Literature DB >> 34403045

Automatic measurement plane placement for 4D Flow MRI of the great vessels using deep learning.

Philip A Corrado1, Daniel P Seiter2, Oliver Wieben3.   

Abstract

PURPOSE: Despite the great potential and flexibility of 4D flow MRI for hemodynamic analysis, a major limitation is the need for time-consuming and user-dependent post-processing. We propose a fast four-step algorithm for rapid, robust, and repeatable flow measurements in the great vessels based on automatic placement of measurement planes and vessel segmentation.
METHODS: Our algorithm works by (1) subsampling the 3D image into 3D patches, (2) predicting the probability of each patch containing individual vessels and location/orientation of the vessel within the patch via a convolutional neural network, (3) selecting the predicted planes with highest probabilities for each vessel, and (4) shifting the plane centers to the maximum velocity within each plane. The method was trained on 283 scans and evaluated on 40 unseen scans by comparing algorithm-derived processing times, plane locations, and flow measurements to those of two manual observers (graduate students) using t-tests, Pearson correlation, and Bland-Altman analysis.
RESULTS: The average processing time for the algorithm (18 s) was shorter than observer 1 (362 s; P < 0.001) and observer 2 (317 s; P < 0.001). The distance between planes placed by the algorithm and those placed by manual observers was slightly greater (O1 vs. algorithm: 9.0 mm, O2 vs. algorithm: 10.3 mm) than the distance between planes placed by the two manual observers (8.3 mm). The correlation between flow values for planes placed by the algorithm and those placed by manual observers was slightly lower (O1 vs. algorithm: R = 0.68, O2 vs. algorithm: R = 0.72) than the flow correlation between the two manual observers (R = 0.81).
CONCLUSION: Our method is a feasible and accurate approach for fast, reproducible, and automated flow measurement and visualization in 4D flow MRI of the great vessels, with similar variability compared to a manual annotator as the variability between two manual observers. This approach could be applied in other anatomical regions.
© 2021. CARS.

Entities:  

Keywords:  CNN; Deep learning; Flow; Landmark; Localization; MRI; ResNet

Mesh:

Year:  2021        PMID: 34403045      PMCID: PMC8851604          DOI: 10.1007/s11548-021-02475-1

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  21 in total

1.  Fully automated 3D aortic segmentation of 4D flow MRI for hemodynamic analysis using deep learning.

Authors:  Haben Berhane; Michael Scott; Mohammed Elbaz; Kelly Jarvis; Patrick McCarthy; James Carr; Chris Malaisrie; Ryan Avery; Alex J Barker; Joshua D Robinson; Cynthia K Rigsby; Michael Markl
Journal:  Magn Reson Med       Date:  2020-03-13       Impact factor: 4.668

2.  Automated segmentation of blood-flow regions in large thoracic arteries using 3D-cine PC-MRI measurements.

Authors:  Roy van Pelt; Huy Nguyen; Bart ter Haar Romeny; Anna Vilanova
Journal:  Int J Comput Assist Radiol Surg       Date:  2011-07-21       Impact factor: 2.924

3.  Automated multi-atlas segmentation of cardiac 4D flow MRI.

Authors:  Mariana Bustamante; Vikas Gupta; Daniel Forsberg; Carl-Johan Carlhäll; Jan Engvall; Tino Ebbers
Journal:  Med Image Anal       Date:  2018-08-13       Impact factor: 8.545

Review 4.  Comprehensive 4D velocity mapping of the heart and great vessels by cardiovascular magnetic resonance.

Authors:  Michael Markl; Philip J Kilner; Tino Ebbers
Journal:  J Cardiovasc Magn Reson       Date:  2011-01-14       Impact factor: 5.364

5.  Clinical evaluation of aortic coarctation with 4D flow MR imaging.

Authors:  Michael D Hope; Alison K Meadows; Thomas A Hope; Karen G Ordovas; David Saloner; Gautham P Reddy; Marcus T Alley; Charles B Higgins
Journal:  J Magn Reson Imaging       Date:  2010-03       Impact factor: 4.813

6.  Longitudinal Monitoring of Hepatic Blood Flow before and after TIPS by Using 4D-Flow MR Imaging.

Authors:  Peter Bannas; Alejandro Roldán-Alzate; Kevin M Johnson; Michael A Woods; Orhan Ozkan; Utaroh Motosugi; Oliver Wieben; Scott B Reeder; Harald Kramer
Journal:  Radiology       Date:  2016-05-12       Impact factor: 11.105

7.  Quantification of thoracic blood flow using volumetric magnetic resonance imaging with radial velocity encoding: in vivo validation.

Authors:  Alex Frydrychowicz; Oliver Wieben; Eric Niespodzany; Scott B Reeder; Kevin M Johnson; Christopher J François
Journal:  Invest Radiol       Date:  2013-12       Impact factor: 6.016

8.  Evaluating reinforcement learning agents for anatomical landmark detection.

Authors:  Amir Alansary; Ozan Oktay; Yuanwei Li; Loic Le Folgoc; Benjamin Hou; Ghislain Vaillant; Konstantinos Kamnitsas; Athanasios Vlontzos; Ben Glocker; Bernhard Kainz; Daniel Rueckert
Journal:  Med Image Anal       Date:  2019-02-14       Impact factor: 8.545

9.  Venous and arterial flow quantification are equally accurate and precise with parallel imaging compressed sensing 4D phase contrast MRI.

Authors:  Umar Tariq; Albert Hsiao; Marcus Alley; Tao Zhang; Michael Lustig; Shreyas S Vasanawala
Journal:  J Magn Reson Imaging       Date:  2012-11-21       Impact factor: 4.813

10.  Interactive virtual probing of 4D MRI blood-flow.

Authors:  Roy van Pelt; Javier Oliván Bescós; Marcel Breeuwer; Rachel E Clough; M Eduard Gröller; Bart ter Haar Romenij; Anna Vilanova
Journal:  IEEE Trans Vis Comput Graph       Date:  2011-12       Impact factor: 4.579

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.