Scanner-Independent MyoMapNet for Accelerated Cardiac MRI T1 Mapping Across Vendors and Field Strengths

Abstract

Background: In cardiac T₁ mapping, a series of T₁ -weighted (T₁ w) images are collected and numerically fitted to a two or three-parameter model of the signal recovery to estimate voxel-wise T₁ values. To reduce the scan time, one can collect fewer T₁ w images, albeit at the cost of precision or/and accuracy. Recently, the feasibility of using a neural network instead of conventional two- or three-parameter fit modeling has been demonstrated. However, prior studies used data from a single vendor and field strength; therefore, the generalizability of the models has not been established.

Purpose: To develop and evaluate an accelerated cardiac T₁ mapping approach based on MyoMapNet, a convolution neural network T₁ estimator that can be used across different vendors and field strengths by incorporating the relevant scanner information as additional inputs to the model.

Study type: Retrospective, multicenter.

Population: A total of 1423 patients with known or suspected cardiac disease (808 male, 57 ± 16 years), from three centers, two vendors (Siemens, Philips), and two field strengths (1.5 T, 3 T). The data were randomly split into 60% training, 20% validation, and 20% testing.

Field strength/sequence: A 1.5 T and 3 T, Modified Look-Locker inversion recovery (MOLLI) for native and postcontrast T₁ .

Assessment: Scanner-independent MyoMapNet (SI-MyoMapNet) was developed by altering the deep learning (DL) architecture of MyoMapNet to incorporate scanner vendor and field strength as inputs. Epicardial and endocardial contours and blood pool (by manually drawing a large region of interest in the blood pool) of the left ventricle were manually delineated by three readers, with 2, 8, and 9 years of experience, and SI-MyoMapNet myocardial and blood pool T₁ values (calculated from four T₁ w images) were compared with conventional MOLLI T₁ values (calculated from 8 to 11 T₁ w images).

Statistical tests: Equivalency test with 95% confidence interval (CI), linear regression slope, Pearson correlation coefficient (r), Bland-Altman analysis.

Results: The proposed SI-MyoMapNet successfully created T₁ maps. Native and postcontrast T₁ values measured from SI-MyoMapNet were strongly correlated with MOLLI, despite using only four T₁ w images, at both field-strengths and vendors (all r > 0.86). For native T₁ , SI-MyoMapNet and MOLLI were in good agreement for myocardial and blood T₁ values in institution 1 (myocardium: 5 msec, 95% CI [3, 8]; blood: -10 msec, 95%CI [-16, -4]), in institution 2 (myocardium: 6 msec, 95% CI [0, 11]; blood: 0 msec, [-18, 17]), and in institution 3 (myocardium: 7 msec, 95% CI [-8, 22]; blood: 8 msec, [-14, 30]). Similar results were observed for postcontrast T₁ .

Data conclusion: Inclusion of field strength and vendor as additional inputs to the DL architecture allows generalizability of MyoMapNet across different vendors or field strength.

Evidence level: 2.

Technical efficacy: Stage 2.

Keywords: deep learning; inversion-recovery cardiac T1 mapping; myocardial tissue characterization.