Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 17, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Improved Prediction on Heart Transplant Rejection Using Convolutional Autoencoder and Multiple Instance Learning on

Yuanda Zhu¹, May D Wang², Li Tong²

¹School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA.

... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics

|June 25, 2020

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Assessing Patient Awareness and Misconceptions Regarding MRI Radiation Risks in China: A Questionnaire Study.

Nursing open·2026

Same author

Lipid droplet-mitochondria tethering releases MAVS inhibition to potentiate antiviral immunity.

Cell reports·2026

Same author

Preparation, characterization and anti-fatigue activity of polysaccharides from <i>Pleurotus eryngii</i>.

Food science and biotechnology·2026

Same author

Impact of metastasis-directed therapy for metachronous thoracic metastases following definitive (chemo)radiotherapy in p16-positive head and neck squamous cell carcinoma.

Oral oncology·2026

Same author

Machine learning based retrospective cohort study to predict mortality risk in Chinese patients undergoing extracorporeal membrane oxygenation.

Scientific reports·2026

Same author

Early pregnancy biomarkers for gestational diabetes mellitus prediction: a systematic review and meta-analysis of routine laboratory, metabolic, and inflammatory markers.

Frontiers in endocrinology·2026

Deep learning models can automatically detect heart transplant rejection from tissue images, improving accuracy and efficiency over manual examination. Unsupervised clustering enhances classification performance for this critical diagnostic task.

Area of Science:

Cardiology
Computational Pathology
Artificial Intelligence in Medicine

Background:

Heart transplant rejection poses a significant threat to patient survival.
Endomyocardial biopsies are crucial for early detection of rejection, even before symptoms appear.
Manual examination of biopsy slides is labor-intensive, costly, and prone to errors.

Purpose of the Study:

To develop an automated deep learning pipeline for detecting heart transplant rejection using whole-slide images.
To enhance the accuracy and efficiency of rejection diagnosis compared to manual methods.
To investigate the impact of unsupervised clustering on classification performance.

Main Methods:

A stacked convolutional autoencoder was used for feature extraction from image tiles.

Keywords:

heart transplant rejection multiple instance learning pathological whole-slide imaging stacked convolutional autoencoder weakly-supervised learning

Related Experiment Videos

Last Updated: Dec 17, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Multiple instance learning (MIL) was combined with dimensionality reduction.

Unsupervised clustering was applied prior to classification for improved performance.

Main Results:

The developed pipeline demonstrated promising results for automatic heart transplant rejection detection.
Integrating unsupervised clustering after feature extraction led to higher classification accuracy.
The method maintained capability for multi-class classification of rejection severity.

Conclusions:

Automated analysis of whole-slide images using deep learning offers a promising alternative to manual biopsy review.
Unsupervised clustering is a valuable technique for improving the performance of deep learning models in transplant rejection classification.
This approach has the potential to streamline diagnostics and improve patient outcomes in heart transplantation.