Your browser doesn't support javascript.
loading
Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients.
Xue, Hui; Tseng, Ethan; Knott, Kristopher D; Kotecha, Tushar; Brown, Louise; Plein, Sven; Fontana, Marianna; Moon, James C; Kellman, Peter.
Afiliação
  • Xue H; National Heart, Lung and Blood Institute, National Institutes of Health, Bethesda, Maryland, USA.
  • Tseng E; National Heart, Lung and Blood Institute, National Institutes of Health, Bethesda, Maryland, USA.
  • Knott KD; Barts Heart Centre, London, UK.
  • Kotecha T; National Amyloidosis Centre, Royal Free Hospital, London, UK.
  • Brown L; Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK.
  • Plein S; Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK.
  • Fontana M; National Amyloidosis Centre, Royal Free Hospital, London, UK.
  • Moon JC; Barts Heart Centre, London, UK.
  • Kellman P; National Heart, Lung and Blood Institute, National Institutes of Health, Bethesda, Maryland, USA.
Magn Reson Med ; 84(5): 2788-2800, 2020 11.
Article em En | MEDLINE | ID: mdl-32378776
ABSTRACT

PURPOSE:

Quantification of myocardial perfusion has the potential to improve the detection of regional and global flow reduction. Significant effort has been made to automate the workflow, where one essential step is the arterial input function (AIF) extraction. Failure to accurately identify the left ventricle (LV) prevents AIF estimation required for quantification, therefore high detection accuracy is required. This study presents a robust LV detection method using the convolutional neural network (CNN).

METHODS:

CNN models were trained by assembling 25,027 scans (N = 12,984 patients) from three hospitals, seven scanners. Performance was evaluated using a hold-out test set of 5721 scans (N = 2805 patients). Model inputs were a time series of AIF images (2D+T). Two variations were investigated (1) two classes (2CS) for background and foreground (LV mask), and (2) three classes (3CS) for background, LV, and RV. The final model was deployed on MRI scanners using the Gadgetron reconstruction software framework.

RESULTS:

Model loading on the MRI scanner took ~340 ms and applying the model took ~180 ms. The 3CS model successfully detected the LV in 99.98% of all test cases (1 failure out of 5721). The mean Dice ratio for 3CS was 0.87 ± 0.08 with 92.0% of all cases having Dice >0.75. The 2CS model gave a lower Dice ratio of 0.82 ± 0.22 (P < 1e-5). There was no significant difference in foot-time, peak-time, first-pass duration, peak value, and area-under-curve (P > .2) comparing automatically extracted AIF signals with signals from manually drawn contours.

CONCLUSIONS:

A CNN-based solution to detect the LV blood pool from the arterial input function image series was developed, validated, and deployed. A high LV detection accuracy of 99.98% was achieved.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Aprendizado Profundo / Ventrículos do Coração Tipo de estudo: Diagnostic_studies Limite: Humans Idioma: En Revista: Magn Reson Med Assunto da revista: DIAGNOSTICO POR IMAGEM Ano de publicação: 2020 Tipo de documento: Article País de afiliação: Estados Unidos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Aprendizado Profundo / Ventrículos do Coração Tipo de estudo: Diagnostic_studies Limite: Humans Idioma: En Revista: Magn Reson Med Assunto da revista: DIAGNOSTICO POR IMAGEM Ano de publicação: 2020 Tipo de documento: Article País de afiliação: Estados Unidos