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

Philip A Corrado; Daniel P Seiter; Oliver Wieben

doi:10.1007/s11548-021-02475-1

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

Int J Comput Assist Radiol Surg. 2022 Jan;17(1):199-210. doi: 10.1007/s11548-021-02475-1. Epub 2021 Aug 17.

Authors

Philip A Corrado¹, Daniel P Seiter², Oliver Wieben³

Affiliations

¹ Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA. pcorrado2@wisc.edu.
² Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA.
³ Departments of Medical Physics and Radiology, University of Wisconsin-Madison, Madison, WI, USA.

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.

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

MeSH terms

Algorithms
Deep Learning*
Humans
Imaging, Three-Dimensional
Magnetic Resonance Imaging
Neural Networks, Computer
Reproducibility of Results

Abstract

MeSH terms

Grants and funding