More Web Proxy on the site http://driver.im/

research-article

Open access

Choice Over Effort: Mapping and Diagnosing Augmented Whole Slide Image Datasets with Training Dynamics

Authors:

Benoit Louis Marteau,

May Dongmei WangAuthors Info & Claims

BCB '23: Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

Article No.: 28, Pages 1 - 6

https://doi.org/10.1145/3584371.3612980

Published: 04 October 2023 Publication History

Abstract

In pediatric heart transplantation, manual annotations with interob-server and intraobserver variability among cardiovascular pathology experts lead to significant disagreements about the severity of rejection. Artificial intelligence (AI)-enabled computational pathology usually requires large-scale manual annotations of gigapixel whole-slide images (WSIs) for effective model training. To address these challenges, we develop and validate an AI-enabled rare disease detection framework for automating heart transplant rejection detection from whole-slide images of pediatric patients. Specifically, we conduct a novel dataset cartography with data maps and training dynamics to map and diagnose the augmented samples, exploring the model behavior on individual instances during model training. Extensive experiments on internal and external patient cohorts have demonstrated the feasibility of both tile-level and biopsy-level detection. The proposed data-efficient learning framework may support seamless scalability to real-world rare disease detection without the burden of iterative expert annotations.

References

[1]

Monica Colvin-Adams and Adheesh Agnihotri. 2011. Cardiac allograft vasculopathy: current knowledge and future direction. Clinical transplantation 25, 2 (2011), 175--184.

[2]

Adrienne E Dooley, Li Tong, Shriprasad R Deshpande, and May D Wang. 2018. Prediction of heart transplant rejection using histopathological whole-slide imaging. In 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI). IEEE, 251--254.

[3]

Felipe O Giuste, Ryan Sequeira, Vikranth Keerthipati, Peter Lais, Ali Mirzazadeh, et al. 2023. Explainable synthetic image generation to improve risk assessment of rare pediatric heart transplant rejection. Journal of Biomedical Informatics 139 (2023), 104303.

Digital Library

[4]

Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, et al. 2020. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139--144.

Digital Library

[5]

Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33 (2020), 6840--6851.

[6]

Siddharth Karamcheti, Ranjay Krishna, Li Fei-Fei, and Christopher D Manning. 2021. Mind your outliers! investigating the negative impact of outliers on active learning for visual question answering. arXiv preprint arXiv:2107.02331 (2021).

[7]

Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2017. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017).

[8]

Abdallah G Kfoury, M Elizabeth H Hammond, Gregory L Snow, Stavros G Drakos, Josef Stehlik, et al. 2009. Cardiovascular mortality among heart transplant recipients with asymptomatic antibody-mediated or stable mixed cellular and antibody-mediated rejection. The Journal of heart and lung transplantation 28, 8 (2009), 781--784.

[9]

Jana Lipkova, Tiffany Y Chen, Ming Y Lu, Richard J Chen, Maha Shady, et al. 2022. Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies. Nature medicine 28, 3 (2022), 575--582.

[10]

Ming Y Lu, Drew FK Williamson, Tiffany Y Chen, Richard J Chen, Matteo Barbieri, et al. 2021. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering 5, 6 (2021), 555--570.

[11]

Faisal Mahmood and Eric J Topol. 2022. Digitising heart transplant rejection. The Lancet 400, 10345 (2022), 17.

[12]

Ali Mirzazadeh, Arshawn Mohseni, Sahar Ibrahim, Felipe O Giuste, Yuanda Zhu, et al. 2021. Improving heart transplant rejection classification training using progressive generative adversarial networks. In 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI). IEEE, 1--4.

[13]

Marc E. Richmond, Steven D. Zangwill, Steven J. Kindel, Shriprasad R. Deshpande, Jacob N. Schroder, et al. 2020. Donor fraction cell-free DNA and rejection in adult and pediatric heart transplantation. The Journal of Heart and Lung Transplantation 39, 5 (2020), 454--463.

[14]

Baptiste Rozière, Morgane Riviere, Olivier Teytaud, Jérémy Rapin, Yann LeCun, et al. 2021. Inspirational Adversarial Image Generation. IEEE Transactions on Image Processing 30 (2021), 4036--4045.

Digital Library

[15]

Martin Schweiger, Brian Stiasny, Hitendu Dave, Anna Cavigelli-Brunner, Christian Balmer, et al. 2015. Pediatric heart transplantation. Journal of thoracic disease 7, 3 (2015), 552.

[16]

Tobias Paul Seraphin, Mark Luedde, Christoph Roderburg, Marko van Treeck, Pascal Scheider, et al. 2023. Prediction of heart transplant rejection from routine pathology slides with self-supervised Deep Learning. European Heart JournalDigital Health 4, 3 (2023), 265--274.

[17]

Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, et al. 2020. Dataset cartography: Mapping and diagnosing datasets with training dynamics. arXiv preprint arXiv:2009.10795 (2020).

[18]

Li Tong, Ying Sha, and May D Wang. 2019. Improving classification of breast cancer by utilizing the image pyramids of whole-slide imaging and multi-scale convolutional neural networks. In 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Vol. 1. IEEE, 696--703.

[19]

Li Tong, Hang Wu, and May D Wang. 2019. CAESNet: Convolutional AutoEncoder based Semi-supervised Network for improving multiclass classification of endomicroscopic images. Journal of the American Medical Informatics Association 26, 11 (2019), 1286--1296.

[20]

Arash Vahdat, Karsten Kreis, and Jan Kautz. 2021. Score-based generative modeling in latent space. Advances in Neural Information Processing Systems 34 (2021), 11287--11302.

[21]

Mike Zhang and Barbara Plank. 2021. Cartography active learning. arXiv preprint arXiv:2109.04282 (2021).

[22]

Yuchen Zhuang, Yue Yu, Lingkai Kong, Xiang Chen, and Chao Zhang. 2023. Dy-Gen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling. arXiv preprint arXiv:2305.19395 (2023).

[23]

Boback Ziaeian and Gregg C Fonarow. 2016. Epidemiology and aetiology of heart failure. Nature Reviews Cardiology 13, 6 (2016), 368--378.

Cited By

Shi WMurakoso MGuo XWang M(2023)Development of Interpretable Machine Learning Models for COVID-19 Drug Target Docking Scores Prediction2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)10.1109/BIBM58861.2023.10385756(4124-4131)Online publication date: 5-Dec-2023
https://doi.org/10.1109/BIBM58861.2023.10385756
Shi WMurakoso MGuo XXiong LChen MWang M(2023)Effective Surrogate Models for Docking Scores Prediction of Candidate Drug Molecules on SARS-CoV-2 Protein Targets2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)10.1109/BIBM58861.2023.10385643(4235-4242)Online publication date: 5-Dec-2023
https://doi.org/10.1109/BIBM58861.2023.10385643

Index Terms

Choice Over Effort: Mapping and Diagnosing Augmented Whole Slide Image Datasets with Training Dynamics
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches

Recommendations

An approach for detecting blood vessel diseases from cone-beam CT image
ICIP '95: Proceedings of the 1995 International Conference on Image Processing (Vol.2)-Volume 2 - Volume 2

This paper is aimed at assisting a medical doctor to detect blood vessel diseases from the high-resolution 3D blood vessels images obtained by cone-beam CT. The important objective is to show how the representation of blood vessels morphology can lead ...
Retinal image segmentation using double‐scale non‐linear thresholding on vessel support regions

Retinal vessel segmentation is a critical indicator of diagnosis, screening, and treatment of cardiovascular and ophthalmologic diseases. Due to the fact that the retinal vessels usually have some tiny structures and blurred boundaries, especially with ...
Automated Vascular Smooth Muscle Segmentation, Reconstruction, Classification and Simulation on Whole-Slide Histology

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

BCB '23: Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

September 2023

626 pages

ISBN:9798400701269

DOI:10.1145/3584371

General Chairs:
May D. Wang
SGeorgia Institute of Technology
,
Byung-Jun Yoon

Copyright © 2023 Owner/Author(s).

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGBio: ACM Special Interest Group on Bioinformatics

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 04 October 2023

Check for updates

Author Tags

Qualifiers

Research-article

Conference

BCB '23

Sponsor:

SIGBio

BCB '23: 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

September 3 - 6, 2023

TX, Houston, USA

Acceptance Rates

Overall Acceptance Rate 254 of 885 submissions, 29%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
342
Total Downloads

Downloads (Last 12 months)236
Downloads (Last 6 weeks)31

Reflects downloads up to 09 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Shi WMurakoso MGuo XWang M(2023)Development of Interpretable Machine Learning Models for COVID-19 Drug Target Docking Scores Prediction2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)10.1109/BIBM58861.2023.10385756(4124-4131)Online publication date: 5-Dec-2023
https://doi.org/10.1109/BIBM58861.2023.10385756
Shi WMurakoso MGuo XXiong LChen MWang M(2023)Effective Surrogate Models for Docking Scores Prediction of Candidate Drug Molecules on SARS-CoV-2 Protein Targets2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)10.1109/BIBM58861.2023.10385643(4235-4242)Online publication date: 5-Dec-2023
https://doi.org/10.1109/BIBM58861.2023.10385643

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten