Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies.

Lipkova, Jana; Chen, Tiffany Y; Lu, Ming Y; Chen, Richard J; Shady, Maha; Williams, Mane; Wang, Jingwen; Noor, Zahra; Mitchell, Richard N; Turan, Mehmet; Coskun, Gulfize; Yilmaz, Funda; Demir, Derya; Nart, Deniz; Basak, Kayhan; Turhan, Nesrin; Ozkara, Selvinaz; Banz, Yara; Odening, Katja E and Mahmood, Faisal (2022). Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies. Nature medicine, 28(3), pp. 575-582. Springer Nature 10.1038/s41591-022-01709-2

[img] Text
s41591-022-01709-2.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (10MB) | Request a copy

Endomyocardial biopsy (EMB) screening represents the standard of care for detecting allograft rejections after heart transplant. Manual interpretation of EMBs is affected by substantial interobserver and intraobserver variability, which often leads to inappropriate treatment with immunosuppressive drugs, unnecessary follow-up biopsies and poor transplant outcomes. Here we present a deep learning-based artificial intelligence (AI) system for automated assessment of gigapixel whole-slide images obtained from EMBs, which simultaneously addresses detection, subtyping and grading of allograft rejection. To assess model performance, we curated a large dataset from the United States, as well as independent test cohorts from Turkey and Switzerland, which includes large-scale variability across populations, sample preparations and slide scanning instrumentation. The model detects allograft rejection with an area under the receiver operating characteristic curve (AUC) of 0.962; assesses the cellular and antibody-mediated rejection type with AUCs of 0.958 and 0.874, respectively; detects Quilty B lesions, benign mimics of rejection, with an AUC of 0.939; and differentiates between low-grade and high-grade rejections with an AUC of 0.833. In a human reader study, the AI system showed non-inferior performance to conventional assessment and reduced interobserver variability and assessment time. This robust evaluation of cardiac allograft rejection paves the way for clinical trials to establish the efficacy of AI-assisted EMB assessment and its potential for improving heart transplant outcomes.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Pre-clinic Human Medicine > Institute of Physiology
04 Faculty of Medicine > Department of Cardiovascular Disorders (DHGE) > Clinic of Cardiology
04 Faculty of Medicine > Service Sector > Institute of Pathology

UniBE Contributor:

Banz Wälti, Yara Sarah and Odening, Katja Elisabeth

Subjects:

600 Technology > 610 Medicine & health
500 Science > 570 Life sciences; biology

ISSN:

1546-170X

Publisher:

Springer Nature

Language:

English

Submitter:

Pubmed Import

Date Deposited:

23 Mar 2022 10:11

Last Modified:

23 Mar 2022 10:20

Publisher DOI:

10.1038/s41591-022-01709-2

PubMed ID:

35314822

BORIS DOI:

10.48350/167876

URI:

https://boris.unibe.ch/id/eprint/167876

Actions (login required)

Edit item Edit item
Provide Feedback