Skip to content

Commit

Permalink
Add 2024 scores
Browse files Browse the repository at this point in the history
  • Loading branch information
matthewreyna committed Sep 21, 2024
1 parent ccd03f6 commit 05c6ea5
Show file tree
Hide file tree
Showing 11 changed files with 114 additions and 15 deletions.
2 changes: 2 additions & 0 deletions 2024/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,8 @@ The George B. Moody PhysioNet Challenges are annual competitions that invite par

## <a name="announcements"></a> Announcements

- <a name="2024.09.20"></a>__September 20, 2024:__ We have released the [results](results) of the 2024 Challenge. Congratulations to the winners! Please see the [announcement](https://groups.google.com/g/physionet-challenges/) for more details.

- <a name="2024.08.19"></a>__August 19, 2024:__ We have extended the official phase deadline to 23:59 GMT on August 21, 2024. Please see the [deadlines](#key-dates-deadlines) for the updated deadlines.

- <a name="2024.07.09"></a>__July 9, 2024:__ The PhysioNet Challenges spent several days last month at [Data Science Africa 2024](https://www.datascienceafrica.org/dsa2024nyeri/). The [DSAIL](https://dekut-dsail.github.io/) at [DeKUT](https://www.dkut.ac.ke/) helped us to run a hackathon over 4 days with more than 50 attendees, including some that we will win a prize from the [IEEE SPS](https://signalprocessingsociety.org/publications-resources/data-challenges/digitization-and-classification-ecg-images-george-b-moody) at [CinC 2024](https://cinc2024.org). Please see [this announcement](https://groups.google.com/g/physionet-challenges/c/_-V_t1srd-o) for more information about our trip to DSA.
Expand Down
14 changes: 1 addition & 13 deletions 2024/leaderboard/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,16 +4,4 @@ layout: after_2015

# Leaderboard for the 2024 Challenge

This leaderboard contains the [Challenge scores](../#scoring) on the [validation data](../#data) for the [official phase](../#rules) entries to the [2024 Challenge](../).

<iframe width="100%" height="500" src="https://docs.google.com/spreadsheets/d/e/2PACX-1vRxoN5oxymRHNa5XFjautP0Jn6BqtrX8gVkoW6M3FPzEYvi8ma-7sF9-ftU8gwkX2XCcunkYbCxdO3E/pubhtml?rm=minimal&amp;gid=1894271459&amp;gid=2117462787&amp;single=false&amp;widget=true&amp;headers=false"></iframe>

The MATLAB example code is available [here](https://github.com/physionetchallenges/matlab-example-2024),
the Python example code is available [here](https://github.com/physionetchallenges/python-example-2024),
and the vanilla deep learning approach is available
[here](https://github.com/physionetchallenges/example-classifier-2024). These
are minimal working examples to demonstrate the code, and to serve as a
template to the teams, but not for comparisons; they are deliberately designed
not to perform well.


The 2024 Challenge is over. Please see [this page](../results/) for the Challenge results!
Binary file modified 2024/papers/cinc_paper_checklist.pdf
Binary file not shown.
22 changes: 21 additions & 1 deletion 2024/results/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,4 +4,24 @@ layout: after_2015

# Results for the 2024 Challenge

Please check the [leaderboard](../leaderboard/) for the current results!
This page contains the scores for the 2024 PhysioNet Challenge.

During the course of the Challenge, teams submitted entries with their approaches, and we trained and evaluated each entry on the [Challenge data](../#data). The training data were public, and the hidden data were hidden.

During the [unofficial and official phases](../#rules) of the Challenge, we trained each entry on the training set, and we [scored](../#scoring) each entry on a subset of the hidden data. After the official phase, each team selected one entry for evaluation on all of the hidden data, and we evaluated these entries on all of the hidden data.

Teams that satisfied all of the [Challenge rules](../#rules) were eligible for rankings and prizes as official Challenge entries. Teams that did not satisfy one or more of the rules were not eligible for rankings or prizes as unofficial Challenge entries. (Both the official and unofficial entries are from the official phase of the Challenge.)

- __[Team summary table](team_summary_table.tsv)__: summary of the teams that participated in the 2024 Challenge. This table includes ranking and prize eligibility information.

- Scores and rankings (sorted by rank) for __official entries, i.e., eligible for rankings__:
- [Digitization](official_scores_digitization.tsv)
- [Classification](official_scores_classification.tsv)

- Scores (sorted alphabetically by team name) for __unofficial entries, i.e., not eligible for rankings__:
- [Digitization](unofficial_scores_digitization.tsv)
- [Classification](unofficial_scores_classification.tsv)

The score tables include signal-to-noise ratios (SNR) scores for the digitization task and macro _F_-measure scores for the classification tasks. All scores are on the hidden data. The leaderboard scores are scores reported during the official phase on color and black-and-white scans of paper ECGs from the PTB-XL data. The other scores are scores for models retrained on the full test set and evaluated on variants of the paper ECGs from the PTB-XL data, including scans and photographs of clean, stained, and deteriorated ECG papers and photographs of computer monitors showing ECGs.

The [Challenge webpage](../) and [Challenge description paper](../papers/) describe the Challenge. Please cite the [Challenge data paper and the Challenge description paper](../papers/) when describing the Challenge.
13 changes: 13 additions & 0 deletions 2024/results/official_scores_classification.tsv
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
Rank Team name Leaderboard: F-measure Color scans of clean papers: F-measure Black-and-white scans of clean papers: F-measure Mobile phone photos of clean papers: F-measure Mobile phone photos of stained papers: F-measure Mobile phone photos of deteriorated papers: F-measure Color scans of deteriorated papers: F-measure Black-and-white scans of deteriorated papers: F-measure Screenshots of computer monitor: F-measure
1 AIMED 0.817 0.833 0.796 0.644 0.636 0.711 0.830 0.775 0.636
2 Inventec AIC 0.742 0.779 0.628 0.697 0.694 0.739 0.777 0.582 0.726
3 BAPORLab 0.730 0.716 0.696 0.609 0.634 0.644 0.720 0.664 0.604
4 CeZIS 0.645 0.691 0.586 0.648 0.659 0.700 0.700 0.576 0.691
5 ECG_UVA 0.516 0.580 0.481 0.070 0.068 0.076 0.595 0.468 0.086
6 DSAIL 0.429 0.502 0.118 0.072 0.080 0.078 0.463 0.093 0.104
7 USST_Med 0.393 0.056 0.056 0.056 0.056 0.056 0.056 0.056 0.056
8 Revenger 0.330 0.332 0.327 0.306 0.316 0.306 0.331 0.319 0.288
9 PulsePlex 0.317 0.222 0.222 0.222 0.222 0.222 0.222 0.222 0.222
10 DSAIL_Nyeri 0.227 0.290 0.104 0.055 0.058 0.053 0.271 0.077 0.058
11 Leicester Fox 0.068 0.044 0.078 0.068 0.058 0.067 0.056 0.074 0.060
12 Ahus AI Lab 0.056 0.056 0.056 0.056 0.056 0.056 0.056 0.056 0.056
13 changes: 13 additions & 0 deletions 2024/results/official_scores_digitization.tsv
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
Rank Team name Leaderboard: SNR Color scans of clean papers: SNR Black-and-white scans of clean papers: SNR Mobile phone photos of clean papers: SNR Mobile phone photos of stained papers: SNR Mobile phone photos of deteriorated papers: SNR Color scans of deteriorated papers: SNR Black-and-white scans of deteriorated papers: SNR Screenshots of computer monitor: SNR
1 SignalSavants 12.151 4.930 3.479 -1.071 -0.723 -1.304 0.506 0.514 -1.759
2 BAPORLab 5.493 6.220 4.735 -0.261 -1.116 0.807 0.905 0.358 0.123
3 Ahus AI Lab 3.047 3.318 2.777 0.138 -0.345 0.792 0.670 -0.320 -0.512
4 USST_Med 2.202 -0.058 -0.058 -0.375 -0.375 -0.375 -0.375 -0.375 -0.375
5 Inventec AIC 0.397 4.101 -2.569 -4.574 -5.106 -3.782 -2.157 -2.802 -2.450
6 TimeBeater -0.056 -0.058 -0.056 -0.375 -0.375 -0.375 -0.375 -0.375 -0.375
7 VinUniTeam -0.066 -0.069 -0.062 -0.027 -0.027 -0.029 -0.030 -0.026 -0.047
8 PulsePlex -0.081 -0.082 -0.080 -0.303 -0.301 -0.302 -0.303 -0.303 -0.303
9 Revenger -0.733 -0.148 -1.267 -9.019 -8.545 -6.398 -1.636 -3.559 -6.532
10 PapyrusECG -5.192 1.211 -11.781 -11.960 -12.635 -8.888 -1.549 -10.926 -11.648
11 Leicester Fox -12.032 -12.032 -12.032 -12.813 -12.813 -12.813 -12.813 -12.813 -12.813
12 DeRC_ECG -31.302 -31.302 -31.302 -31.122 -31.122 -31.122 -31.122 -31.122 -31.122
50 changes: 50 additions & 0 deletions 2024/results/team_summary_table.tsv
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
Team name CinC submission ID Title Authors Accepted CinC abstract? Wild card CinC abstract? Withdrawn CinC abstract? CinC preprint uploaded by deadline? Presented at CinC? Withdrawn from Challenge? Successful unofficial phase entry Successful official phase entry? Successfully trained on the training set and scored on the validation and test sets? Open-source license? Eligible for rankings and prizes?
Ahus AI Lab 262 ECG-DUal: Pose- and warp-invariant digitalization of printed ECGs using dual U-nets Bjørn-Jostein Singstad, Jesper Ravn, Arian Ranjbar TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
AIMED 398 Image-Based Electrocardiogram Classification using Pre-trained ConvNext Models with Demographic Data Felipe Meneguitti Dias, Estela Ribeiro, Quenaz Bezerra Soares, Jose Krieger, Marco Antonio Gutierrez TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
am_HAI 277 Automated Digitization of Paper-Based ECGs: A Methodological Approach Enhanced by Denoising Autoencoders Chaithanya Kalyan Reddy Bhuma, Subhash khambampati, Sushanth Reddy Dondapati, Tejo Vardhan Kattamuri, Bharadwaj Madiraju, Kunal Achintya Reddy Seerapu, Rahul Krishnan Pathinarupothi TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
BAPORLab 227 A Multi-Stage Deep Learning Approach for Digitization of Paper ECGs and Automated Cardiovascular Disease Classification Hong-Cheol Yoon, Dong-Kyu Kim, Hyun-Seok Kim, Woo-Young Seo, Chang-Hoe Heo, Sung-Hoon Kim TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
Berru's widows 265 U-Net Guided Digitization of 12-Lead Printed ECGs Álvaro José Bocanegra, Etel Silva Garcia, Andrea Saglietto, Oscar Camara TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE FALSE
buckeye_ai 402 Comparative Analysis of Digitization and Direct Classification Approaches for Arrhythmia Detection from Paper ECGs using CNN based architectures Jana F. Abedeljaber, Biswajit Padhi, Ping Zhang TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE FALSE
CeZIS 231 Digital signal and image-based ECG classification and its performance by modern residual convolutional networks Peter Bugata, Peter Bugata Jr., Dávid Hudák, Vladimíra Kmečová, Monika Staňková, Ľubomír Antoni, Erik Bruoth, Dávid Gajdoš, Gabriela Vozáriková, Ivan Žežula TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
Deakin_Squad 382 A Versatile, Advanced Framework for Enhanced Multi-Label ECG Classification Leveraging Synergistic Deep and Traditional Machine Learning Techniques Vinayaka Vivekananda Malgi, Sunil Aryal TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
DeepInTheHeart 472 Contrastive Waveform-Image Pretraining for Electrocardiogram Digitization and Classification Adel M. Hassan, Muhammad Nuhan Ahnaf TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
DeRC_ECG 225 DeRC_ECG: Joint UNet-Resnet framework for automated reconstruction and classification of noisy paper-based ECGs Weijie Sun, Siqi Cao TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE
DeTECRohr 370 Enabling ECG Digitization and Classification with Hierachical End-To-End Training Tizian Claus Dege, Maurice Rohr, Christoph Hoog Antink TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE
DSAIL 498 Automated ECG Image Classification with InceptionV3 Antony Gitau, Victor Ruto, David YN Njoroge, Lorna Mugambi, Victoria A. Sitati and Austin Kaburia TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
DSAIL_Nyeri 499 Heart Disease Classification Using EfficientNet B5 with Three-Dimensional Scaled Electrocardiogram Images David Wachira Warutumo, Paul K. Bett, Clinton Mwangi Kuya and Mary Wambui Kariuki TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
easyG 272 U-Net Guided Digitization of 12-Lead Printed ECGs Martin Kropf, Dieter Hayn, Martin Baumgartner, Sai Pavan Kumar Veeranki, Fabian Wiesmueller TRUE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
ECG_UVA 496 Applying pre-trained deep learning models for Multi-Label Classification of Realistic and Noisy Electrocardiogram Images Navchetan Awasthi, Swati Gupta and Max Aiden Kowalchuk TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
ECGénie 481 Deep Learning Image Segmentation for Time-Series Reconstruction from ECG Images Samer Jammoul, Abdullatif Hassan, Emily Zhang, Philip Warrick, Jonathan Afilalo TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE
ETH_SCAI_Lab 174 Comprehensive ECG classification using Tree Models and YOLOv8 Shreyasvi Natraj, Bertram Fuchs, Diego Paez TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
GIRAFFE 210 GIRAFFE: Crafting Deep Learning Ensembles for Classifying ECG Paper Printouts Damian Marek Kucharski, Arkadiusz Paweł Czerwiński, Agata Maria Wijata, Jacek Kawa, Yalin Zheng, Gregory Lip, Jakub Nalepa TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE
Heartsmiths 458 Enhancing ECG Digitization and Diagnostic Accuracy through Operational Generative Adversarial Networks Muhammad Uzair Zahid, Zarmeen Shahid, Khuzaima Shahid, Serkan Kiranyaz, Moncef Gabbouj TRUE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
Inria Epione 372 Leveraging Binarized Generated Images for Enhanced Denoising and Digitization of Scanned ECGs Rafael Silva, Yingyu Yang, Maëlis Morier, Safaa Al-Ali, Maxime Sermesant TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE
Inventec AIC 224 Dual Deep Learning System to Digitalize and Classify 12-Lead ECGs from Scanned Images Chou ChunTi, Sergio González Vázquez TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
ISIBrno-AIMT 4 Paper is not Dead: Automated Conversion and Analysis of Printed ECG Using Object Detection, Attention, and Siamese Neural Networks Jan Pavlus, Kristyna Pijackova, Veronika Vicianova, Petr Nejedly, Filip Plesinger TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
Leicester Fox 343 Hybrid Approach for Electrocardiogram Images Classification: Residual Network and Random Forest Jingzhi Gong, NOOR QAQOS, Chintan Patel, Ekenedirichukwu Nelson Obianom, Shamsu Idris Abdullahi, Fan Feng, Abdulmalik Koya, Abdulhamed Mohammed Jasim, ZAID A. ABOD, G. Andre Ng, Xin Li TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
Lubdub 433 Cardiovascular Diseases Classification based on ECG Scans with Transfer Learning Hui Lu, Adithya Ramachandran TRUE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
mins-eth 199 Convolutional Neural Networks with Spatial Transformer Modules for End-to-End Digitization of Paper Electrocardiogram Records Haoliang Shang, Clemens Hutter, Rodrigo Casado Noguerales, Yani Zhang TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
MultiMeDIA_OX 435 Automated Deep Learning Based Digitization and Classification of Paper Electrocardiograms Haobo Zhu, Mohammad Atwany, Alexander James Sharp, Abhirup Banerjee TRUE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
Paper2Pulse 31 Paper2Pulse: Advancing Cardiovascular Diagnosis through Digitization and Classification of ECG Images MINJUNG KANG, HyunJee Nam, Gi nam Kim, Sunghwan Park, Il-Youp Kwak, jaewoo Lee TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
PapyrusECG 495 Fusion of Deep Learning and Rule-Based Techniques for Enhanced Paper-Based ECG Digitization Amaan Kazi, Kelvin K. Nguyen, Varun Sendilraj, Shadi Manafi, Sasan Esfahani, Zaniar Ardalan and Saman Parvaneh TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
PKU_NIHDS 326 Text-to-ECG Generation and Image Style Transfer Helps ECG Images Digitalization and Classification Zisheng Liang, Shanwei Zhang, 可鑫 王, qinghao zhao, Deyun Zhang, Shijia Geng, Jun Li, Yuxi Zhou, Shenda Hong TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE
Proton 249 ECG Image Digitization Based on ResUNet-YOLO and Anomaly Detection Using Multi-branch SE-ResNet Model Zhen Wang, Hanshuang Xie, Yamin Liu, MN Zheng TRUE FALSE TRUE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
PulsePlex 393 Transformative Multimodal Fusion Techniques for ECG Image Analysis: PulsePlex's Approach for Classification and Waveforms Reconstruction MD. Kamrujjaman Mobin TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
Revenger 128 A Novel Multi-Task Learning Framework for Simultaneous Digitization and Classification of Electrocardiogram Images Jingsu Kang, Hao WEN TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
RoadRuNNers 247 Driving ECG digitization - Using Techniques from Autonomous Driving to Detect Regions of Interest in ECG Images Philip Hempel, Nicolai Spicher TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE
RPG_ML@IISC 80 Automating the Digitization of ECG Images with Deep Neural Networks Vasanth Kumar B, Rahul Pandit FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
RPG_ML@IISC 81 Automating the Classification of ECG Images with Deep Neural Networks Vasanth Kumar B, Rahul Pandit TRUE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
shenhai_dl 468 A hybrid method combining graph convolutional network and structured state space model for reconstructing and classifying paper ECGs Xiang Wang TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
SignalSavants 97 Digitising ECG Images: A Vision to Time Series Transformer Vs. A Pipeline of Specialised Deep-Learning Models Felix H. Krones, Terry J. Lyons, Adam Mahdi, Benjamin Walker TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
Team_IRS 385 Optimizing 12-Lead Electrocardiogram Abnormality Detection with VGGNet and ResNet Ravindu Hiran Weerakoon, Sasika Pamith Amarasinghe, Isiri Amani Withanawasam TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
The Easy Geese 118 A modular framework for the interpretation of paper ECGs Sara Summerton, Tuija Leinonen, George Searle, Matti Kaisti, David C. Wong TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE FALSE
TimeBeater 167 High-Fidelity Digitization and Automated Classification of Electrocardiograms Using Wave-GAN and ResNet-50 Frameworks ke jiang, Runze Shen, 政 胡, sibo wang TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
tju_forest 158 An electrocardiogram (ECG) digital system for the extraction and classification of paper-based ECG 雨晴 王, Yulin Sun, Leshui David, 张 之涵, Runnan He, Xiuyun Liu TRUE FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE FALSE
Toy Story 375 Efficient End-to-End Neural Network Architecture for Denoising-Extraction-Classification on ECG Images zirui wang, sunxiaohe li, yizhuo feng, yang liu TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
uhealthcareteam 73 Overcoming Modality Gaps: Self-Supervised Learning for Image-based Cardiovascular Disease Detection Yeongyeon Na, Minje Park, Taehyung Yu, Jeonghwa Lim, Younghoon Ji, Sunghoon Joo TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
USST_Med 134 From Paper to Digital: ECG Processing with U-Net Digitization and ResNet Classification Xiankai Yu, Yangcheng Huang, Jian Wu, Jiahao Wang, Wenjie Cai TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
VinUniTeam 135 VinDigitizer: A Hybrid Approach to Digitize Paper-based ECG Records Cuong V. Nguyen, Hieu Xuan Nguyen, Nhat Duong Anh, Cuong Do TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
VitalRhythms 159 Transformer-Based Deep Learning Approach for the Digitization and Classification of Physical ECG Paper Images Mohanad Alkhodari, Mostafa Mohamed Moussa, Leontios J. Hadjileontiadis, Ahsan Khandoker TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE FALSE
wavie_ABI 229 WAVIE: A Modular and Open-Source Python Implementation for Fully Automated Digitisation of Paper Electrocardiograms Mathilde A. Verlyck, Joshua R. Dillon, Stephen A. Creamer, Debbie Zhao TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE FALSE TRUE FALSE
YAMA 222 Enhanced ECG Signal Classification and Reconstruction Using Deep Features and Extra Trees Classifier ruhallah amandi TRUE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
ZHAW_ET 373 ECG Digitization by Classical Digital Image Processing Federico Wadehn, Remo Schneider, Janic Aeschbacher TRUE FALSE TRUE FALSE FALSE FALSE TRUE TRUE TRUE TRUE FALSE
Loading

0 comments on commit 05c6ea5

Please sign in to comment.