Médecine

Paramédical

Autres domaines


Suscribirse

Dense, deep learning-based intracranial aneurysm detection on TOF MRI using two-stage regularized U-Net - 26/03/22

Doi : 10.1016/j.neurad.2022.03.005 
Frédéric Claux a, 1 , Maxime Baudouin b, 1, , Clément Bogey b, Aymeric Rouchaud a, b
a Univ. Limoges, CNRS, XLIM, UMR 7252, F-87000 Limoges, France 
b Limoges university hospital, Department of radiology, Limoges, France 

Corresponding author at: Limoges university hospital, Department of radiology, Limoges, France.Limoges university hospitalDepartment of radiologyLimogesFrance
En prensa. Pruebas corregidas por el autor. Disponible en línea desde el Saturday 26 March 2022

Abstract

Background and purpose

The prevalence of unruptured intracranial aneurysms in the general population is high and aneurysms are usually asymptomatic. Their diagnosis is often fortuitous on MRI and might be difficult and time consuming for the radiologist. The purpose of this study was to develop a deep learning neural network tool for automated segmentation of intracranial arteries and automated detection of intracranial aneurysms from 3D time-of-flight magnetic resonance angiography (TOF-MRA).

Materials and methods

3D TOF-MRA with aneurysms were retrospectively extracted. All were confirmed with angiography. The data were divided into two sets: a training set of 24 examinations and a test set of 25 examinations. Manual annotations of intracranial blood vessels and aneurysms were performed by neuroradiologists. A double convolutional neuronal network based on the U-Net architecture with regularization was used to increase performance despite a small amount of training data. The performance was evaluated for the test set. Subgroup analyses according to size and location of aneurysms were performed.

Results

The average processing time was 15 min. Overall, the sensitivity and the positive predictive value of the proposed algorithm were 78% (21 of 27; 95% CI: 62–94) and 62% (21 of 34; 95%CI: 46–78) respectively, with 0.5 FP/case. Despite gradual improvement in sensitivity regarding aneurysm size, there was no significant difference of sensitivity detection between subgroups of size and location.

Conclusions

This developed tool based on a double CNN with regularization trained with small dataset, enables accurate intracranial arteries segmentation as well as effective aneurysm detection on 3D TOF MRA.

El texto completo de este artículo está disponible en PDF.

Graphical abstract




Image, graphical abstract

El texto completo de este artículo está disponible en PDF.

Highlights

The prevalence of unruptured intracranial aneurysms in the general population is 3.2%.
Deep convolutional neural networks have improved the development of automatic diagnostic tools.
An innovative method using a cascaded neuronal network (segmentation then detection).
Developed tool will be available for download free of charge at the following URL: aneudetect.

El texto completo de este artículo está disponible en PDF.

Keywords : Cerebral aneurysm, Artificial intelligence, Deep learning, Magnetic resonance angiography

Abbreviations : TOF, FP, CNN, ICA, MCA, ACA, PICA, BT, PCA


Esquema


© 2022  Elsevier Masson SAS. Reservados todos los derechos.
Añadir a mi biblioteca Eliminar de mi biblioteca Imprimir
Exportación

    Exportación citas

  • Fichero

  • Contenido

Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
El acceso al texto completo de este artículo requiere una suscripción.

¿Ya suscrito a @@106933@@ revista ?

Mi cuenta


Declaración CNIL

EM-CONSULTE.COM se declara a la CNIL, la declaración N º 1286925.

En virtud de la Ley N º 78-17 del 6 de enero de 1978, relativa a las computadoras, archivos y libertades, usted tiene el derecho de oposición (art.26 de la ley), el acceso (art.34 a 38 Ley), y correcta (artículo 36 de la ley) los datos que le conciernen. Por lo tanto, usted puede pedir que se corrija, complementado, clarificado, actualizado o suprimido información sobre usted que son inexactos, incompletos, engañosos, obsoletos o cuya recogida o de conservación o uso está prohibido.
La información personal sobre los visitantes de nuestro sitio, incluyendo su identidad, son confidenciales.
El jefe del sitio en el honor se compromete a respetar la confidencialidad de los requisitos legales aplicables en Francia y no de revelar dicha información a terceros.