Publications from Will Two Do? Varying Dimensions in Electrocardiography: The PhysioNet/Computing in Cardiology Challenge 2021

The following paper describes the PhysioNet/Computing in Cardiology Challenge. Please cite this publication when referencing the Challenge.

The following papers were presented at the Computing in Cardiology Conference.

Will Two Do? Varying Dimensions in Electrocardiography: the PhysioNet/Computing in Cardiology Challenge 2021
Matthew Reyna¹, Nadi Sadr¹, Erick Perez Alday¹, Annie Gu¹, Amit Shah¹, Chad Robichaux¹, Ali Rad¹, Andoni Elola², Salman Seyedi¹, Sardar Ansari³, Hamid Ghanbari³, Qiao Li¹, Ashish Sharma¹, Gari Clifford^4
1Emory University, ²University of the Basque Country UPV/EHU, ³University of Michigan, ⁴Emory University and Georgia Institute of Technology
Pathologies Prediction on Short ECG Signals with Focus on Feature Extraction Based on Beat Morphology and Image Deformation
Jeffrey Prehn¹, Svetoslav Ivanov², Georgi Nalbantov^1
1Data Science Consulting Ltd., ²DSC
A Two-Phase Multilabel ECG Classification Using One-Dimensional Convolutional Neural Network and Modified Labels
Peter Bugata¹, Peter Bugata Jr.¹, Vladimira Kmecova¹, Monika Stankova¹, David Gajdos¹, David Hudak¹, Richard Stana², Simon Horvat², Lubomir Antoni², Gabriela Vozarikova², Erik Bruoth², Alexander Szabari^2
1VSL Software, a.s., ²Pavol Jozef Šafárik University
Two will do: Convolutional Neural Network with Asymmetric Loss and Self-Learning Label Correction for Imbalanced Multi-Label ECG Data Classification
Cristina Gallego Vázquez¹, Alexander Breuss¹, Oriella Gnarra¹, Julian Portmann², Giulia Da Poian^1
1Sensory‐Motor Systems (SMS) Lab, Department of Health Sciences and Technology (D‐HEST), Institute of Robotics and Intelligent Systems (IRIS), ETH Zurich, ²Department of Computer Science, ETH Zurich
Learning ECG Representations for Multi-Label Classification of Cardiac Abnormalities
Jangwon Suh¹, Jimyeong Kim¹, Eunjung Lee¹, Jaeill Kim¹, Duhun Hwang¹, Jungwon Park¹, Junghoon Lee¹, Jaeseung Park¹, Seo-Yoon Moon¹, Yeonsu Kim¹, Min Kang¹, Soonil Kwon², Eue-Keun Choi³, Wonjong Rhee^1
1Seoul National University, ²Seoul National University Hospital, ³Seoul National University College of Medicine
Reduced-Lead ECG Classifier Model Trained with DivideMix and Model Ensemble
Hiroshi Seki¹, Takashi Nakano¹, Koshiro Ikeda¹, Shinji Hirooka¹, Takaaki Kawasaki¹, Mitsutomo Yamada¹, Shumpei Saito¹, Toshitaka Yamakawa², Shimpei Ogawa^1
1AMI inc., ²Kumamoto University
Convolution-Free Waveform Transformers for Multi-Lead ECG Classification
Annamalai Natarajan¹, Gregory Boverman¹, Yale Chang¹, Corneliu Antonescu², Jonathan Rubin^1
1Philips Research North America, ²University of Arizona Banner Health
Classification of ECG using Ensemble of Residual CNNs with Attention Mechanism
Petr Nejedly¹, Adam Ivora², Ivo Viscor², Zuzana Koscova², Radovan Smisek³, Pavel Jurak², Filip Plesinger^2
1Institute of Scientific Instruments of the Czech Academy of Science, ²Institute of Scientific Instruments of the CAS, ³Brno University of Technology, Faculty of Electrical Engineering and Communication, Department of Biomedical Engineering
Combining a ResNet Model with Handcrafted Temporal Features for ECG Classification with Varying Number of Leads
Stefano Magni, Andrea Sansonetti, Chiara Salvi, Tiziana Tabiadon, Guadalupe García Isla
Politecnico di Milano
MTFNet: A Morphological and Temporal Features Network for multiple leads ECG Classification
Lebing Pan, Weibai Pan, Mengxue Li, Yuxia Guan, Ying An
Central South University
Towards Generalization of Cardiac Abnormality Classification Using ECG Signal
Xiaoyu Li¹, Chen Li¹, Xian Xu², Yuhua Wei¹, Jishang Wei³, Yuyao Sun², Buyue Qian⁴, Xiao Xu^2
1Xi'an Jiaotong University, ²Ping An Health Technology, ³HP Labs, ⁴The First Affiliated Hospital of Xi'an Jiaotong University
3-D ECG images with Deep Learning Approach for Identification of Cardiac Abnormalities from a Variable Number of Leads
giovanni bortolan
IN-CNR
A Branched Deep Neural Network for End-to-end Classification from ECGs with Varying Dimensions
Han Duan¹, Junchao Fan¹, Junhui Zhang², Bin Xiao¹, Xiuli Bi¹, Xu Ma^3
1Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing 400065, China, ²Health Management Center, the First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China, ³Human Genetics Resource Center, National Health Commission, Beijing 100181, China
Hybrid Arrhythmia Detection on Varying-Dimensional Electrocardiography: Combining Deep Neural Networks and Clinical Rules
Hao WEN¹ and Jingsu KANG^2
1Beihang University, ²Tianjin Medical University
Using mel-frequency cepstrum and amplitude-time heart variability as XGBoost handcrafted features for heart disease detection
Sergey Krivenko¹, Anatolii Pulavskyi¹, Liudmyla Kryvenko², Olha Krylova², Stanislav Krivenko^3
1HealthEntire, ²Kharkiv National Medical University, ³Kharkiv National University of radioelectronics
Two Might Do: A Beat-by-Beat Classification of Cardiac Abnormalities using Deep Learning with Domain-Specific Features
Berken Utku Demirel¹, Adnan Harun Dogan², Mohammad Abdullah Al Faruque^3
1University of California Irvine, ²Middle East Technical University, ³University of California, Irvine
Multi-label Classification of Electrocardiogram using a Deep Neural Network
Hanshuang Xie¹, Qineng cao², Jiayi Yan³, hong z^3
1Hangzhou Proton Technology Co Ltd, ²Hangzhou Proton Technology Co., Ltd. in Hangzhou, ³Hangzhou Proton Technology Co.,Ltd.
Swarm Decomposition Enhances the Discrimination of Cardiac Arrhythmias in Varied-lead ECG Using ResNet-BiLSTM Network Activations
Mohanad Alkhodari¹, Georgios Apostolidis², Charilaos Zisou², Leontios Hadjileontiadis¹, Ahsan Khandoker^1
1Khalifa University, ²Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki
Cardiac Abnormality Detection based on an Ensemble Voting of Single-Lead Classifier Predictions
Pierre Aublin¹, Julien Oster¹, Mouin Ben Ammar², Jérémy Fix³, Michel Barret^4
1INSERM, ²ENSTA, ³CentraleSupélec, ⁴International Research Lab Georgia Tech - CNRS IRL 2958 CentraleSupélec
Cardiac Abnormalities Recognition in ECG Using a Convolutional Network with Attention and Input with an Adaptable Number of Leads
Tomas Vicar¹, Petra Novotna¹, Jakub Hejc², Oto Janousek³, Marina Ronzhina^1
1Department of Biomedical Engineering, Brno University of Technology, ²International Clinical Research Center, St. Anne’s University Hospital, Brno, Czech Republic, ³Department of Biomedical Engineering, Brno University of Technology, Brno, Czech Republic
Semi-supervised Learning for ECG Classification
Rui Rodrigues
FCT Nova
N-BEATS for Heart Disfunction Classification
Bartosz Puszkarski, Krzysztof Hryniów, Grzegorz Sarwas
Warsaw University of Technology
Improving Machine Learning Education during the COVID-Pandemic using past Computing in Cardiology Challenges
Maurice Rohr¹, Filip Plesinger², Veronika Bulkova³, Christoph Hoog Antink^4
1Technische Universität Darmstadt, ²Institute of Scientific Instruments of the CAS, ³Medical Data Transfer, s.r.o., ⁴TU Darmstadt
Automatic Diagnosis of Cardiac Disease from Twelve-lead and Reduced-lead ECGs using Multi-label Classification
Prathic Sundararajan, Kevin Moses, Cristhian Potes, Saman Parvaneh
Edwards Lifesciences
Multi-Label Cardiac Abnormalities Classification on Selected Leads of ECG Signals
Zhuoyang Xu, Yangming Guo, Tingting Zhao, Zhuo Liu, Xingzhi Sun
Ping An Technology
Cardiac Anomalies Detection Through 2D-CNN and ECG Spectrograms
Jonathan Roberto Torres Castillo and Miguel Padilla Castañeda
Universidad Nacional Autónoma de México
Multi-label ECG classification using Convolutional Neural Networks in a Classifier Chain
Bjørn-Jostein Singstad¹, Pål Brekke¹, Eraraya Muten^2
1Oslo University Hospital, ²Institut Teknologi Bandung
A Mixed-Domain Self-Attention Network for Multilabel Cardiac Irregularity Classification Using Reduced-Lead Electrocardiogram
Hao-Chun Yang¹, Wan-Ting Hsieh², Trista Pei-Chun Chen^2
1National Tsing Hua University, ²Inventec Corporation
Towards High Generalization Performance on Electrocardiogram Classification
Hyeongrok Han¹, Seongjae Park², Seonwoo Min¹, Hyun-Soo Choi³, Eunji Kim¹, Hyunki Kim¹, Sangha Park¹, Jin-Kook Kim², Junsang Park², Junho An², Kwnanglo Lee², Wonsun Jeong², Sangil Chon², Kwonwoo Ha², Myungkyu Han², Sungroh Yoon^1
1Seoul National University, ²HUINNO Co., Ltd, ³Kangwon National University
Deep Discriminative Domain Generalization with Adversarial Feature Learning for Classifying ECG Signals
Zuogang Shang¹, Zhibin Zhao², Hui Fang³, Samuel Relton⁴, Darcy Murphy⁵, Zoe Hancox⁴, Ruqiang Yan², David Wong^5
1Xi’an Jiaotong University, ²the Department of Mechanical Engineering, Xi’an Jiaotong University, ³the Department of Computer Science, Loughborough University, ⁴Leeds Institute of Health Sciences, University of Leeds, ⁵the Department of Computer Science and the Center for Health Informatics, University of Mancheste
A Novel Multi-Scale Convolutional Neural Network for Arrhythmia Classification on Reduced-lead ECGs
Pan Xia¹, Zhengling He², Yusi Zhu¹, Zhongrui Bai³, Xianya Yu¹, Yuqi Wang⁴, Fanglin Geng¹, Lidong Du¹, Xianxiang Chen¹, Peng Wang¹, Zhen Fang^1
1Aerospace Information Research Institute, Chinese Academy of Sciences, ²University of Chinese Academy of Sciences, ³School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, ⁴Institute of Microelectronics of Chinese Academy of Sciences
Classifying different dimensional ECGs using deep residual convolutional neural networks
Wenjie Cai, Fanli Liu, Xuan Wang, Bolin Xu, Yaohui Wang
University of Shanghai for Science and Technology
Multiple Cardiac Disease Detection from Minimal-Lead ECG Combining Feedforward Neural Networks with a One-vs-Rest Approach
Santiago Jiménez-Serrano¹, Miguel Rodrigo², Conrado J. Calvo³, José Millet Roig¹, Francisco Castells^1
1Instituto ITACA - Universitat Politècnica de València, ²Electronics Engineering Department, Universitat de València, ³Universitat Politècnica de València
Robust and Task-Aware Training of Deep Residual Networks for Varying-Lead ECG Classification
Hansheng Ren, Miao Xiong, Bryan Hooi
National University of Singapore
Rethinking ECG Classification with Neural Networks as a Sequence-to-Sequence Task
Philipp Sodmann¹, Lars Kaderali¹, Marcus Vollmer^2
1Universität Greifswald, ²Institute of Bioinformatics, University Medicine Greifswald
Multi-label Classification on 12, 6, 3 and 2 Lead ECG Signals using Convolutional Recurrent Neural Networks
Niels Osnabrugge¹, Felix Rustemeyer¹, Francesca Battipaglia², Christos Kaparakis¹, Kata Keresztesi¹, Joel Karel¹, Pietro Bonizzi^3
1Maastricht University, ²hearMAASters (Maastricht University), ³Department of Data Science and Knowledge Engineering, Maastricht University
Detecting Cardiac Abnormalities with Multi-Lead ECG Signals: A Modular Network Approach
Ryan Clark¹, Mohammadreza Heydarian², Mohammad Siddiqui¹, Sajjad Rashidiani³, Md Asif Khan³, Thomas Doyle^3
1School of Biomedical Engineering, McMaster University, ²Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada, ³Department of Electrical and Computer Engineering, McMaster University
An InceptionTime-Inspired Convolutional Neural Network to Detect Cardiac Abnormalities in Reduced-Lead ECG Data
Harry Crocker and Aaron Costall
University of Bath
An Ensemble Learning Approach to Detect Cardiac Abnormalities in ECG Data Irrespective of Lead Availability
Tim Uhlemann¹, Sebastian Wegener², Joshua Prim¹, Nils Gumpfer¹, Dimitri Grün², Jennifer Hannig¹, Till Keller², Michael Guckert^1
1Cognitive Information Systems, Kompetenzzentrum für Informationstechnologie, Technische Hochschule Mittelhessen - University of Applied Sciences, ²Department of Internal Medicine I, Cardiology, Justus-Liebig-University Gießen
Ensemble Learning of Modified Residual Networks for Classifying ECG with Different Set of Leads
Federico Muscato¹, Valentina Corino², Luca Mainardi^2
1Department of Electronics, Information and Bioengineering, Politecnico di Milano, ²Politecnico di Milano
Diagnosis of Cardiac Abnormalities Applying Scattering Transform and Fourier-Bessel Expansion on ECG Signals
Nidhi Sawant and Shivnarayan Patidar
National Institute of Technology Goa
Reduced-Lead Electrocardiogram Classification using Wavelet Analysis and Deep Learning
Adrian Cornely, Alondra Carrillo, Grace Mirsky
Benedictine University
Generative Pre-Trained Transformer for Cardiac Abnormality Detection
Pierre Louis Gaudilliere, Halla Sigurthorsdottir, Jérôme Van Zaen, Clémentine Aguet, Mathieu Lemay, Ricard Delgado-Gonzalo
Swiss Center for Electronics and Microtechnology (CSEM)
Automated Diagnosis of Reduced-lead Electrocardiograms using a Shared Classifier
Hidde Jessen, Rutger van de Leur, Pieter Doevendans, Rene van Es
UMC Utrecht
Classification of ECG Signals with Different Lead Systems Using AutoML
Matteo Bodini¹, Massimo W Rivolta², Roberto Sassi^2
1Università degli Studi di Milano, ²Dipartimento di Informatica, Università degli Studi di Milano
Spatio-temporal ECG Network for Detecting Cardiac Disorders from Multi-lead ECGs
Long Chen¹, Zheheng Jiang², Tiago P. Almeida¹, Fernando S. Schlindwein¹, Jakevir S. Shoker¹, G. Andre Ng¹, Huiyu Zhou¹, Xin Li^1
1University of Leicester, ²Lancaster University
Multi-Label Classification of Cardiac Abnormalities for Multi-Lead ECG Recordings Based on Auto-Encoder Features and a Neural Network Classifier
Onno Linschmann¹, Maurice Rohr², Klaus Leonhardt¹, Christoph Hoog Antink^3
1RWTH Aachen, ²Technische Universität Darmstadt, ³TU Darmstadt
ECG classification combining conventional signal analysis, random forests and neural networks – a stacked learning scheme
Martin Kropf¹, Martin Baumgartner², Sai Pavan Kumar Veeranki³, Lukas Haider², Dieter Hayn⁴, Günter Schreier^2
1Charité Berlin, ²AIT Austrian Institute of Technology, ³Technical University Graz, ⁴AIT Austrian Institute of Technology and Ludwig Boltzmann Institute for Digital Health and Prevention
Arrhythmia Classification of Reduced-Lead Electrocardiograms by Scattering-Recurrent Networks
Philip Warrick¹, Vincent Lostanlen², Michael Eickenberg³, Masun Nabhan Homsi⁴, Adrian Rodriguez⁵, Joakim Anden^5
1PeriGen Canada, McGill University, ²LS2N, CNRS, École Centrale de Nantes, ³Flatiron Institute, ⁴Helmholtz Centre for Environmental Research - UFZ, ⁵KTH Royal Institute of Technology
Automatic Classification of 12-, 6-, 4-, 3-, and 2-Lead Electrocardiograms Using Morphological Feature Extraction
Alexander Hammer¹, Matthieu Scherpf², Hannes Ernst¹, Jonas Weiß¹, Daniel Schwensow¹, Martin Schmidt^1
1TU Dresden, ²TU Dresden, Institute of Biomedical Engineering, Dresden, Germany
Incorporating Clinical and Heartbeat Level Features with Multichannel ECG for Cardiac Abnormality Detection Using Parallel CNN and GAP Network
Deepankar Nankani and Rashmi Dutta Baruah
Department of Computer Science and Engineering, Indian Institute of Technology Guwahati
Channel self-Attention Deep Learning Framework for Multi-Cardiac Abnormality Diagnosis from Varied-lead ECG Signals
Apoorva Srivastava¹, Ajith Hari¹, Sawon Pratiher², sazedul alam³, Nirmalya Ghosh¹, Nilanjan Banerjee⁴, Amit Patra^1
1Indian Institute of Technology, Kharagpur, ²IIT Kharagpur, ³PhD student, CSEE, UMBC., ⁴Assistant Professor, UMBC
Leveraging Period-specific Variations in ECG Topology for Classification Tasks
Paul Samuel Ignacio
University of the Philippines Baguio
Multi-label Cardiac Abnormality Classification from Electrocardiogram using Deep Convolutional Neural Networks
Nima Wickramasinghe¹ and Mohamed Athif^2
1Department of Electronic and Telecommunication Engineering, University of Moratuwa, ²Department of Biomedical Engineering, Boston University
High-Order Cardiomyopathy Human Heart Model and Mesh Generation
Fariba Mohammadi¹, Suzanne Shontz¹, Cristian Linte^2
1University of Kansas, ²Rochester Institute of Technology
Demystifying Heart Failure with Mid-Range Ejection Fraction using Machine Learning
Achal Dixit and Soumi Chattopadhyay
Indian Institute of Information Technology Guwahati
Spatiotemporal Quantification of In Vitro Cardiomyocyte Contraction Dynamics Using Video Microscopy-based Software Tool
Antti Ahola and Jari Hyttinen
Tampere University
Dynamics of Ventricular Electrophysiology are Unmasked through Noninvasive Electrocardiographic Imaging
Job Stoks¹, Bianca Van Rees¹, Uyen Chau Nguyen², Ralf Peeters¹, Paul Volders¹, Matthijs Cluitmans^1
1Maastricht University, ²Cardiovascular Research Institute Maastricht (CARIM)
Electrocardiographic Imaging in Atrial Fibrillation: Selection of the Optimal Tikhonov-Regularization Parameter
Rubén Molero Alabau, Carlos Fambuena Santos, Andreu M. Climent, Maria de la Salud Guillem Sánchez
Universitat Politècnica de València