Automatic detection of punctate white matter lesions in infants using deep learning of composite images from two cases.
Sci Rep
; 13(1): 4426, 2023 03 17.
Article
em En
| MEDLINE
| ID: mdl-36932141
ABSTRACT
Punctate white matter lesions (PWMLs) in infants may be related to neurodevelopmental outcomes based on the location or number of lesions. This study aimed to assess the automatic detectability of PWMLs in infants on deep learning using composite images created from several cases. To create the initial composite images, magnetic resonance (MR) images of two infants with the most PWMLs were used; their PWMLs were extracted and pasted onto MR images of infants without abnormality, creating many composite PWML images. Deep learning models based on a convolutional neural network, You Only Look Once v3 (YOLOv3), were constructed using the training set of 600, 1200, 2400, and 3600 composite images. As a result, a threshold of detection probability of 20% and 30% for all deep learning model sets yielded a relatively high sensitivity for automatic PWML detection (0.908-0.957). Although relatively high false-positive detections occurred with the lower threshold of detection probability, primarily, in the partial volume of the cerebral cortex (≥ 85.8%), those can be easily distinguished from the white matter lesions. Relatively highly sensitive automatic detection of PWMLs was achieved by creating composite images from two cases using deep learning.
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Substância Branca
/
Aprendizado Profundo
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
Limite:
Humans
/
Infant
Idioma:
En
Ano de publicação:
2023
Tipo de documento:
Article