CareSleepNet: A Hybrid Deep Learning Network for Automatic Sleep Staging
J. Wang, S. Zhao, H. Jiang, Y. Zhou, Z. Yu, T. Li, S. Li, G. Pan,
Sleep staging is essential for sleep assessment and plays an important role in disease diagnosis, which refers to the classification of sleep epochs into different sleep stages. Polysomnography (PSG), consisting of many different physiological signals, e.g. electroencephalogram (EEG) and electrooculogram (EOG), is a gold standard for sleep staging. Although existing studies have achieved high performance on automatic sleep staging from PSG, there are still some limitations: 1) they focus on local features but ignore global features within each sleep epoch, and 2) they ignore cross-modality context relationship between EEG and EOG. In this paper, we propose CareSleepNet, a novel hybrid deep learning network for automatic sleep staging from PSG recordings. Specifically, we first design a multi-scale Convolutional-Transformer Epoch Encoder to encode both local salient wave features and global features within each sleep epoch. Then, we devise a Cross-Modality Context Encoder based on co-attention mechanism to model cross-modality context relationship between different modalities. Next, we use a Transformer-based Sequence Encoder to capture the sequential relationship among sleep epochs. Finally, the learned feature representations are fed into an epoch-level classifier to determine the sleep stages. We collected a private sleep dataset, SSND, and use two public datasets, Sleep-EDF-153 and ISRUC to evaluate the performance of CareSleepNet. The experiment results show that our CareSleepNet achieves the state-of-the-art performance on the three datasets. Moreover, we conduct ablation studies and attention visualizations to prove the effectiveness of each module and to analyze the influence of each modality.
Tags: Sleep staging, Polysomnography (PSG), CareSleepNet, a novel hybrid deep learning network for automatic sleep staging, Cross-Modality Context Encoder, Transformer-based Sequence Encoder
https://ieeexplore.ieee.org/document/10595067
Sensor Informatics
Using Semi-supervised Domain Adaptation to Enhance EEG-Based Cross-Task Mental Workload Classification Performance
Wang, Tao; Ke, Yufeng; Huang, Yichao; He, Feng; Zhong, Wenxiao; Liu, Shuang; Ming, Dong
Topological Gait Analysis: A New Framework and its Application to the Study of Human Gait
Mishra, Shreyam; Chatterjee, Debasish; Kanekar, Neeta
In-home Gait Abnormality Detection through Footstep-Induced Floor Vibration Sensing and Person-Invariant Contrastive Learning
Dong, Yiwen; Kim, Sung Eun; Schadl, Kornél; Huang, Peide; Ding, Wenhao; Rose, Jessica; Noh, Hae Young
Sleep Stage Classification via Multi-view Based Self-supervised Contrastive Learning of EEG
Zhao, Chen; wu, wei ; Zhang, Haoyi; Zhang, Ruiyan; Zheng, Xinyue; Kong, Xiangzeng
EEG Characteristic Comparison of Motor Imagery between Supernumerary and Inherent limb: Sixth-finger MI Enhances the ERD Pattern and Classification Performance
Wang, Zhuang; Liu, Yuan; Huang, Shuai-fei; Qiu, Shiyin; Zhang, Yujian; Huang, Huimin; An, Xingwei; Ming, Dong
ConDiff-rPPG: Robust Remote Physiological Measurement to Heterogeneous Occlusions
Wang, Jiyao; Wei, Ximeng; Lu, Hao; Chen, Yingcong; He, Dengbo
ΔBP-Net: Monitoring “Changes” in Blood Pressure Using PPG With Self-Contrastive Masking
Wang, Weinan; Mohseni, Pedram; Kilgore, Kevin; Najafizadeh, Laleh
An Accurate Non-contact Photoplethysmography via Active Cancellation of Reflective Interference
Tong, Yonggang; Huang, Zhipei; Qiu, Feng; wang, tao; Wang, Yiquan; Qin, Fei; Yin, Ming
MSVTNet: Multi-Scale Vision Transformer Neural Network for EEG-Based Motor Imagery Decoding
Liu, Ke; Yang, Tao; Yu, Zhuliang; Yi, Weibo; Yu, Hong; Wang, Guoyin; Wu, Wei
DS-MS-TCN: Otago Exercises Recognition with a Dual-Scale Multi-Stage Temporal Convolutional Network
Shang, Meng; Dedeyne, Lenore; Dupont, Jolan; Vercauteren, Laura; Amini, Nadjia; Lapauw, Laurence; Gielen, Evelien; Verschueren, Sabine; Varon, Carolina; De Raedt, Walter; Vanrumste, Bart
Fully Convolutional Hybrid Fusion Network with Heterogeneous Representations for Identification of S1 and S2 from Phonocardiogram
Jang, Yeonggul; Jung, Juyeong; Hong, Youngtaek; Lee, Jina; Jeong, Hyunseok; Shim, Hackjoon; Chang, Hyuk-Jae
Modulating Inter-Muscular Coordination Patterns In The Upper Extremity Induces Changes to Inter-Muscular, Cortico-Muscular, and Cortico-Cortical Connectivity
Houston, Michael; Seo, Gang; Fang, Feng; Park, Jeongho; Park, Hyung Soon; Roh, Jinsook; Zhang, Yingchun
Tags: Mental workload (MWL) assessment, EEG-Based Cross-Task, Domain Adaptation
Imaging Informatics
Adaptive Annotation Correlation Based Multi-Annotation Learning for Calibrated Medical Image Segmentation
Huang, Wei; Zhang, Lei; Shu, Xin; Wang, Zizhou; Yi, Zhang
An Eye Movement Classification Method based on Cascade Forest
Wang, Can; Wang, Ruimin; Leng, Yue; Iramina, Keiji; Yang, Yuan-kui; Ge, Sheng
Deep Quasi-Recurrent Self-Attention with Dual Encoder-Decoder in Biomedical CT Image Segmentation
Agarwal, Rohit; Chowdhury, Arindam; Chatterjee, Rajib Kumar; Chel, Haradhan; Murmu, Chiranjib; Murmu, Narayan; Nandi, Debashis
Cross-attention-based saliency inference for predicting cancer metastasis on whole slide images
Su, Ziyu; Rezapour, Mostafa; Sajjad, Usama; Niu, Shuo; Gurcan, Metin; Niazi, Muhammad Khalid Khan
DualStreamFoveaNet: A Dual Stream Fusion Architecture with Anatomical Awareness for Robust Fovea Localization
Song, Sifan; Wang, Jinfeng; Wang, Zilong; Wang, Hongxing; Su, Jionglong; Ding, Xiaowei; Dang, Kang
Multiband Convolutional Riemannian Network with Band-wise Riemannian Triplet Loss for Motor Imagery Classification
Shin, Jinhyo; Chung, Wonzoo
Generalized super-resolution 4D Flow MRI – using ensemble learning to extend across the cardiovascular system
Ericsson, Leon; Hjalmarsson, Adam; Akbar, Muhammad Usman; Ferdian, Edward; Bonini, Mia; Hardy, Brandon; Schollenberger, Jonas; Aristova, Maria; Winter, Patrick; Burris, Nicholas; Fyrdahl, Alexander; Sigfridsson, Andreas; Schnell, Susanne; Figueroa, C. Alberto; Nordsletten, David; Young, Alistair; Marlevi, David
Weakly Supervised Classification for Nasopharyngeal Carcinoma with Transformer in Whole Slide Images
Hu, Ziwei; Wang, Jianchao; Gao, Qinquan; Wu, Zhida; Xu, Hanchuan; Guo, Zhecheng; Quan, Jiawei; Zhong, Lihua; Du, Min; Tong, Tong; Chen, Gang
Clinical-Inspired Framework for Automatic Kidney Stone Recognition and Analysis on Transverse CT Images
Xu, Wenfeng; Lai, Cong; Mo, Zefeng; Liu, Cheng; Li, Maoyuan; Zhao, Gansen; Xu, Kewei
Fundus image enhancement through direct diffusion bridges
Kim, Sehui; Chung, Hyungjin; Park, Se Hie; Chung, Eui-Sang; Yi, Kayoung; Ye, Jong
Deep-DM: Deep-driven deformable model for 3D image segmentation using limited data
R. Torres, Helena; Oliveira, Bruno; Fritze, Anne; Birdir, Cahit; Ruediger, Mario; Fonseca, Jaime; Morais, Pedro; Vilaça, João
tDKI-Net: A Joint q-t Space Learning Network for Diffusion-Time-Dependent Kurtosis Imaging
Zheng, Tianshu; Ba, Ruicheng; Huang, Yongquan; Wu, Dan
DPFNet: Fast Reconstruction of Multi-coil MRI Based on Dual Domain Parallel Fusion Network
Wang, Yi; Luo, Bing; Yuan, Zhang; xiao, Zhenting; Wang, Miaomiao; Niu, Yilong; Nandi, Asoke
BTSSPro: Prompt-Guided Multimodal Co-learning for Breast Cancer Tumor Segmentation and Survival Prediction
Li, Wei; Liu, Tianyu; Feng, Feiyan; Yu, Sheng-Peng; Wang, Hong; Sun, Yanshen
Transfer Contrastive Learning for Raman Spectroscopy Skin Cancer Tissue Classification
Wang, Zhiqiang; Lin, Yanbin; Zhu, Xingquan
CroMAM: A Cross-Magnification Attention Feature Fusion Model for Predicting Genetic Status and Survival of Gliomas using Histological Images
Guo, Jisen; Xu, Peng; Wu, Yuankui; Tao, Yunyun; Han, Chu; lin, jiatai; Zhao, Ke; Liu, Zaiyi; Liu, Wenbin; Lu, Cheng
Hyperbolic graph embedding of MEG brain networks to study brain alterations in individuals with subjective cognitive decline
Baker, Cole; Suárez-Méndez, Isabel; Smith, Grace; Marsh, Elisabeth B.; Funke, Michael; Mosher, John; Maestú, Fernando; Xu, Mengjia; Pantazis, Dimitrios
Automatic segmentation of hemorrhages in the ultra-wide field retina: multi-scale attention subtraction networks and an ultra-wide field retinal hemorrhage dataset
Wu, Renkai; Liang, Pengchen; Huang, Yiqi; Chang, Qing; Yao, Huiping
CAGCL: Predicting Short- and Long-Term Breast Cancer Survival with Cross-Modal Attention and Graph Contrastive Learning
Palmal, Susmita; Saha, Sriparna; Arya, Nikhilanand; Tripathy, Somanath
Tags: Medical image segmentation, Adaptive annotation Correlation based multI-annOtation LearNing (ACTION) multi-annotation setting
Medical Informatics
Eye Gaze Guided Cross-Modal Alignment Network for Radiology Report Generation
Peng, Peixi; Fan, Wanshu; Shen, Yue; Liu, Wenfei; Yang, Xin; Zhang, Qiang; Wei, Xiaopeng; Zhou, Dongsheng
Synthesizing Feature-Aligned and Category-aware Electronic Medical Records for Intracranial Aneurysm Rupture Prediction
Yang, Qian; Li, Caizi; Ou, Chubin; Li, Kang; Liao, Xiangyun; Duan, Chuanzhi; Yu, Lequan ; Si, Weixin
Multi-task Learning for Audio-based Infant Cry Detection and Reasoning
Xia, Ming; Huang, Dongmin; Wang, Wenjin
ESSN: An Efficient Sleep Sequence Network for Automatic Sleep Staging
Chen, Yongliang; Lv, Yudan; Sun, Xinyu; Poluektov, Mikhail; Zhang, Yuan; Penzel, Thomas
Smartphone-Based Digitized Neurological Examination Toolbox for Multi-test Neurological Abnormality Detection and Documentation
Hoang, Trung-Hieu; Christopher, Zallek; Do, Minh
CDI-NSTSEG: A clinical diagnosis-inspired effective and efficient framework for non-salient small tumor segmentation
Ju, Jianguo; Qiu, Dandan; Ren, Shumin; Lei, Hao; Zhao, Wei; Xu, Pengfei; Zhao, Xuesong; Guan, Ziyu
MLVICX: Multi-Level Variance-Covariance Exploration for Chest X-ray Self-Supervised Representation Learning
Singh, Azad; Gorade, Vandan; Mishra, Deepak
Signed Curvature Graph Representation Learning of Brain Networks for Brain Age Estimation
Li, Jingming; Lyu, Zhengyuan; Yu, Hu; Fu, Si; Li , Ke ; Yao, Li; Guo, Xiaojuan
A Telemedicine Analytic Framework for Fully and Semi-automatic Alzheimers Disease Screening using Clock Drawing Test
Bo, Wei; Sullivan, Suzanne S.; Zhang, Xiaoyu; Gao, Mingchen; Xu, Wenyao
Asymmetric multi-task learning for interpretable gaze-driven grasping action forecasting
González Díaz, Iván; Molina-Moreno, Miguel; Benois-Pineau, Jenny; de Rugy, Aymar
Tags: Radiology report generation, Eye Gaze Guided Cross-Modal Alignment Network (EGGCA-Net), Dual Fine-Grained Branch
Multi-Task Branch, clinical decision-making and patient care.
Bioinformatics
GENNDTI: Drug-target interaction prediction using graph neural network enhanced by router nodes
Yang, Beiyuan; Liu, Yule; Wu, Junfeng; Bai, Fang; Zheng, Mingyue; Zheng, Jie
Advancing Bioactivity Prediction through Molecular Docking and Self-Attention
Yin, Yueming; Lam, Hilbert Yuen In; Mu, Yuguang; Li, Hoi Yeung; Kong, Adams
Predicting miRNA-disease associations based on spectral graph transformer with dynamic attention and Regularization
Li, Zhengwei; Bai, Xu; Nie, Ru; Liu, Yanyan; Zhang, Lei; You, Zhuhong
Geometric molecular graph representation learning model for drug-drug interactions prediction
Jiang, Zhenyu; Ding, Pingjian; Shen, Cong; Dai, Xiaopeng
Advancing the Boundary of Pre-trained Models for Drug Discovery: Interpretable Fine-Tuning Empowered by Molecular Physicochemical Properties
Lian, XiaoQing; Zhu, Jie; Lv, Tianxu; Hong, Xiaoyan; Ding, Longzhen; Chu, Wei; Ni, Jianming; Pan, Xiang
Identifying Associations between Small Nucleolar RNAs and Diseases via Graph Convolutional Network and Attention Mechanism
Liu, Shuchen; Zhu, Wen; Wang, Peng; Yu, Shaoyou; Wu, Fangxiang
Self-supervised Pre-training via Multi-view Graph Information Bottleneck for Molecular Property Prediction
Zang, Xuan; Zhang, Junjie; Tang, Buzhou
Multi-view multiattention graph learning with stack deep matrix factorization for circRNA-drug sensitivity association identification
Ning, Ai; Yuan, Haoliang; Liang, Yong; Lu, Shanghui; Ouyang, Dong; Lai, Qi Hong; Lai, Loi Lei
Tags: drug-target interactions (DTI), graph neural network (GNN), biological and chemical mechanisms involved.
Modeling and AI Informatics
CALLM: Enhancing Clinical Interview Analysis through Data Augmentation with Large Language Models
Wu, Yuqi; Mao, Kaining; Zhang, Yanbo; Chen, Jie
AI-CADR: Artificial Intelligence Based Risk Stratification of Coronary Artery Disease using Novel Non-invasive Biomarkers
Sajid, Muhammad; Hassan, Ali; Khan, Dilshad Ahmed; Khan, Shoab; Bakhshi, Asim Dilawar; Akram, Muhammad Usman; Babar, Mishal; Hussain, Farhan; Abdul, Wadood
DYNAMITE: Integrating Archetypal Analysis and Process Mining for Interpretable Disease Progression Modelling
Trescato, I.; Tavazzi, E.; Vettoratti, Martina; Gatta, R.; Vasta, R.; Chiò, A.; Di Camillo, Barbara
A personal thermal comfort model based on causal artificial intelligence: a physiological sensor-enabled causal identifiability
Sahoh, Bukhoree; Kliangkhlao, Mallika; Haruehansapong, Kanjana; Yeranee, Kirttayoth; Punsawad, Yunyong
Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis
Lo, Frank Po Wen; Qiu, Jianing; Wang, Zeyu; Chen, Junhong; Xiao, Bo; Yuan, Wu; Giannarou, Stamatia; Frost, Gary; Lo, Benny
Tags: Large Language Models (LLMs), text-generation capabilities, Clinical data Augmentation, dynamic diagnostic dialogues
Public Health Informatics
Mental Health and Mobile Communication Profiles of Crowdsourced Participants
Tlachac, ML; Heinz, Michael