Deep Learning on Bone Scintigraphy to Detect Abnormal Cardiac Uptake at Risk of Cardiac Amyloidosis.

BACKGROUND: Cardiac uptake on technetium-99m whole-body scintigraphy (WBS) is almost pathognomonic of transthyretin cardiac amyloidosis. The rare false positives are often related to light-chain cardiac amyloidosis. However, this scintigraphic feature remains largely unknown, leading to misdiagnosis despite characteristic images. A retrospective review of all WBSs in a hospital database to detect those with cardiac uptake may allow the identification of undiagnosed patients. OBJECTIVES: The authors sought to develop and validate a deep learning-based model that automatically detects significant cardiac uptake (Perugini grade ≥2) on WBS from large hospital databases in order to retrieve patients at risk of cardiac amyloidosis. METHODS: The model is based on a convolutional neural network with image-level labels. The performance evaluation was performed with C-statistics using a 5-fold cross-validation scheme stratified so that the proportion of positive and negative WBSs remained constant across folds and using an external validation data set. RESULTS: The training data set consisted of 3,048 images: 281 positives (Perugini grade ≥2) and 2,767 negatives. The external validation data set consisted of 1,633 images: 102 positives and 1,531 negatives. The performance of the 5-fold cross-validation and external validation was as follows: 98.9% (± 1.0) and 96.1% for sensitivity, 99.5% (± 0.4) and 99.5% for specificity, and 0.999 (SD = 0.000) and 0.999 for the area under the curve of the receiver-operating characteristic curves. Sex, age <90 years, body mass index, injection-acquisition delay, radionuclides, and the indication of WBS only slightly affected performances. CONCLUSIONS: The authors' detection model is effective at identifying patients with cardiac uptake Perugini grade ≥2 on WBS and may help in the diagnosis of patients with cardiac amyloidosis.

Prevalence and determinants of iron deficiency in cardiac amyloidosis.

AIMS: Iron deficiency (ID) is common in patient with chronic heart failure (HF) and has been widely studied. In contrast, data concerning ID in cardiac amyloidosis (CA) are limited. Amyloidosis is a severe and fatal systemic disease, characterized by an accumulation of amyloid fibrils in various tissues/organs, including nerves, kidneys, gastrointestinal tract, and heart. Amyloid deposits in the heart eventually cause HF. The main subtypes of CA are light chain (AL), hereditary transthyretin (ATTRv), and wild-type transthyretin (ATTRwt). We performed this study to determine the prevalence, clinical outcome (all-cause mortality), and determinants of ID among the three main subtypes of CA. METHODS AND RESULTS: Iron deficiency status were analysed in 816 CA patients enrolled at the French Referral Centre for Cardiac Amyloidosis: 271 (33%) had AL, 164 (20%) ATTRv, and 381 (47%) ATTRwt. ID affected 49% of CA patients, 45% with AL, 58% with ATTRv, and 48% with ATTRwt. We identified ATTR status (ATTRv P = 0.003, ATTRwt P = 0.037), diabetes (P = 0.003), aspirin treatment (P = 0.009), haemoglobin levels (P = 0.006), and altered global longitudinal strain (P = 0.02) as independent ID determinants. There is no difference in all-cause mortality considering ID status. CONCLUSIONS: Iron deficiency is common in patients with CA, irrespective of the subtype. Patients seem more likely to have ID if diagnosed with ATTR, if diabetic, and/or treated with aspirin. In CA, the benefit of intravenous iron therapy, for ID, on morbidity and mortality needs further study.

Prognostic Value of N-Terminal Pro-Brain Natriuretic Peptide and High-Sensitivity Troponin T Levels in the Natural History of Transthyretin Amyloid Cardiomyopathy and Their Evolution after Tafamidis Treatment.

BACKGROUND: We assesse the evolution and prognostic value of N-terminal pro-brain natriuretic peptide (NT-proBNP) and high-sensitivity troponin T (cTnT-HS) in transthyretin amyloid cardiomyopathy (ATTR-CA) before and after tafamidis treatment. METHODS AND RESULTS: 454 ATTR-CA patients without tafamidis (Cohort A) and 248 ATTR-CA with tafamidis (Cohort B) were enrolled. Event-free survival (EFS) events were death, heart transplant, or acute heart failure. In Cohort A, 27% of patients maintained NT-proBNP < 3000 ng/L and 14% cTnT-HS < 50 ng/L at 12 months relative to baseline levels. In Cohort B, the proportions were 49% and 29%, respectively. In Cohort A, among the 333 patients without an increased NT-proBNP > 50% relative to baseline EFS was extended compared to the 121 patients with an increased NT-proBNP > 50% (HR: 0.75 [0.57; 0.98]; p = 0.032). In Cohort A, baseline NT-proBNP > 3000 ng/L and cTnT-HS > 50 ng/L and a relative increase of NT-proBNP > 50% during follow-up were independent prognostic factors of EFS. The slopes of logs NT-proBNP and cTnT-HS increased with time before and stabilized after tafamidis. CONCLUSION: ATTR-CA patients with increasing NT-proBNP had an increased risk of EFS. Tafamidis stabilize NT-proBNP and cTnT-HS increasing, even if initial NT-proBNP levels were >3000 ng/L. Thus suggesting that all patients, irrespective of baseline NT-proBNP levels, may benefit from tafamidis.