2% (κ = 0.78)]. The inter-rater reliability between manual scorers was 84.6% (κ = 0.78), and the automatic method reached similar agreements with scorers, 83.4% (κ = 0.76) and 82.7% (κ = 0.75). Conclusion The developed algorithm achieved high classification accuracy and substantial agreements with two manual scorers; the performance metrics compared favorably with typical inter-rater reliability between manual scorers and performance reported in previous studies. These suggest that our algorithm may facilitate less labor-intensive and reliable automatic sleep scoring in preadolescent children.
Collapse
Affiliation(s)
- Pranavan Somaskandhan
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD, Australia
- *Correspondence: Pranavan Somaskandhan,
| | - Timo Leppänen
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD, Australia
- Department of Technical Physics, University of Eastern Finland, Kuopio, Finland
- Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| | - Philip I. Terrill
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD, Australia
| | - Sigridur Sigurdardottir
- Reykjavik University Sleep Institute, School of Technology, Reykjavik University, Reykjavik, Iceland
| | - Erna Sif Arnardottir
- Reykjavik University Sleep Institute, School of Technology, Reykjavik University, Reykjavik, Iceland
- Internal Medicine Services, Landspitali–The National University Hospital of Iceland, Reykjavik, Iceland
| | - Kristín A. Ólafsdóttir
- Reykjavik University Sleep Institute, School of Technology, Reykjavik University, Reykjavik, Iceland
| | - Marta Serwatko
- Department of Clinical Engineering, Landspitali University Hospital, Reykjavik, Iceland
| | - Sigurveig Þ. Sigurðardóttir
- Department of Immunology, Landspitali University Hospital, Reykjavik, Iceland
- Faculty of Medicine, University of Iceland, Reykjavik, Iceland
| | - Michael Clausen
- Department of Allergy, Landspitali University Hospital, Reykjavik, Iceland
- Children's Hospital Reykjavik, Reykjavik, Iceland
| | - Juha Töyräs
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD, Australia
- Department of Technical Physics, University of Eastern Finland, Kuopio, Finland
- Science Service Center, Kuopio University Hospital, Kuopio, Finland
| | - Henri Korkalainen
- Department of Technical Physics, University of Eastern Finland, Kuopio, Finland
- Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland
| |
Collapse
|
36
|
Xie Z, Yang Y, Zhang Y, Wang J, Du S. Deep learning on multi-view sequential data: a survey. Artif Intell Rev 2022; 56:6661-6704. [PMID: 36466765 PMCID: PMC9707228 DOI: 10.1007/s10462-022-10332-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/02/2022]
Abstract
With the progress of human daily interaction activities and the development of industrial society, a large amount of media data and sensor data become accessible. Humans collect these multi-source data in chronological order, called multi-view sequential data (MvSD). MvSD has numerous potential application domains, including intelligent transportation, climate science, health care, public safety and multimedia, etc. However, as the volume and scale of MvSD increases, the traditional machine learning methods become difficult to withstand such large-scale data, and it is no longer appropriate to use hand-craft features to represent these complex data. In addition, there is no general framework in the process of mining multi-view relationships and integrating multi-view information. In this paper, We first introduce four common data types that constitute MvSD, including point data, sequence data, graph data, and raster data. Then, we summarize the technical challenges of MvSD. Subsequently, we review the recent progress in deep learning technology applied to MvSD. Meanwhile, we discuss how the network represents and learns features of MvSD. Finally, we summarize the applications of MvSD in different domains and give potential research directions.
Collapse
Affiliation(s)
- Zhuyang Xie
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756 China
- Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory, Southwest Jiaotong University, Chengdu, 611756 China
| | - Yan Yang
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756 China
- Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory, Southwest Jiaotong University, Chengdu, 611756 China
| | - Yiling Zhang
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756 China
- Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory, Southwest Jiaotong University, Chengdu, 611756 China
| | - Jie Wang
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756 China
- Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory, Southwest Jiaotong University, Chengdu, 611756 China
| | - Shengdong Du
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756 China
- Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory, Southwest Jiaotong University, Chengdu, 611756 China
| |
Collapse
|
37
|
Shen N, Luo T, Chen C, Zhang Y, Zhu H, Zhou Y, Wang Y, Chen W. Towards an automatic narcolepsy detection on ambiguous sleep staging and sleep transition dynamics joint model. J Neural Eng 2022; 19. [PMID: 36001951 DOI: 10.1088/1741-2552/ac8c6b] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2022] [Accepted: 08/24/2022] [Indexed: 11/11/2022]
Abstract
Objective.Mixing/dissociation of sleep stages in narcolepsy adds to the difficulty in automatic sleep staging. Moreover, automatic analytical studies for narcolepsy and multiple sleep latency test (MSLT) have only done automatic sleep staging without leveraging the sleep stage profile for further patient identification. This study aims to establish an automatic narcolepsy detection method for MSLT.Approach.We construct a two-phase model on MSLT recordings, where ambiguous sleep staging and sleep transition dynamics make joint efforts to address this issue. In phase 1, we extract representative features from electroencephalogram (EEG) and electrooculogram (EOG) signals. Then, the features are input to an EasyEnsemble classifier for automatic sleep staging. In phase 2, we investigate sleep transition dynamics, including sleep stage transitions and sleep stages, and output likelihood of narcolepsy by virtue of principal component analysis (PCA) and a logistic regression classifier. To demonstrate the proposed framework in clinical application, we conduct experiments on 24 participants from our hospital, considering ten patients with narcolepsy and fourteen patients with MSLT negative.Main results.Applying the two-phase leave-one-subject-out testing scheme, the model reaches an accuracy, sensitivity, and specificity of 87.5%, 80.0%, and 92.9% for narcolepsy detection. Influenced by disease pathology, accuracy of automatic sleep staging in narcolepsy appears to decrease compared to that in the non-narcoleptic population.Significance.This method can automatically and efficiently distinguish patients with narcolepsy based on MSLT. It probes into the amalgamation of automatic sleep staging and sleep transition dynamics for narcolepsy detection, which would assist clinic and neuroelectrophysiology specialists in visual interpretation and diagnosis.
Collapse
Affiliation(s)
- Ning Shen
- Fudan University School of Information Science and Engineering, 220 Handan Road, Yangpu District, Shanghai, China, 2005 Songhu Road, Yangpu District, Shanghai, China, Shanghai, 200433, CHINA
| | - Tian Luo
- Department of Neurology, Children's Hospital of Fudan University, 399 Wanyuan Road, Minhang District, Shanghai, China, Shanghai, 201102, CHINA
| | - Chen Chen
- Fudan University Human Phenome Institute, 825 Zhangheng Road, Pudong District, Shanghai, China, Shanghai, 201203, CHINA
| | - Yanjiong Zhang
- Department of Neurology, Children's Hospital of Fudan University, 399 Wanyuan Road, Minhang District, Shanghai, China, Shanghai, 201102, CHINA
| | - Hangyu Zhu
- Fudan University School of Information Science and Engineering, 220 Handan Road, Yangpu District, Shanghai, China, 2005 Songhu Road, Yangpu District, Shanghai, China, Shanghai, 200433, CHINA
| | - Yuanfeng Zhou
- Department of Neurology, Children's Hospital of Fudan University, 399 Wanyuan Road, Minhang District, Shanghai, China, Shanghai, 201102, CHINA
| | - Yi Wang
- Department of Neurology, Children's Hospital of Fudan University, 399 Wanyuan Road, Minhang District, Shanghai, China, Shanghai, 201102, CHINA
| | - Wei Chen
- Department of Electronic Engineering, Fudan University, 220 Handan Road, Yangpu District, Shanghai, China, 2005 Songhu Road, Yangpu District, Shanghai, China, Shanghai, Shanghai, 200433, CHINA
| |
Collapse
|
38
|
Towards precision sleep medicine: Self-attention GAN as an innovative data augmentation technique for developing personalized automatic sleep scoring classification. Comput Biol Med 2022; 148:105828. [PMID: 35816855 DOI: 10.1016/j.compbiomed.2022.105828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2022] [Revised: 05/07/2022] [Accepted: 07/03/2022] [Indexed: 11/03/2022]
Abstract
It is very important to have good quality sleep, which can affect aspects such as memory consolidation, emotional regulation, learning, physical development, and quality of life. Diagnosing human sleep quality and problems quickly and accurately is an important issue for human well-being. Therefore, many automatic sleep scoring methods have been proposed. However, the methods have been developed using sleep data from different individuals or groups. The accuracies of these proposed methods might decrease, due to existing individual differences. In this study, the self-attention generative adversarial network (SAGAN) was applied as an advanced data augmentation technique to propose an improved personalized automatic sleep scoring classification. First, the spectrograms were converted from electroencephalography (EEG). Then, SAGAN was used to generate synthesized spectrograms for each subject. Finally, the real and synthesized spectrograms of each subject were utilized to train a personalized classifier. The averaged accuracy and standard deviation of the proposed method are 95.74% and 3.78%, respectively. Compared to the classifier trained with all subjects' training data, the average accuracy increased by 8.08%. The results proved that the generated spectrograms significantly improved the performance of the personalized automatic sleep scoring classification. The contributions of the proposed method were that made the medical staff and subjects save massive medical resources and time for manual recording and scoring.
Collapse
|
39
|
Phan H, Mikkelsen K. Automatic sleep staging of EEG signals: recent development, challenges, and future directions. Physiol Meas 2022; 43. [PMID: 35320788 DOI: 10.1088/1361-6579/ac6049] [Citation(s) in RCA: 34] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Accepted: 03/23/2022] [Indexed: 11/11/2022]
Abstract
Modern deep learning holds a great potential to transform clinical practice on human sleep. Teaching a machine to carry out routine tasks would be a tremendous reduction in workload for clinicians. Sleep staging, a fundamental step in sleep practice, is a suitable task for this and will be the focus in this article. Recently, automatic sleep staging systems have been trained to mimic manual scoring, leading to similar performance to human sleep experts, at least on scoring of healthy subjects. Despite tremendous progress, we have not seen automatic sleep scoring adopted widely in clinical environments. This review aims to give a shared view of the authors on the most recent state-of-the-art development in automatic sleep staging, the challenges that still need to be addressed, and the future directions for automatic sleep scoring to achieve clinical value.
Collapse
Affiliation(s)
- Huy Phan
- School of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Rd, London, E1 4NS, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND
| | - Kaare Mikkelsen
- Department of Electrical and Computer Engineering, Aarhus Universitet, Finlandsgade 22, Aarhus, 8000, DENMARK
| |
Collapse
|