An official website of the United States government
Precision in segmenting cardiac MR images is critical for accurately diagnosing cardiovascular diseases. Several deep learning models have been shown useful in segmenting the structure of the heart, such as atrium, ventricle and myocardium, in cardiac MR images. Given the diverse image quality in cardiac MRI scans from various clinical settings, it is currently uncertain how different levels of noise affect the precision of deep learning image segmentation. This uncertainty could potentially lead to bias in subsequent diagnoses. The goal of this study is to examine the effects of noise in cardiac MRI segmentation using deep learning. We employed the Automated Cardiac Diagnosis Challenge MRI dataset and augmented it with varying degrees of Rician noise during model training to test the model’s capability in segmenting heart structures. Three models, including TransUnet, SwinUnet, and Unet, were compared by calculating the SNR-Dice relations to evaluate the models’ noise resilience. Results show that the TransUnet model, which combines CNN and Transformer architectures, demonstrated superior noise resilience. Noise augmentation during model training improved the models’ noise resilience for segmentation. The findings under-score the critical role of deep learning models in adequately handling diverse noise conditions for the segmentation of heart structures in cardiac images.
more »
« less
Automatic Segmentation and Cardiac Mechanics Analysis of Evolving Zebrafish Using Deep Learning
Background: In the study of early cardiac development, it is essential to acquire accurate volume changes of the heart chambers. Although advanced imaging techniques, such as light-sheet fluorescent microscopy (LSFM), provide an accurate procedure for analyzing the heart structure, rapid, and robust segmentation is required to reduce laborious time and accurately quantify developmental cardiac mechanics. Methods: The traditional biomedical analysis involving segmentation of the intracardiac volume occurs manually, presenting bottlenecks due to enormous data volume at high axial resolution. Our advanced deep-learning techniques provide a robust method to segment the volume within a few minutes. Our U-net-based segmentation adopted manually segmented intracardiac volume changes as training data and automatically produced the other LSFM zebrafish cardiac motion images. Results: Three cardiac cycles from 2 to 5 days postfertilization (dpf) were successfully segmented by our U-net-based network providing volume changes over time. In addition to understanding each of the two chambers' cardiac function, the ventricle and atrium were separated by 3D erode morphology methods. Therefore, cardiac mechanical properties were measured rapidly and demonstrated incremental volume changes of both chambers separately. Interestingly, stroke volume (SV) remains similar in the atrium while that of the ventricle increases SV gradually. Conclusion: Our U-net-based segmentation provides a delicate method to segment the intricate inner volume of the zebrafish heart during development, thus providing an accurate, robust, and efficient algorithm to accelerate cardiac research by bypassing the labor-intensive task as well as improving the consistency in the results.
more »
« less
- Award ID(s):
- 1936519
- PAR ID:
- 10277274
- Date Published:
- Journal Name:
- Frontiers in Cardiovascular Medicine
- Volume:
- 8
- ISSN:
- 2297-055X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Bernard, Olivier; Clarysse, Patrick; Duchateau, Nicolas; Ohayon, Jacques; Viallon, Magalie. (Ed.)In this work we present a machine learning model to segment long axis magnetic resonance images of the left ventricle (LV) and address the challenges encountered when, in doing so, a small training dataset is used. Our approach is based on a heart locator and an anatomically guided UNet model in which the UNet is followed by a B-Spline head to condition training. The model is developed using transfer learning, which enabled the training and testing of the proposed strategy from a small swine dataset. The segmented LV cavity and myocardium in the long axis view show good agreement with ground truth segmentations at different cardiac phases based on the Dice similarity coefficient. In addition the model provides a measure of segmentations' uncertainty, which can then be incorporated while developing LV computational models and indices of cardiac performance based on the segmented images. Finally, several challenges related to long axis, as opposed to short axis, image segmentation are highlighted, including proposed solutions.more » « less
-
The COVID-19 pandemic has intensified the need for home-based cardiac health monitoring systems. Despite advancements in electrocardiograph (ECG) and phonocardiogram (PCG) wearable sensors, accurate heart sound segmentation algorithms remain understudied. Existing deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), struggle to segment noisy signals using only PCG data. We propose a two-step heart sound segmentation algorithm that analyzes synchronized ECG and PCG signals. The first step involves heartbeat detection using a CNN-LSTM-based model on ECG data, and the second step focuses on beat-wise heart sound segmentation with a 1D U-Net that incorporates multi-modal inputs. Our method leverages temporal correlation between ECG and PCG signals to enhance segmentation performance. To tackle the label-hungry issue in AI-supported biomedical studies, we introduce a segment-wise contrastive learning technique for signal segmentation, overcoming the limitations of traditional contrastive learning methods designed for classification tasks. We evaluated our two-step algorithm using the PhysioNet 2016 dataset and a private dataset from Bayland Scientific, obtaining a 96.43 F1 score on the former. Notably, our segment-wise contrastive learning technique demonstrated effective performance with limited labeled data. When trained on just 1% of labeled PhysioNet data, the model pre-trained on the full unlabeled dataset only dropped 2.88 in the F1 score, outperforming the SimCLR method. Overall, our proposed algorithm and learning technique present promise for improving heart sound segmentation and reducing the need for labeled data.more » « less
-
The complex motion of the beating heart is accomplished by the spatial arrangement of contracting cardiomyocytes with varying orientation across the transmural layers, which is difficult to imitate in organic or synthetic models. High-fidelity testing of intracardiac devices requires anthropomorphic, dynamic cardiac models that represent this complex motion while maintaining the intricate anatomical structures inside the heart. In this work, we introduce a biorobotic hybrid heart that preserves organic intracardiac structures and mimics cardiac motion by replicating the cardiac myofiber architecture of the left ventricle. The heart model is composed of organic endocardial tissue from a preserved explanted heart with intact intracardiac structures and an active synthetic myocardium that drives the motion of the heart. Inspired by the helical ventricular myocardial band theory, we used diffusion tensor magnetic resonance imaging and tractography of an unraveled organic myocardial band to guide the design of individual soft robotic actuators in a synthetic myocardial band. The active soft tissue mimic was adhered to the organic endocardial tissue in a helical fashion using a custom-designed adhesive to form a flexible, conformable, and watertight organosynthetic interface. The resulting biorobotic hybrid heart simulates the contractile motion of the native heart, compared with in vivo and in silico heart models. In summary, we demonstrate a unique approach fabricating a biomimetic heart model with faithful representation of cardiac motion and endocardial tissue anatomy. These innovations represent important advances toward the unmet need for a high-fidelity in vitro cardiac simulator for preclinical testing of intracardiac devices.more » « less
-
Cardiac Cine Magnetic Resonance (CMR) Imaging has made a significant paradigm shift in medical imaging technology, thanks to its capability of acquiring high spatial and temporal resolution images of different structures within the heart that can be used for reconstructing patient-specific ventricular computational models. In this work, we describe the development of dynamic patient-specific right ventricle (RV) models associated with normal subjects and abnormal RV patients to be subsequently used to assess RV function based on motion and kinematic analysis. We first constructed static RV models using segmentation masks of cardiac chambers generated from our accurate, memory-efficient deep neural architecture - CondenseUNet - featuring both a learned group structure and a regularized weight-pruner to estimate the motion of the right ventricle. In our study, we use a deep learning-based deformable network that takes 3D input volumes and outputs a motion field which is then used to generate isosurface meshes of the cardiac geometry at all cardiac frames by propagating the end-diastole (ED) isosurface mesh using the reconstructed motion field. The proposed model was trained and tested on the Automated Cardiac Diagnosis Challenge (ACDC) dataset featuring 150 cine cardiac MRI patient datasets. The isosurface meshes generated using the proposed pipeline were compared to those obtained using motion propagation via traditional non-rigid registration based on several performance metrics, including Dice score and mean absolute distance (MAD).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/fcvm.2021.675291
