scholarly journals 70 Deep learning to diagnose cardiac amyloidosis from cardiac magnetic resonance findings

2020 ◽  
Vol 22 (Supplement_N) ◽  
pp. N116-N130
Author(s):  
Alberto Aimo ◽  
Nicola Martini ◽  
Andrea Barison ◽  
Daniele Della Latta ◽  
Giuseppe Vergaro ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Cardiac Amyloidosis ◽  
Diagnostic Yield ◽  
Area Under The Curve ◽  
Blood Pool ◽  
Left Ventricular ◽  
Blood Dyscrasia ◽  
Test Accuracy

Abstract Aims Cardiac 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 and results 1.5 T CMR was performed in 187 subjects with suspected CA (n = 92, 49% with unexplained left ventricular—LV—hypertrophy; n = 95, 51% with blood dyscrasia and suspected light-chain amyloidosis). Patients were randomly assigned to the training (n = 121, 65%), validation (n = 28, 15%), and testing subgroups (n = 38, 20%). Short axis (SA), 2-chamber (2 C), 4-chamber (4 C) 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. The DL strategy displayed good diagnostic accuracy (84%), with an area under the curve (AUC) of 0.96. The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 78%, 94%, and 86% respectively. A ML algorithm considering all CMR features had a similar diagnostic yield to DL strategy (AUC 0.93 vs. 0.96; p = 0.45). Conclusion 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.

scholarly journals Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance

2020 ◽  
Vol 22 (1) ◽  
Author(s):  
Nicola Martini ◽  
Alberto Aimo ◽  
Andrea Barison ◽  
Daniele Della Latta ◽  
Giuseppe Vergaro ◽  
...  
Keyword(s):  
Cardiovascular Magnetic Resonance ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Cardiac Amyloidosis ◽  
Diagnostic Yield ◽  
Area Under The Curve ◽  
Blood Pool ◽  
Left Ventricular ◽  
Blood Dyscrasia ◽  
Test Accuracy

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.

Deep learning to diagnose cardiac amyloidosis from CMR findings

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
A Aimo ◽  
N Martini ◽  
A Barison ◽  
D Della Latta ◽  
A Ripoli ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Strategies ◽  
Cardiac Amyloidosis ◽  
Left Ventricular ◽  
Automated Image Analysis ◽  
Blood Dyscrasia ◽  
Gradient Boosting ◽  
Al Amyloidosis ◽  
Test Accuracy ◽  
Imaging Features

Abstract Background Cardiac magnetic resonance (CMR) is an important diagnostic technique for cardiac amyloidosis (CA). A deep learning (DL) approach to define the likelihood of CA based on automated interpretation of CMR images has never been attempted so far. Methods 187 subjects underwent standard 1.5 T CMR examination (GE-Healthcare, Milwaukee, USA) as part of a diagnostic workup for either unexplained left ventricular hypertrophy or blood dyscrasia with suspected light-chain (AL) amyloidosis. Patients were randomly assigned to 3 subgroups, which were used for training (n=121, 65%), internal validation (n=28, 15%), and model testing (n=38, 20%). LGE images in different orientations (short-axis, 2- and 4-chambers) were selected as the most informative CMR features. A deep convolutional neural network was trained to classify CMR examinations as “amyloidosis” (probability ≥50%) or “no amyloidosis” (probability &lt;50%) based on these features. Different learning strategies (data augmentation, batch normalization in convolutional layers, dropout before dense layers) were adopted to prevent model overfitting. Binary cross entropy was used as loss function. For comparison, a machine learning (ML) model based on gradient boosting trees was built for the binary classification of patients (amyloidosis vs no amyloidosis) based on clinical and imaging features extracted from the CMR exam. Results CA was diagnosed in 101 subjects (54%; 45 AL, 56 transthyretin amyloidosis). A model including 2C, 4C and SA LGE images was created. In the test cohort, it allowed to diagnose CA with good diagnostic accuracy (84.2%), and an area under the curve (AUC) of 0.96 (Figure). The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 0.78, 0.94, and 0.86, respectively. An ML algorithm considering all available parameters (LV volumes and function, LGE presence and pattern, early darkening, pericardial and pleural effusion, etc.) displayed a similar diagnostic performance than the DL method (AUC 0.93 vs. 0.96; p=0.45). Conclusions The deep learning technique allowed to create an accurate diagnostic tool for CA based on LGE patterns, which could be easily converted into an online platform for automated image analysis. Funding Acknowledgement Type of funding source: None

scholarly journals Deep Learning to Estimate Cardiac Magnetic Resonance-Derived Left Ventricular Mass

2020 ◽  
Author(s):  
Shaan Khurshid ◽  
Samuel Friedman ◽  
James P. Pirruccello ◽  
Paolo Di Achille ◽  
Nathaniel Diamant ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Open Source ◽  
Pearson Correlation ◽  
Absolute Error ◽  
Learning Model ◽  
Left Ventricular ◽  
Lv Mass ◽  
Deep Learning Model

ABSTRACTBackgroundCardiac magnetic resonance (CMR) is the gold standard for left ventricular hypertrophy (LVH) diagnosis. CMR-derived LV mass can be estimated using proprietary algorithms (e.g., inlineVF), but their accuracy and availability may be limited.ObjectiveTo develop an open-source deep learning model to estimate CMR-derived LV mass.MethodsWithin participants of the UK Biobank prospective cohort undergoing CMR, we trained two convolutional neural networks to estimate LV mass. The first (ML4Hreg) performed regression informed by manually labeled LV mass (available in 5,065 individuals), while the second (ML4Hseg) performed LV segmentation informed by inlineVF contours. We compared ML4Hreg, ML4Hseg, and inlineVF against manually labeled LV mass within an independent holdout set using Pearson correlation and mean absolute error (MAE). We assessed associations between CMR-derived LVH and prevalent cardiovascular disease using logistic regression adjusted for age and sex.ResultsWe generated CMR-derived LV mass estimates within 38,574 individuals. Among 891 individuals in the holdout set, ML4Hseg reproduced manually labeled LV mass more accurately (r=0.864, 95% CI 0.847-0.880; MAE 10.41g, 95% CI 9.82-10.99) than ML4Hreg (r=0.843, 95% CI 0.823-0.861; MAE 10.51, 95% CI 9.86-11.15, p=0.01) and inlineVF (r=0.795, 95% CI 0.770-0.818; MAE 14.30, 95% CI 13.46-11.01, p<0.01). LVH defined using ML4Hseg demonstrated the strongest associations with hypertension (odds ratio 2.76, 95% CI 2.51-3.04), atrial fibrillation (1.75, 95% CI 1.37-2.20), and heart failure (4.53, 95% CI 3.16-6.33).ConclusionsML4Hseg is an open-source deep learning model providing automated quantification of CMR-derived LV mass. Deep learning models characterizing cardiac structure may facilitate broad cardiovascular discovery.

scholarly journals A Deep Learning Segmentation Approach in Free-Breathing Real-Time Cardiac Magnetic Resonance Imaging

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Fan Yang ◽  
Yan Zhang ◽  
Pinggui Lei ◽  
Lihui Wang ◽  
Yuehong Miao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Cardiac Function ◽  
Data Augmentation ◽  
Function Analysis ◽  
Free Breathing ◽  
Blood Pool ◽  
Training Time ◽  
Segmentation Approach

Objectives. The purpose of this study was to segment the left ventricle (LV) blood pool, LV myocardium, and right ventricle (RV) blood pool of end-diastole and end-systole frames in free-breathing cardiac magnetic resonance (CMR) imaging. Automatic and accurate segmentation of cardiac structures could reduce the postprocessing time of cardiac function analysis. Method. We proposed a novel deep learning network using a residual block for the segmentation of the heart and a random data augmentation strategy to reduce the training time and the problem of overfitting. Automated cardiac diagnosis challenge (ACDC) data were used for training, and the free-breathing CMR data were used for validation and testing. Results. The average Dice was 0.919 (LV), 0.806 (myocardium), and 0.818 (RV). The average IoU was 0.860 (LV), 0.699 (myocardium), and 0.761 (RV). Conclusions. The proposed method may aid in the segmentation of cardiac images and improves the postprocessing efficiency of cardiac function analysis.

scholarly journals Comparison between echocardiography and cardiac magnetic resonance for differential diagnosis of left ventricular hypertrophy

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
E Corsi ◽  
G Todiere ◽  
A Barison ◽  
C Grigoratos ◽  
G.D Aquaro
Keyword(s):  
Differential Diagnosis ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Left Ventricular Hypertrophy ◽  
Cardiac Amyloidosis ◽  
Ventricular Hypertrophy ◽  
Left Ventricular ◽  
Athlete’S Heart ◽  
Kaplan Meier ◽  
Athlete's Heart

Abstract Background Left ventricular hypertrophy (LVH) may be due to different causes, ranging from, benign secondary forms (athlete's heart) to severe prognosis cardiomyopathies (i.e. cardiac amyloidosis). Early and accurate differential diagnosis is important to proper patient management. LVH may be detected by echocardiography signs of hypertrophy or other abnormalities often associated to hypertrophic phenotypes. Cardiac magnetic resonance (CMR) is often used to confirm the initial diagnostic suspicion. On the best of our knowledge, there are no study specifically designed to evaluate the final impact of CMR in changing or confirming the initial diagnostic echocardiographic suspicion. Aim To evaluate the clinical prognostic correlates of CMR in patients with echocardiographic or ECG suspicion of LVH (or cardiomyopathies with hypertrophic phenotype). Methods and results We enrolled 275 pts with echocardiographic evidence of LVH. Using current guidelines, the initial echocardiographic diagnostic suspicion was: hypertrophic cardiomyopathy (HCM) in 46.9% of pts; cardiac amyloidosis in 14.5%; hypertensive LVH in 17%; aortic stenosis in 1.5%; athlete's heart in 0.3%; undetermined LVH in 17%. CMR changed the diagnosis in 42% cases: the diagnosis of HCM increased from 44% to 72% of pts; hypertensive and undetermined LVH decreased significantly (respectively to 4% and 5%). Finally, the change in diagnostic suspicion was associated to reclassification of risk of patients: Kaplan-Meier curves demonstrated that HCM and cardiac amyloidosis had worst prognosis than undetermined or hypertensive LVH. Conclusions CMR changed the echocardiographic suspicion in almost half of patients with LVH. This study highlights the indication of CMR in patient with ECG or echocardiographic suspicion of LVH. Kaplan-Meier curves Funding Acknowledgement Type of funding source: None

scholarly journals Amyloid Deposits and Fibrosis on Left Ventricular Endomyocardial Biopsy Correlate With Extracellular Volume in Cardiac Amyloidosis

2021 ◽  
Author(s):  
Angela Pucci ◽  
Alberto Aimo ◽  
Veronica Musetti ◽  
Andrea Barison ◽  
Giuseppe Vergaro ◽  
...  
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Endomyocardial Biopsy ◽  
Cardiac Amyloidosis ◽  
Troponin T ◽  
Tissue Sample ◽  
Extracellular Volume ◽  
Left Ventricular ◽  
Transthyretin Amyloidosis ◽  
Amyloid Deposits

Background The relative contribution of amyloid and fibrosis to extracellular volume expansion in cardiac amyloidosis (CA) has never been defined. Methods and Results We included all patients diagnosed with amyloid light‐chain (AL) or transthyretin cardiac amyloidosis at a tertiary referral center between 2014 to 2020 and undergoing a left ventricular endomyocardial biopsy. Patients (n=37) were more often men (92%), with a median age of 72 years (interquartile range, 68–81). Lambda‐positive AL was found in 14 of 19 AL cases (38%) and kappa‐positive AL in 5 of 19 (14%), while transthyretin was detected in the other 18 cases (48%). Amyloid deposits accounted for 15% of tissue sample area (10%–30%), without significant differences between AL and transthyretin amyloidosis. All patients displayed myocardial fibrosis, with a median extent of 15% of tissue samples (10%–23%; range, 5%–60%), in the absence of spatial overlap with amyloid deposits. Interstitial fibrosis was often associated with mild and focal subendocardial fibrosis. The extent of fibrosis or the combination of amyloidosis and fibrosis did not differ significantly between transthyretin amyloidosis and AL subgroups. In 20 patients with myocardial T1 mapping at cardiac magnetic resonance, the combined amyloid and fibrosis extent displayed a modest correlation with extracellular volume ( r =0.661, P =0.001). The combined amyloid and fibrosis extent correlated with high‐sensitivity troponin T ( P =0.035) and N‐terminal pro‐B‐type natriuretic peptide ( P =0.002) serum levels. Conclusions Extracellular spaces in cardiac amyloidosis are enlarged to a similar extent by amyloid deposits and fibrotic tissue. Their combination can better explain the increased extracellular volume at cardiac magnetic resonance and circulating biomarkers than amyloid extent alone.

scholarly journals Deep Learning to Predict Cardiac Magnetic Resonance–Derived Left Ventricular Mass and Hypertrophy From 12-Lead ECGs

2021 ◽  
Vol 14 (6) ◽  
Author(s):  
Shaan Khurshid ◽  
Samuel Friedman ◽  
James P. Pirruccello ◽  
Paolo Di Achille ◽  
Nathaniel Diamant ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Left Ventricular Mass ◽  
Left Ventricular ◽  
Uk Biobank ◽  
C Statistic ◽  
Lv Mass ◽  
Test Sets ◽  
The Uk

Background: Classical methods for detecting left ventricular (LV) hypertrophy (LVH) using 12-lead ECGs are insensitive. Deep learning models using ECG to infer cardiac magnetic resonance (CMR)-derived LV mass may improve LVH detection. Methods: Within 32 239 individuals of the UK Biobank prospective cohort who underwent CMR and 12-lead ECG, we trained a convolutional neural network to predict CMR-derived LV mass using 12-lead ECGs (left ventricular mass-artificial intelligence [LVM-AI]). In independent test sets (UK Biobank [n=4903] and Mass General Brigham [MGB, n=1371]), we assessed correlation between LVM-AI predicted and CMR-derived LV mass and compared LVH discrimination using LVM-AI versus traditional ECG-based rules (ie, Sokolow-Lyon, Cornell, lead aVL rule, or any ECG rule). In the UK Biobank and an ambulatory MGB cohort (MGB outcomes, n=28 612), we assessed associations between LVM-AI predicted LVH and incident cardiovascular outcomes using age- and sex-adjusted Cox regression. Results: LVM-AI predicted LV mass correlated with CMR-derived LV mass in both test sets, although correlation was greater in the UK Biobank (r=0.79) versus MGB (r=0.60, P<0.001 for both). When compared with any ECG rule, LVM-AI demonstrated similar LVH discrimination in the UK Biobank (LVM-AI c-statistic 0.653 [95% CI, 0.608 -0.698] versus any ECG rule c-statistic 0.618 [95% CI, 0.574 -0.663], P=0.11) and superior discrimination in MGB (0.621; 95% CI, 0.592 -0.649 versus 0.588; 95% CI, 0.564 -0.611, P=0.02). LVM-AI-predicted LVH was associated with incident atrial fibrillation, myocardial infarction, heart failure, and ventricular arrhythmias. Conclusions: Deep learning-inferred LV mass estimates from 12-lead ECGs correlate with CMR-derived LV mass, associate with incident cardiovascular disease, and may improve LVH discrimination compared to traditional ECG rules.

Sign in / Sign up

Export Citation Format

Share Document