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


Journal

JACC. Cardiovascular imaging
ISSN: 1876-7591
Titre abrégé: JACC Cardiovasc Imaging
Pays: United States
ID NLM: 101467978

Informations de publication

Date de publication:
08 2023
Historique:
received: 17 03 2022
revised: 09 12 2022
accepted: 05 01 2023
medline: 11 8 2023
pubmed: 25 5 2023
entrez: 25 5 2023
Statut: ppublish

Résumé

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. 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. 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. 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. 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.

Sections du résumé

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.

Identifiants

pubmed: 37227330
pii: S1936-878X(23)00086-4
doi: 10.1016/j.jcmg.2023.01.014
pii:
doi:

Types de publication

Journal Article Research Support, Non-U.S. Gov't

Langues

eng

Sous-ensembles de citation

IM

Pagination

1085-1095

Commentaires et corrections

Type : CommentIn
Type : CommentIn
Type : CommentIn

Informations de copyright

Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.

Déclaration de conflit d'intérêts

Funding Support and Author Disclosures This work was financed by a research grant from Pfizer France. Its initiative, conception and realization were independent. The authors have reported that they have no relationships relevant to the contents of this paper to disclose.

Auteurs

Marc-Antoine Delbarre (MA)

Department of Internal Medicine, Amiens University Hospital, Amiens, France; Research Unit 7517, Mécanisme physiopathologiques et conséquences des calcifications cardiovasculaires (MP3CV), Jules Verne Picardie University, Amiens, France. Electronic address: https://twitter.com/ma_delbarre.

François Girardon (F)

Department of Research and Development, Codoc SAS, Paris, France.

Lucien Roquette (L)

Department of Research and Development, Codoc SAS, Paris, France.

Paul Blanc-Durand (P)

Department of Nuclear Medicine, Henri Mondor University Hospital, Assistance-Publique Hôpitaux de Paris (APHP), Créteil, France; Institut National de la Santé et de la Recherche Médicale (INSERM), Institut Mondor de la Recherche Biomédicale (IMRB), Team 8, Université Paris Est Créteil (UPEC), Créteil, France; Institut National de Recherhe en Informatique et en automatique, Epione Team, Sophia Antipolis Epione Team, Sophia Antipolis, France.

Marc-Antoine Hubaut (MA)

Department of Nuclear Medicine, Roger Salengro Hospital, Lille University Hospital, Lille, France.

Éric Hachulla (É)

Department of Internal Medicine and Clinical Immunology, Referral Centre for Centre for Rare Systemic Autoimmune Diseases North and North-West of France, Centre Hospitalier et Universitaire (University Hospital Center) Lille, Lille, France; University of Lille, Inserm, U1286 Institute for Translational Research in Inflammation, Lille, France.

Franck Semah (F)

Department of Nuclear Medicine, Roger Salengro Hospital, Lille University Hospital, Lille, France.

Damien Huglo (D)

Department of Nuclear Medicine, Claude Huriez Hospital, Lille University Hospital, Lille, France.

Nicolas Garcelon (N)

Department of Research and Development, Codoc SAS, Paris, France.

Etienne Marchal (E)

Nuclear Medicine Department, Amiens University Hospital, Amiens, France.

Isabelle El Esper (I)

Nuclear Medicine Department, Amiens University Hospital, Amiens, France.

Christophe Tribouilloy (C)

Research Unit 7517, Mécanisme physiopathologiques et conséquences des calcifications cardiovasculaires (MP3CV), Jules Verne Picardie University, Amiens, France; Department of Cardiology, Amiens University Hospital, Amiens, France.

Nicolas Lamblin (N)

Department of Cardiology, Cœur-Poumons Institut, Lille University Hospital, Lille, France; Inserm UMR1167, Institut Pasteur of Lille, Lille, France.

Pierre Duhaut (P)

Department of Internal Medicine, Amiens University Hospital, Amiens, France; Research Unit 7517, Mécanisme physiopathologiques et conséquences des calcifications cardiovasculaires (MP3CV), Jules Verne Picardie University, Amiens, France.

Jean Schmidt (J)

Department of Internal Medicine, Amiens University Hospital, Amiens, France; Research Unit 7517, Mécanisme physiopathologiques et conséquences des calcifications cardiovasculaires (MP3CV), Jules Verne Picardie University, Amiens, France.

Emmanuel Itti (E)

Department of Nuclear Medicine, Henri Mondor University Hospital, Assistance-Publique Hôpitaux de Paris (APHP), Créteil, France.

Thibaud Damy (T)

Department of Cardiology, French Referral Center for Cardiac Amyloidosis, Henri Mondor University Hospital, Assistance-Publique Hôpitaux de Paris (APHP), Créteil, France; InsermUnit U955, Clinical Epidemiology and Ageing, Paris-Est Créteil University, Val-de-Marne, Créteil, France. Electronic address: https://twitter.com/ThibaudDamy.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH