A Framework for the Generation of Realistic Synthetic Cardiac Ultrasound and Magnetic Resonance Imaging Sequences From the Same Virtual Patients

Abstract

The use of synthetic sequences is one of the most promising tools for advanced in silico evaluation of the quantification of cardiac deformation and strain through 3-D ultrasound (US) and magnetic resonance (MR) imaging. In this paper, we propose the first simulation framework which allows the generation of realistic 3-D synthetic cardiac US and MR (both cine and tagging) image sequences from the same virtual patient. A state-of-the-art electromechanical (E/M) model was exploited for simulating groundtruth cardiac motion fields ranging from healthy to various pathological cases, including both ventricular dyssynchrony and myocardial ischemia. The E/M groundtruth along with template MR/US images and physical simulators were combined in a unified framework for generating synthetic data. We efficiently merged several warping strategies to keep the full control of myocardial deformations while preserving realistic image texture. In total, we generated 18 virtual patients, each with synthetic 3-D US, cine MR, and tagged MR sequences. The simulated images were evaluated both qualitatively by showing realistic textures and quantitatively by observing myocardial intensity distributions similar to real data. In particular, the US simulation showed a smoother myocardium/background interface than the state-of-the-art. We also assessed the mechanical properties. The pathological subjects were discriminated from the healthy ones by both global indexes (ejection fraction and the global circumferential strain) and regional strain curves. The synthetic database is comprehensive in terms of both pathology and modality, and has a level of realism sufficient for validation purposes. All the 90 sequences are made publicly available to the research community via an open-access database.

Kinematic boundary conditions substantially impact in silico ventricular function

“…First, suboptimal long‐axis TMRI data and the lower tag density in the radial direction led to a large variation in measured systolic strains in both longitudinal and radial directions (also seen in previous studies) due to which only the in vivo circumferential strains could be used for validation purposes. Second, the used acquisition and estimation motion and deformation tracking method do not account for out‐of‐plane motion which could lead to discrepancies with the FEA computed systolic strains, similar to Sun et al and Gao et al To study the effect of out‐of‐plane motion on the strain results, which is considered beyond the scope of this study, synthetic MR imaging sequences should be built from a finite element electromechanical ground‐truth model (eg, Zhou et al) and subsequently processed with the used motion tracking algorithm to study its performance. Future work should focus on collecting higher quality image data and inclusion of appropriate tracking algorithms, so we could assess right ventricular deformation as well).…”

Arterial Spin Labeling Image Synthesis From Structural MRI Using Improved Capsule-Based Networks

“…Although large-scale medical image datasets acquired by actual scanning are challenging to be constructed, medical images of high-quality can be synthesized, alternatively [11]- [12]. Recent studies have demonstrated that, diverse medical image modalities, including MRI images [13]- [19], PET images [20]- [22], CT / X-Ray images [23]- [25], ultrasound images [26], mammography images [27]- [28], eye (including retinal, fundus, and glaucoma) images [29]- [32], endoscopic images [33], can be successfully synthesized. Generally, machine learning techniques are widely acknowledged to provide a profound impact on medical image synthesis, and the synthesis task itself can be considered as finding a good mapping from the source image to the target image [34].…”

Faculty Opinions recommendation of Myocardial strain imaging: review of general principles, validation, and sources of discrepancies.

“…Currently, open-access libraries of 2D and 3D simulated ultrasound datasets, as well as simulated cine cMR, are being built to facilitate performance analysis of different software packages in order to promote quality assurance. [48][49][50] The tested strain imaging methods have shown promising results, and efforts have been made to reach the level of realism of the real ultrasound and cMR images.…”