Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance
Abstract Background Cardiovascular magnetic resonance (CMR) is part of the diagnostic work-up for cardiac amyloidosis (CA). Deep learning (DL) is an application of artificial intelligence that may allow to automatically analyze CMR findings and establish the likelihood of CA. Methods 1.5 T CMR was p...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-12-01
|
Series: | Journal of Cardiovascular Magnetic Resonance |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12968-020-00690-4 |
id |
doaj-66b4abdccc024c8b8359d61499fba750 |
---|---|
record_format |
Article |
spelling |
doaj-66b4abdccc024c8b8359d61499fba7502020-12-08T13:44:07ZengBMCJournal of Cardiovascular Magnetic Resonance1532-429X2020-12-0122111110.1186/s12968-020-00690-4Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonanceNicola Martini0Alberto Aimo1Andrea Barison2Daniele Della Latta3Giuseppe Vergaro4Giovanni Donato Aquaro5Andrea Ripoli6Michele Emdin7Dante Chiappino8Deep Health Unit, Fondazione Toscana Gabriele MonasterioInstitute of Life Sciences, Scuola Superiore Sant’AnnaInstitute of Life Sciences, Scuola Superiore Sant’AnnaDeep Health Unit, Fondazione Toscana Gabriele MonasterioInstitute of Life Sciences, Scuola Superiore Sant’AnnaCardiology Division, Fondazione Toscana Gabriele MonasterioDeep Health Unit, Fondazione Toscana Gabriele MonasterioInstitute of Life Sciences, Scuola Superiore Sant’AnnaDeep Health Unit, Fondazione Toscana Gabriele MonasterioAbstract Background Cardiovascular magnetic resonance (CMR) is part of the diagnostic work-up for cardiac amyloidosis (CA). Deep learning (DL) is an application of artificial intelligence that may allow to automatically analyze CMR findings and establish the likelihood of CA. Methods 1.5 T CMR was performed in 206 subjects with suspected CA (n = 100, 49% with unexplained left ventricular (LV) hypertrophy; n = 106, 51% with blood dyscrasia and suspected light-chain amyloidosis). Patients were randomly assigned to the training (n = 134, 65%), validation (n = 30, 15%), and testing subgroups (n = 42, 20%). Short axis, 2-chamber, 4-chamber late gadolinium enhancement (LGE) images were evaluated by 3 networks (DL algorithms). The tags “amyloidosis present” or “absent” were attributed when the average probability of CA from the 3 networks was ≥ 50% or < 50%, respectively. The DL strategy was compared to a machine learning (ML) algorithm considering all manually extracted features (LV volumes, mass and function, LGE pattern, early blood-pool darkening, pericardial and pleural effusion, etc.), to reproduce exam reading by an experienced operator. Results The DL strategy displayed good diagnostic accuracy (88%), with an area under the curve (AUC) of 0.982. The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 83%, 95%, and 89% respectively. A ML algorithm considering all CMR features had a similar diagnostic yield to DL strategy (AUC 0.952 vs. 0.982; p = 0.39). Conclusions A DL approach evaluating LGE acquisitions displayed a similar diagnostic performance for CA to a ML-based approach, which simulates CMR reading by experienced operators.https://doi.org/10.1186/s12968-020-00690-4Deep learningArtificial intelligenceDiagnosisAmyloidosisCardiovascular magnetic resonance |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Nicola Martini Alberto Aimo Andrea Barison Daniele Della Latta Giuseppe Vergaro Giovanni Donato Aquaro Andrea Ripoli Michele Emdin Dante Chiappino |
spellingShingle |
Nicola Martini Alberto Aimo Andrea Barison Daniele Della Latta Giuseppe Vergaro Giovanni Donato Aquaro Andrea Ripoli Michele Emdin Dante Chiappino Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance Journal of Cardiovascular Magnetic Resonance Deep learning Artificial intelligence Diagnosis Amyloidosis Cardiovascular magnetic resonance |
author_facet |
Nicola Martini Alberto Aimo Andrea Barison Daniele Della Latta Giuseppe Vergaro Giovanni Donato Aquaro Andrea Ripoli Michele Emdin Dante Chiappino |
author_sort |
Nicola Martini |
title |
Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance |
title_short |
Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance |
title_full |
Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance |
title_fullStr |
Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance |
title_full_unstemmed |
Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance |
title_sort |
deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance |
publisher |
BMC |
series |
Journal of Cardiovascular Magnetic Resonance |
issn |
1532-429X |
publishDate |
2020-12-01 |
description |
Abstract Background Cardiovascular magnetic resonance (CMR) is part of the diagnostic work-up for cardiac amyloidosis (CA). Deep learning (DL) is an application of artificial intelligence that may allow to automatically analyze CMR findings and establish the likelihood of CA. Methods 1.5 T CMR was performed in 206 subjects with suspected CA (n = 100, 49% with unexplained left ventricular (LV) hypertrophy; n = 106, 51% with blood dyscrasia and suspected light-chain amyloidosis). Patients were randomly assigned to the training (n = 134, 65%), validation (n = 30, 15%), and testing subgroups (n = 42, 20%). Short axis, 2-chamber, 4-chamber late gadolinium enhancement (LGE) images were evaluated by 3 networks (DL algorithms). The tags “amyloidosis present” or “absent” were attributed when the average probability of CA from the 3 networks was ≥ 50% or < 50%, respectively. The DL strategy was compared to a machine learning (ML) algorithm considering all manually extracted features (LV volumes, mass and function, LGE pattern, early blood-pool darkening, pericardial and pleural effusion, etc.), to reproduce exam reading by an experienced operator. Results The DL strategy displayed good diagnostic accuracy (88%), with an area under the curve (AUC) of 0.982. The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 83%, 95%, and 89% respectively. A ML algorithm considering all CMR features had a similar diagnostic yield to DL strategy (AUC 0.952 vs. 0.982; p = 0.39). Conclusions A DL approach evaluating LGE acquisitions displayed a similar diagnostic performance for CA to a ML-based approach, which simulates CMR reading by experienced operators. |
topic |
Deep learning Artificial intelligence Diagnosis Amyloidosis Cardiovascular magnetic resonance |
url |
https://doi.org/10.1186/s12968-020-00690-4 |
work_keys_str_mv |
AT nicolamartini deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT albertoaimo deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT andreabarison deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT danieledellalatta deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT giuseppevergaro deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT giovannidonatoaquaro deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT andrearipoli deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT micheleemdin deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance AT dantechiappino deeplearningtodiagnosecardiacamyloidosisfromcardiovascularmagneticresonance |
_version_ |
1724389276160884736 |