Functional imaging and modeling of the heart : ... International Workshop, FIMH ..., proceedings. FIMH最新文献

4D cardiac imaging offers impactful insights into structural heart dynamics. However, analyzing 4D data using conventional 3D software tools requires additional effort. This paper introduces three natively 4D-optimized software applications we have developed: ITK-SNAP 4 for 4D image I/O, visualization, and segmentation; Greedy Propagation for intra-series registration and creation of 4D segmentation from sparse 3D segmentations; and Scherzo for fast web-based 4D model generation and visualization. These open-source tools provide a streamlined user experience, comprehensive features, and broad file type support including common 4D cardiac image formats. Experiments on core features demonstrate feasibility and consistency.

Segmentation of the left atrium (LA) is crucial for characterizing and appraising left atrial anatomy, morphology, and function in the context of a series of diseases, the most prevalent one being atrial fibrillation (AFib). Despite significant advances in deep learning-based segmentation models, their dependency on large annotated datasets for training limits their effectiveness in niche applications such as atrium segmentation, where annotated data is scarce. Pre-trained foundation models, trained on large-scale general-purpose datasets in a self-supervised manner, can offer an advantage by providing transferable features and enabling adoption to data-scarce domains. In this work, we explore the domain adaptability and robustness of some pre-trained foundation models, such as DINOv2, SAM, and MedSAM, as powerful alternatives for LA segmentation from MRI images. We integrated a modified UNet decoder that leverages the global contextual features encoded by the foundation models. Our approach is evaluated on the 2022 LAScarQS and 2018 LASC segmentation challenge datasets for end-to-end fine-tuning and lower training data settings, respectively. The performance of the UNet decoder was superior to that of the linear decoder used in the original papers of these foundation models, as well as other UNet baselines. Notably, DINOv2 combined with a UNet decoder consistently outperforms the baselines and improves Dice (91.5%, 91.6%) and IoU scores (84.5%, 86.6%), highlighting the model's generalizability and robustness across diverse datasets and limited training data. This study also underscores the transformative potential of foundation models in medical image segmentation, paving the way for more generalized and adaptable solutions across various medical applications.

Myocardial infarction (MI) results in cardiac myocyte death and often initiates the formation of a fibrotic scar in the myocardium surrounded by a border zone. Myocyte loss and collagen-rich scar tissue heavily influence the biomechanical behavior of the myocardium which could lead to various cardiac diseases such as systolic heart failure and arrhythmias. Knowledge of how myocyte and collagen micro-architecture changes affect the passive mechanical behavior of the border zone remains limited. Computational modeling provides us with an invaluable tool to identify and study the mechanisms driving the biomechanical remodeling of the myocardium post-MI. We utilized a rodent model of MI and an image-based approach to characterize the three-dimensional (3-D) myocyte and collagen micro-architecture at various timepoints post-MI. Left ventricular free wall (LVFW) samples were obtained from infarcted hearts at 1-week and 4-week post-MI (n = 1 each). Samples were labeled using immunoassays to identify the extracellular matrix (ECM) and myocytes. 3-D reconstructions of the infarct border zone were developed from confocal imaging and meshed to develop high-fidelity micro-anatomically accurate finite element models. We performed a parametric study using these models to investigate the influence of collagen undulation on the passive micromechanical behavior of the myocardium under a diastolic load. Our results suggest that although parametric increases in collagen undulation elevate the strain amount experienced by the ECM in both early- and late-stage MI, the sensitivity of myocytes to such increases is reduced from early to late-stage MI. Our 3-D micro-anatomical modeling holds promise in identifying mechanisms of border zone maladaptation post-MI.

The myocardium is composed of a complex network of contractile myofibers that are organized in such a way as to produce efficient contraction and relaxation of the heart. The myofiber architecture in the myocardium is a key determinant of cardiac motion and the global or organ-level function of the heart. Reports of architectural remodeling in cardiac diseases, such as pulmonary hypertension and myocardial infarction, potentially contributing to cardiac dysfunction call for the inclusion of an architectural marker for an improved assessment of cardiac function. However, the in-vivo quantification of three-dimensional myo-architecture has proven challenging. In this work, we examine the sensitivity of cardiac strains to varying myofiber orientation using a multiscale finite-element model of the LV. Additionally, we present an inverse modeling approach to predict the myocardium fiber structure from cardiac strains. Our results indicate a strong correlation between fiber orientation and LV kinematics, corroborating that the fiber structure is a principal determinant of LV contractile behavior. Our inverse model was capable of accurately predicting the myocardial fiber range and regional fiber angles from strain measures. A concrete understanding of the link between LV myofiber structure and motion, and the development of non-invasive and feasible means of characterizing the myocardium architecture is expected to lead to advanced LV functional metrics and improved prognostic assessment of structural heart disease.