An official website of the United States government
Heart disease is highly prevalent in developed countries, causing 1 in 4 deaths. In this work we propose a method for a fully automated 4D reconstruction of the left ventricle of the heart. This can provide accurate information regarding the heart wall motion and in particular the hemodynamics of the ventricles. Such metrics are crucial for detecting heart function anomalies that can be an indication of heart disease. Our approach is fast, modular and extensible. In our testing, we found that generating the 4D reconstruction from a set of 250 MRI images takes less than a minute. The amount of time saved as a result of our work could greatly benefit physicians and cardiologist as they diagnose and treat patients.
more »
« less
Automated Segmentation and 4-D reconstruction of the Heart Left Ventricle from CINE MRI
Heart disease is highly prevalent in developed countries, causing 1 in 4 deaths. In this work we propose a method for a fully automated 4D reconstruction of the left ventricle of the heart. This can provide accurate information regarding the heart wall motion and in particular the hemodynamics of the ventricles. Such metrics are crucial for detecting heart function anomalies that can be an indication of heart disease. Our approach is fast, modular and extensible. In our testing, we found that generating the 4D reconstruction from a set of 250 MRI images takes less than a minute. The amount of time saved as a result of our work could greatly benefit physicians and cardiologist as they diagnose and treat patients. Index Terms—Magnetic Resonance Imaging, segmentation, reconstruction, cardiac, machine learning, ventricle
more »
« less
- Award ID(s):
- 1646566
- PAR ID:
- 10130216
- Date Published:
- Journal Name:
- IEEE International Conference on Bioinformatics and Bioengineering (BIBE)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Hypertrophic cardiomyopathy (HCM) is a congenital heart disease characterized by thickening of the heart’s left ventricle (LV) wall that can lead to cardiac dysfunction and heart failure. Ventricular wall thickening affects the motion of cardiac walls and blood flow within the heart. Because abnormal cardiac blood flow in turn could lead to detrimental remodeling of heart walls, aberrant ventricular flow patterns could exacerbate HCM progression. How blood flow patterns are affected by hypertrophy and inter-patient variability is not known. To address this gap in knowledge, we present here strategies to generate personalized computational fluid dynamics (CFD) models of the heart LV from patient cardiac magnetic resonance (cMR) images. We performed simulations of CFD LV models from three cases (one normal, two HCM). CFD computations solved for blood flow velocities, from which flow patterns and the energetics of flow within the LV were quantified. We found that, compared to a normal heart, HCM hearts exhibit anomalous flow patterns and a mismatch in the timing of energy transfer from the LV wall to blood flow, as well as changes in kinetic energy flow patterns. While our results are preliminary, our presented methodology holds promise for in-depth analysis of HCM patient hemodynamics in clinical practice.more » « less
-
Abstract AimCardiac fibrosis contributes to systolic and diastolic dysfunction and can disrupt electrical pathways in the heart. There are currently no therapies that prevent or reverse fibrosis in human cardiac disease. However, animals like freshwater turtles undergo seasonal remodeling of their hearts, demonstrating the plasticity of fibrotic remodeling. InTrachemys scripta, cold temperature affects cardiac load, suppresses metabolism, and triggers a cardiac remodeling response that includes fibrosis. MethodsWe investigated this remodeling using Fourier transform infrared (FTIR) imaging spectroscopy, together with functional assessment of muscle stiffness, and molecular, histological, and enzymatic analyses in control (25°C)T. scriptaand after 8 weeks of cold (5°C) acclimation. ResultsFTIR revealed an increase in absorption bands characteristic of protein, glycogen, and collagen following cold acclimation, with a corresponding decrease in bands characteristic of lipids and phosphates. Histology confirmed these responses. Functionally, micromechanical stiffness of the ventricle increased following cold exposure assessed via atomic force microscopy (AFM) and was associated with decreased activity of regulatory matrix metalloproteinases (MMPs) and increased expression of MMP inhibitors (TMPs) which regulate collagen deposition. ConclusionsBy defining the structural and metabolic underpinnings of the cold‐induced remodeling response in the turtle heart, we show commonalities between metabolic and fibrotic triggers of pathological remodeling in human cardiac disease. We propose the turtle ventricle as a novel model for studying the mechanisms underlying fibrotic and metabolic cardiac remodeling.more » « less
-
This paper introduces a deep neural network based method, i.e., DeepOrganNet, to generate and visualize fully high-fidelity 3D / 4D organ geometric models from single-view medical images with complicated background in real time. Traditional 3D / 4D medical image reconstruction requires near hundreds of projections, which cost insufferable computational time and deliver undesirable high imaging / radiation dose to human subjects. Moreover, it always needs further notorious processes to segment or extract the accurate 3D organ models subsequently. The computational time and imaging dose can be reduced by decreasing the number of projections, but the reconstructed image quality is degraded accordingly. To our knowledge, there is no method directly and explicitly reconstructing multiple 3D organ meshes from a single 2D medical grayscale image on the fly. Given single-view 2D medical images, e.g., 3D / 4D-CT projections or X-ray images, our end-to-end DeepOrganNet framework can efficiently and effectively reconstruct 3D / 4D lung models with a variety of geometric shapes by learning the smooth deformation fields from multiple templates based on a trivariate tensor-product deformation technique, leveraging an informative latent descriptor extracted from input 2D images. The proposed method can guarantee to generate high-quality and high-fidelity manifold meshes for 3D / 4D lung models; while, all current deep learning based approaches on the shape reconstruction from a single image cannot. The major contributions of this work are to accurately reconstruct the 3D organ shapes from 2D single-view projection, significantly improve the procedure time to allow on-the-fly visualization, and dramatically reduce the imaging dose for human subjects. Experimental results are evaluated and compared with the traditional reconstruction method and the state-of-the-art in deep learning, by using extensive 3D and 4D examples, including both synthetic phantom and real patient datasets. The efficiency of the proposed method shows that it only needs several milliseconds to generate organ meshes with 10K vertices, which has great potential to be used in real-time image guided radiation therapy (IGRT).more » « less
-
BackgroundCongenital heart defects affect approximately 1% of births in the United States and Europe, with >1 million children in the United States living with congenital heart defects. Many experience abnormalities in the right ventricular outflow tract, often necessitating surgical intervention early in life. However, the initial repairs typically are temporary solutions as many patients will eventually need pulmonary valve replacement to address pulmonary valve regurgitation and prevent right ventricle failure. Addressing progressive pulmonary valve regurgitation, ideally in patients weighing 8 to 10 kg, is critical to prevent right ventricle dysfunction. Transcatheter pulmonary valve replacement currently treats patients weighing at least 20 kg. Unfortunately, smaller children must wait for valve replacement and risk right ventricular dilation. MethodsTo address this challenge, we have developed the IRIS Valve, a growth‐accommodating transcatheter pulmonary heart valve inspired by origami targeting implantation in at least 8 kg children. The valve stent underwent finite element analysis with validation by fracture testing. Using a 12‐Fr transcatheter system, the IRIS valve was implanted into 8 to 17 kg Yucatan mini pigs for 6 months. ResultsBenchtop fracture testing and finite element analysis confirmed the stent's ability to be crimped to a 3‐mm diameter for loading into a 12‐Fr transcatheter system and expanded to 20 mm without fracture. Animal studies successfully demonstrated excellent integration within the pulmonary valve annulus, intact valve integrity, and favorable tissue response. ConclusionsThe IRIS Valve offers a promising solution for earlier treatment of heart valve disease in pediatric patients with congenital heart defects, potentially improving outcomes in this vulnerable population.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
