Fully automatic geometry planning for cardiac MR imaging and reproducibility of functional cardiac parameters

Abstract

Purpose: To establish operator-independent, fully automated planning of standard cardiac geometries and to determine the impact on interstudy reproducibility of cardiac functional parameters.Materials and Methods: Cardiac MR imaging was done in 50 patients referred for left-ventricular function assessment. In all patients, first standard manual planning was performed followed by automatic planning (AUTO1) and repeat automatic planning (AUTO2) after repositioning the patient to investigate interstudy reproducibility. Cardiac functional parameters were assessed and cine scans were visually graded on a 4-point scale from nondiagnostic to excellent.Results: Overall success rate of AUTO was 94% with good to excellent geometry planning in >94% of cine standard views. Comparing manual versus fully automated planning, a high agreement of cardiac functional parameters (Lin's concordance correlation coefficient, 0.91 to 0.99) with minimal percent bias (0.24 to 3.84%) was found. In addition, a high interstudy reproducibility of automatic planning was demonstrated (Lin's concordance correlation coefficient, 0.89 to 0.99; percent bias, 0.38 to 5.04%; precision, 3.46 to 9.09%). Conclusion:Fully automated planning of cardiac geometries could reliably be performed in patients showing a variety of cardiovascular pathologies. Standard cardiac geometries were precisely replicated and functional parameters were highly accurate.

Deep Learning–based Prescription of Cardiac MRI Planes

“…We also compared our method against recently described strategies by Frick et al (8) and Lu et al (9), and the results are in Table 2. Although our studies do not share common reference datasets, we found statistically improved SAX and four-chamber ages, this was readily accomplished with a single two-dimensional U-Net modified for in-plane heatmap regression.…”

“…However, the authors did not identify the essential four-chamber, three-chamber, and twochamber LAX imaging planes that are necessary for the assessment of wall motion and valve function (24,25). More recently, other studies have used mesh segmentation−based approaches to plan sequences of view planes from a single three-dimensional cardiac MRI acquisition (8,9). Although promising, these approaches were developed by using a more limited test population with the use of an additional acquisition that is not typically used in many cardiac MRI workflows.…”

“…This method was developed and tested in 50 healthy patients but was not validated in a clinical population that may have had greater variation in anatomic structure. Another approach used a mesh-based segmentation model based on canonical geometry or an anatomic atlas (8,9). However, these approaches used an additional volumetric image not typically acquired at cardiac MRI.…”

Machine learning in cardiovascular magnetic resonance: basic concepts and applications

“…Several of these acquisition-related aspects of the CMR examination, which are currently performed manually on most commercial CMR systems, can be either automated or substantially shortened using ML. Multiple CMR hardware vendors are working on workflow optimizations such fully automated localization of the heart and planning of image acquisition planes aligned with the principal cardiac axes [13, 14]. Other investigators have applied ML to automate optimal frequency adjustment for CMR at 3 T [15], and to create a scan control framework that detects image artifacts during the scan and self-corrects imaging parameters or triggers a rescan if the prediction indicates the current slice has artifacts [16].…”

Artificial Intelligence and Cardiovascular Imaging. A win-win Combination

“…ML can be applied in all steps of the cardiovascular imaging chain (image acquisition, reconstruction, and segmentation, myocardial tissue characterization, diagnosis, and prognosis). The image acquisition workflow may be optimized by automated localization of the heart, planning of image acquisition planes, optimal frequency adjustment, and scan control framework detecting artifacts ( 29 , 30 ). Such features are now available, or under development and implementation by many vendors.…”