Recent Advances in Fibrosis and Scar Segmentation From Cardiac MRI: A State-of-the-Art Review and Future Perspectives

Improving the efficiency and accuracy of cardiovascular magnetic resonance with artificial intelligence-review of evidence and proposition of a roadmap to clinical translation

BACKGROUND

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR.

METHODS

Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis.

RESULTS

These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives.

CONCLUSIONS

Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.

Impact of late gadolinium enhancement image acquisition resolution on neural network based automatic scar segmentation

BACKGROUND

Automatic myocardial scar segmentation from late gadolinium enhancement (LGE) images using neural networks promises an alternative to time-consuming and observer-dependent semi-automatic approaches. However, alterations in data acquisition, reconstruction as well as post-processing may compromise network performance. The objective of the present work was to systematically assess network performance degradation due to a mismatch of point-spread function between training and testing data.

METHODS

Thirty-six high-resolution (0.7×0.7×2.0 mm3) LGE k-space datasets were acquired post-mortem in porcine models of myocardial infarction. The in-plane point-spread function and hence in-plane resolution Δx was retrospectively degraded using k-space lowpass filtering, while field-of-view and matrix size were kept constant. Manual segmentation of the left ventricle (LV) and healthy remote myocardium was performed to quantify location and area (% of myocardium) of scar by thresholding (≥ SD5 above remote). Three standard U-Nets were trained on training resolutions Δxtrain = 0.7, 1.2 and 1.7 mm to predict endo- and epicardial borders of LV myocardium and scar. The scar prediction of the three networks for varying test resolutions (Δxtest = 0.7 to 1.7 mm) was compared against the reference SD5 thresholding at 0.7 mm. Finally, a fourth network trained on a combination of resolutions (Δxtrain = 0.7 to 1.7 mm) was tested.

RESULTS

The prediction of relative scar areas showed the highest precision when the resolution of the test data was identical to or close to the resolution used during training. The median fractional scar errors and precisions (IQR) from networks trained and tested on the same resolution were 0.0 percentage points (p.p.) (1.24 - 1.45), and - 0.5 - 0.0 p.p. (2.00 - 3.25) for networks trained and tested on the most differing resolutions, respectively. Deploying the network trained on multiple resolutions resulted in reduced resolution dependency with median scar errors and IQRs of 0.0 p.p. (1.24 - 1.69) for all investigated test resolutions.

CONCLUSION

A mismatch of the imaging point-spread function between training and test data can lead to degradation of scar segmentation when using current U-Net architectures as demonstrated on LGE porcine myocardial infarction data. Training networks on multi-resolution data can alleviate the resolution dependency.

Deep learning for classification of late gadolinium enhancement lesions based on the 16-segment left ventricular model

PURPOSE

This study aimed to develop and validate a deep learning-based method that allows for segmental analysis of myocardial late gadolinium enhancement (LGE) lesions.

METHODS

Cardiac LGE data from 170 patients with coronary artery disease and non-ischemic heart disease were used for training, validation, and testing. Short-axis images were transformed to polar space after identification of the left ventricular (LV) center point and anterior right ventricular (RV) insertion point. Images were obtained after dividing the polar transformed images into segments based on the 16-segment LV model. Five different deep convolutional neural network (CNN) models were developed and validated using the labeled data, where the image after the division corresponded to a segment, and the lesion labeling was based on the 16-segment LV model. Unseen testing data were used to evaluate the performance of the lesion classification.

RESULTS

Without manual lesion segmentation and annotation, the proposed method showed an area under the curve (AUC) of 0.875, and a precision, recall, and F1-score of 0.723, 0.783, and 0.752, respectively for the lesion class when the pretrained ResNet50 model was tested for all slice images. The two pretrained models of ResNet50 and EfficientNet-B0 outperformed the three non-pretrained CNN models in terms of AUCs (0.873-0.875 vs. 0.834-0.841).

CONCLUSION

The proposed method is based on learning a deep CNN model from polar transformed images to predict LGE lesions with good accuracy and does not require time-consuming annotation procedures such as lesion segmentation.

FK-means: automatic atrial fibrosis segmentation using fractal-guided K-means clustering with Voronoi-clipping feature extraction of anatomical structures

Assessment of left atrial (LA) fibrosis from late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) adds to the management of patients with atrial fibrillation. However, accurate assessment of fibrosis in the LA wall remains challenging. Excluding anatomical structures in the LA proximity using clipping techniques can reduce misclassification of LA fibrosis. A novel FK-means approach for combined automatic clipping and automatic fibrosis segmentation was developed. This approach combines a feature-based Voronoi diagram with a hierarchical 3D K-means fractal-based method. The proposed automatic Voronoi clipping method was applied on LGE-MRI data and achieved a Dice score of 0.75, similar to the score obtained by a deep learning method (3D UNet) for clipping (0.74). The automatic fibrosis segmentation method, which uses the Voronoi clipping method, achieved a Dice score of 0.76. This outperformed a 3D UNet method for clipping and fibrosis classification, which had a Dice score of 0.69. Moreover, the proposed automatic fibrosis segmentation method achieved a Dice score of 0.90, using manual clipping of anatomical structures. The findings suggest that the automatic FK-means analysis approach enables reliable LA fibrosis segmentation and that clipping of anatomical structures in the atrial proximity can add to the assessment of atrial fibrosis.

The Nottingham Ischaemic Cardiovascular Magnetic Resonance resource (NotIs CMR): a prospective paired clinical and imaging scar database-protocol

INTRODUCTION

Research utilising artificial intelligence (AI) and cardiovascular magnetic resonance (CMR) is rapidly evolving with various objectives, however AI model development, generalisation and performance may be hindered by availability of robust training datasets including contrast enhanced images.

METHODS

NotIs CMR is a large UK, prospective, multicentre, observational cohort study to guide the development of a biventricular AI scar model. Patients with ischaemic heart disease undergoing clinically indicated contrast-enhanced cardiac magnetic resonance imaging will be recruited at Nottingham University Hospitals NHS Trust and Mid-Yorkshire Hospital NHS Trust. Baseline assessment will include cardiac magnetic resonance imaging, demographic data, medical history, electrocardiographic and serum biomarkers. Participants will undergo monitoring for a minimum of 5 years to document any major cardiovascular adverse events. The main objectives include (1) AI training, validation and testing to improve the performance, applicability and adaptability of an AI biventricular scar segmentation model being developed by the authors and (2) develop a curated, disease-specific imaging database to support future research and collaborations and, (3) to explore associations in clinical outcome for future risk prediction modelling studies.

CONCLUSION

NotIs CMR will collect and curate disease-specific, paired imaging and clinical datasets to develop an AI biventricular scar model whilst providing a database to support future research and collaboration in Artificial Intelligence and ischaemic heart disease.

Quality control-driven deep ensemble for accountable automated segmentation of cardiac magnetic resonance LGE and VNE images

Background

Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterisation. However, accurate segmentation of the left ventricular (LV) myocardium remains a challenge due to limited training data and lack of quality control. This study addresses these issues by leveraging generative adversarial networks (GAN)-generated virtual native enhancement (VNE) images to expand the training set and incorporating an automated quality control-driven (QCD) framework to improve segmentation reliability.

Methods

A dataset comprising 4,716 LGE images (from 1,363 patients with hypertrophic cardiomyopathy and myocardial infarction) was used for development. To generate additional clinically validated data, LGE data were augmented with a GAN-based generator to produce VNE images. LV was contoured on these images manually by clinical observers. To create diverse candidate segmentations, the QCD framework involved multiple U-Nets, which were combined using statistical rank filters. The framework predicted the Dice Similarity Coefficient (DSC) for each candidate segmentation, with the highest predicted DSC indicating the most accurate and reliable result. The performance of the QCD ensemble framework was evaluated on both LGE and VNE test datasets (309 LGE/VNE images from 103 patients), assessing segmentation accuracy (DSC) and quality prediction (mean absolute error (MAE) and binary classification accuracy).

Results

The QCD framework effectively and rapidly segmented the LV myocardium (<1 s per image) on both LGE and VNE images, demonstrating robust performance on both test datasets with similar mean DSC (LGE: 0.845 ± 0.075 ; VNE: 0.845 ± 0.071 ; p = n s ). Incorporating GAN-generated VNE data into the training process consistently led to enhanced performance for both individual models and the overall framework. The quality control mechanism yielded a high performance (MAE = 0.043 , accuracy = 0.951 ) emphasising the accuracy of the quality control-driven strategy in predicting segmentation quality in clinical settings. Overall, no statistical difference (p = n s ) was found when comparing the LGE and VNE test sets across all experiments.

Conclusions

The QCD ensemble framework, leveraging GAN-generated VNE data and an automated quality control mechanism, significantly improved the accuracy and reliability of LGE segmentation, paving the way for enhanced and accountable diagnostic imaging in routine clinical use.

Multi-modality cardiac image computing: A survey

Multi-modality cardiac imaging plays a key role in the management of patients with cardiovascular diseases. It allows a combination of complementary anatomical, morphological and functional information, increases diagnosis accuracy, and improves the efficacy of cardiovascular interventions and clinical outcomes. Fully-automated processing and quantitative analysis of multi-modality cardiac images could have a direct impact on clinical research and evidence-based patient management. However, these require overcoming significant challenges including inter-modality misalignment and finding optimal methods to integrate information from different modalities. This paper aims to provide a comprehensive review of multi-modality imaging in cardiology, the computing methods, the validation strategies, the related clinical workflows and future perspectives. For the computing methodologies, we have a favored focus on the three tasks, i.e., registration, fusion and segmentation, which generally involve multi-modality imaging data, either combining information from different modalities or transferring information across modalities. The review highlights that multi-modality cardiac imaging data has the potential of wide applicability in the clinic, such as trans-aortic valve implantation guidance, myocardial viability assessment, and catheter ablation therapy and its patient selection. Nevertheless, many challenges remain unsolved, such as missing modality, modality selection, combination of imaging and non-imaging data, and uniform analysis and representation of different modalities. There is also work to do in defining how the well-developed techniques fit in clinical workflows and how much additional and relevant information they introduce. These problems are likely to continue to be an active field of research and the questions to be answered in the future.

Personalized biomechanical insights in atrial fibrillation: opportunities & challenges

INTRODUCTION

Atrial fibrillation (AF) is an increasingly prevalent and significant worldwide health problem. Manifested as an irregular atrial electrophysiological activation, it is associated with many serious health complications. AF affects the biomechanical function of the heart as contraction follows the electrical activation, subsequently leading to reduced blood flow. The underlying mechanisms behind AF are not fully understood, but it is known that AF is highly correlated with the presence of atrial fibrosis, and with a manifold increase in risk of stroke.

AREAS COVERED

In this review, we focus on biomechanical aspects in atrial fibrillation, current and emerging use of clinical images, and personalized computational models. We also discuss how these can be used to provide patient-specific care.

EXPERT OPINION

Understanding the connection betweenatrial fibrillation and atrial remodeling might lead to valuable understanding of stroke and heart failure pathophysiology. Established and emerging imaging modalities can bring us closer to this understanding, especially with continued advancements in processing accuracy, reproducibility, and clinical relevance of the associated technologies. Computational models of cardiac electromechanics can be used to glean additional insights on the roles of AF and remodeling in heart function.

A deep-learning approach for myocardial fibrosis detection in early contrast-enhanced cardiac CT images

Aims

Diagnosis of myocardial fibrosis is commonly performed with late gadolinium contrast-enhanced (CE) cardiac magnetic resonance (CMR), which might be contraindicated or unavailable. Coronary computed tomography (CCT) is emerging as an alternative to CMR. We sought to evaluate whether a deep learning (DL) model could allow identification of myocardial fibrosis from routine early CE-CCT images.

Methods and results

Fifty consecutive patients with known left ventricular (LV) dysfunction (LVD) underwent both CE-CMR and (early and late) CE-CCT. According to the CE-CMR patterns, patients were classified as ischemic (n = 15, 30%) or non-ischemic (n = 35, 70%) LVD. Delayed enhancement regions were manually traced on late CE-CCT using CE-CMR as reference. On early CE-CCT images, the myocardial sectors were extracted according to AHA 16-segment model and labeled as with scar or not, based on the late CE-CCT manual tracing. A DL model was developed to classify each segment. A total of 44,187 LV segments were analyzed, resulting in accuracy of 71% and area under the ROC curve of 76% (95% CI: 72%-81%), while, with the bull's eye segmental comparison of CE-CMR and respective early CE-CCT findings, an 89% agreement was achieved.

Conclusions

DL on early CE-CCT acquisition may allow detection of LV sectors affected with myocardial fibrosis, thus without additional contrast-agent administration or radiational dose. Such tool might reduce the user interaction and visual inspection with benefit in both efforts and time.

Automated diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging using deep learning models: A review

In recent years, cardiovascular diseases (CVDs) have become one of the leading causes of mortality globally. At early stages, CVDs appear with minor symptoms and progressively get worse. The majority of people experience symptoms such as exhaustion, shortness of breath, ankle swelling, fluid retention, and other symptoms when starting CVD. Coronary artery disease (CAD), arrhythmia, cardiomyopathy, congenital heart defect (CHD), mitral regurgitation, and angina are the most common CVDs. Clinical methods such as blood tests, electrocardiography (ECG) signals, and medical imaging are the most effective methods used for the detection of CVDs. Among the diagnostic methods, cardiac magnetic resonance imaging (CMRI) is increasingly used to diagnose, monitor the disease, plan treatment and predict CVDs. Coupled with all the advantages of CMR data, CVDs diagnosis is challenging for physicians as each scan has many slices of data, and the contrast of it might be low. To address these issues, deep learning (DL) techniques have been employed in the diagnosis of CVDs using CMR data, and much research is currently being conducted in this field. This review provides an overview of the studies performed in CVDs detection using CMR images and DL techniques. The introduction section examined CVDs types, diagnostic methods, and the most important medical imaging techniques. The following presents research to detect CVDs using CMR images and the most significant DL methods. Another section discussed the challenges in diagnosing CVDs from CMRI data. Next, the discussion section discusses the results of this review, and future work in CVDs diagnosis from CMR images and DL techniques are outlined. Finally, the most important findings of this study are presented in the conclusion section.

Imageable AuNP-ECM Hydrogel Tissue Implants for Regenerative Medicine

In myocardial infarction, a blockage in one of the coronary arteries leads to ischemic conditions in the left ventricle of the myocardium and, therefore, to significant death of contractile cardiac cells. This process leads to the formation of scar tissue, which reduces heart functionality. Cardiac tissue engineering is an interdisciplinary technology that treats the injured myocardium and improves its functionality. However, in many cases, mainly when employing injectable hydrogels, the treatment may be partial because it does not fully cover the diseased area and, therefore, may not be effective and even cause conduction disorders. Here, we report a hybrid nanocomposite material composed of gold nanoparticles and an extracellular matrix-based hydrogel. Such a hybrid hydrogel could support cardiac cell growth and promote cardiac tissue assembly. After injection of the hybrid material into the diseased area of the heart, it could be efficiently imaged by magnetic resonance imaging (MRI). Furthermore, as the scar tissue could also be detected by MRI, a distinction between the diseased area and the treatment could be made, providing information about the ability of the hydrogel to cover the scar. We envision that such a nanocomposite hydrogel may improve the accuracy of tissue engineering treatment.

An accurate and time-efficient deep learning-based system for automated segmentation and reporting of cardiac magnetic resonance-detected ischemic scar

BACKGROUND AND OBJECTIVES

Myocardial infarction scar (MIS) assessment by cardiac magnetic resonance provides prognostic information and guides patients' clinical management. However, MIS segmentation is time-consuming and not performed routinely. This study presents a deep-learning-based computational workflow for the segmentation of left ventricular (LV) MIS, for the first time performed on state-of-the-art dark-blood late gadolinium enhancement (DB-LGE) images, and the computation of MIS transmurality and extent.

METHODS

DB-LGE short-axis images of consecutive patients with myocardial infarction were acquired at 1.5T in two centres between Jan 1, 2019, and June 1, 2021. Two convolutional neural network (CNN) models based on the U-Net architecture were trained to sequentially segment the LV and MIS, by processing an incoming series of DB-LGE images. A 5-fold cross-validation was performed to assess the performance of the models. Model outputs were compared respectively with manual (LV endo- and epicardial border) and semi-automated (MIS, 4-Standard Deviation technique) ground truth to assess the accuracy of the segmentation. An automated post-processing and reporting tool was developed, computing MIS extent (expressed as relative infarcted mass) and transmurality.

RESULTS

The dataset included 1355 DB-LGE short-axis images from 144 patients (MIS in 942 images). High performance (> 0.85) as measured by the Intersection over Union metric was obtained for both the LV and MIS segmentations on the training sets. The performance for both LV and MIS segmentations was 0.83 on the test sets. Compared to the 4-Standard Deviation segmentation technique, our system was five times quicker (<1 min versus 7 ± 3 min), and required minimal user interaction.

CONCLUSIONS

Our solution successfully addresses different issues related to automatic MIS segmentation, including accuracy, time-effectiveness, and the automatic generation of a clinical report.

Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment

BACKGROUND

Segmentation of cardiovascular magnetic resonance (CMR) images is an essential step for evaluating dimensional and functional ventricular parameters as ejection fraction (EF) but may be limited by artifacts, which represent the major challenge to automatically derive clinical information. The aim of this study is to investigate the accuracy of a deep learning (DL) approach for automatic segmentation of cardiac structures from CMR images characterized by magnetic susceptibility artifact in patient with cardiac implanted electronic devices (CIED).

METHODS

In this retrospective study, 230 patients (100 with CIED) who underwent clinically indicated CMR were used to developed and test a DL model. A novel convolutional neural network was proposed to extract the left ventricle (LV) and right (RV) ventricle endocardium and LV epicardium. In order to perform a successful segmentation, it is important the network learns to identify salient image regions even during local magnetic field inhomogeneities. The proposed network takes advantage from a spatial attention module to selectively process the most relevant information and focus on the structures of interest. To improve segmentation, especially for images with artifacts, multiple loss functions were minimized in unison. Segmentation results were assessed against manual tracings and commercial CMR analysis software cvi42(Circle Cardiovascular Imaging, Calgary, Alberta, Canada). An external dataset of 56 patients with CIED was used to assess model generalizability.

RESULTS

In the internal datasets, on image with artifacts, the median Dice coefficients for end-diastolic LV cavity, LV myocardium and RV cavity, were 0.93, 0.77 and 0.87 and 0.91, 0.82, and 0.83 in end-systole, respectively. The proposed method reached higher segmentation accuracy than commercial software, with performance comparable to expert inter-observer variability (bias ± 95%LoA): LVEF 1 ± 8% vs 3 ± 9%, RVEF - 2 ± 15% vs 3 ± 21%. In the external cohort, EF well correlated with manual tracing (intraclass correlation coefficient: LVEF 0.98, RVEF 0.93). The automatic approach was significant faster than manual segmentation in providing cardiac parameters (approximately 1.5 s vs 450 s).

CONCLUSIONS

Experimental results show that the proposed method reached promising performance in cardiac segmentation from CMR images with susceptibility artifacts and alleviates time consuming expert physician contour segmentation.

Detection of myocardial fibrosis: Where we stand

Myocardial fibrosis, resulting from the disturbance of extracellular matrix homeostasis in response to different insults, is a common and important pathological remodeling process that is associated with adverse clinical outcomes, including arrhythmia, heart failure, or even sudden cardiac death. Over the past decades, multiple non-invasive detection methods have been developed. Laboratory biomarkers can aid in both detection and risk stratification by reflecting cellular and even molecular changes in fibrotic processes, yet more evidence that validates their detection accuracy is still warranted. Different non-invasive imaging techniques have been demonstrated to not only detect myocardial fibrosis but also provide information on prognosis and management. Cardiovascular magnetic resonance (CMR) is considered as the gold standard imaging technique to non-invasively identify and quantify myocardial fibrosis with its natural ability for tissue characterization. This review summarizes the current understanding of the non-invasive detection methods of myocardial fibrosis, with the focus on different techniques and clinical applications of CMR.

Predicting post-contrast information from contrast agent free cardiac MRI using machine learning: Challenges and methods

Objectives

Currently, administering contrast agents is necessary for accurately visualizing and quantifying presence, location, and extent of myocardial infarction (MI) with cardiac magnetic resonance (CMR). In this study, our objective is to investigate and analyze pre- and post-contrast CMR images with the goal of predicting post-contrast information using pre-contrast information only. We propose methods and identify challenges.

Methods

The study population consists of 272 retrospectively selected CMR studies with diagnoses of MI (n = 108) and healthy controls (n = 164). We describe a pipeline for pre-processing this dataset for analysis. After data feature engineering, 722 cine short-axis (SAX) images and segmentation mask pairs were used for experimentation. This constitutes 506, 108, and 108 pairs for the training, validation, and testing sets, respectively. We use deep learning (DL) segmentation (UNet) and classification (ResNet50) models to discover the extent and location of the scar and classify between the ischemic cases and healthy cases (i.e., cases with no regional myocardial scar) from the pre-contrast cine SAX image frames, respectively. We then capture complex data patterns that represent subtle signal and functional changes in the cine SAX images due to MI using optical flow, rate of change of myocardial area, and radiomics data. We apply this dataset to explore two supervised learning methods, namely, the support vector machines (SVM) and the decision tree (DT) methods, to develop predictive models for classifying pre-contrast cine SAX images as being a case of MI or healthy.

Results

Overall, for the UNet segmentation model, the performance based on the mean Dice score for the test set (n = 108) is 0.75 (±0.20) for the endocardium, 0.51 (±0.21) for the epicardium and 0.20 (±0.17) for the scar. For the classification task, the accuracy, F1 and precision scores of 0.68, 0.69, and 0.64, respectively, were achieved with the SVM model, and of 0.62, 0.63, and 0.72, respectively, with the DT model.

Conclusion

We have presented some promising approaches involving DL, SVM, and DT methods in an attempt to accurately predict contrast information from non-contrast images. While our initial results are modest for this challenging task, this area of research still poses several open problems.

CM-SegNet: A deep learning-based automatic segmentation approach for medical images by combining convolution and multilayer perceptron

Accurate segmentation of lesions in medical images is of great significance for clinical diagnosis and evaluation. The low contrast between lesions and surrounding tissues increases the difficulty of automatic segmentation, while the efficiency of manual segmentation is low. In order to increase the generalization performance of segmentation model, we proposed a deep learning-based automatic segmentation model called CM-SegNet for segmenting medical images of different modalities. It was designed according to the multiscale input and encoding-decoding thoughts, and composed of multilayer perceptron and convolution modules. This model achieved communication of different channels and different spatial locations of each patch, and considers the edge related feature information between adjacent patches. Thus, it could fully extract global and local image information for the segmentation task. Meanwhile, this model met the effective segmentation of different structural lesion regions in different slices of three-dimensional medical images. In this experiment, the proposed CM-SegNet was trained, validated, and tested using six medical image datasets of different modalities and 5-fold cross validation method. The results showed that the CM-SegNet model had better segmentation performance and shorter training time for different medical images than the previous methods, suggesting it is faster and more accurate in automatic segmentation and has great potential application in clinic.

Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Networks

Point clouds are a widely used format for storing information in a memory-efficient and easily manipulatable representation. However, research in the application of point cloud mapping and subsequent organ reconstruction with deep learning, is limited. In particular, current methods for left atrium (LA) visualization using point clouds recorded from clinical mapping during cardiac ablation are proprietary and remain difficult to validate. Many clinics rely on additional imaging such as MRIs/CTs to improve the accuracy of LA mapping. In this study, for the first time, we proposed a novel deep learning framework for the automatic 3D surface reconstruction of the LA directly from point clouds acquired via widely used clinical mapping systems. The backbone of our framework consists of a 30-layer 3D fully convolutional neural network (CNN). The architecture contains skip connections that perform multi-resolution processing to maximize information extraction from the point clouds and ensure a high-resolution prediction by combining features at different receptive levels. We used large kernels with increased receptive fields to address the sparsity of the point clouds. Residual blocks and activation normalization were further implemented to improve the feature learning on sparse inputs. By utilizing a light-weight design with low-depth layers, our CNN took approximately 10 s per patient. Independent testing on two cross-modality clinical datasets showed excellent dice scores of 93% and surface-to-surface distances below 1 pixel. Overall, our study may provide a more efficient, cost-effective 3D LA reconstruction approach during ablation procedures, and potentially lead to improved treatment of cardiac diseases.

Direct left-ventricular global longitudinal strain (GLS) computation with a fully convolutional network

This study's purpose was to develop a direct MRI-based, deep-learning semantic segmentation approach for computing global longitudinal strain (GLS), a known metric for detecting left-ventricular (LV) cardiotoxicity in breast cancer. Displacement Encoding with Stimulated Echoes cardiac image phases acquired from 30 breast cancer patients and 30 healthy females were unwrapped via a DeepLabV3 + fully convolutional network (FCN). Myocardial strains were directly computed from the unwrapped phases with the Radial Point Interpolation Method. FCN-unwrapped phases of a phantom's rotating gel were validated against quality-guided phase-unwrapping (QGPU) and robust transport of intensity equation (RTIE) phase-unwrapping. FCN performance on unwrapping human LV data was measured with F1 and Dice scores versus QGPU ground-truth. The reliability of FCN-based strains was assessed against RTIE-based strains with Cronbach's alpha (C-α) intraclass correlation coefficient. Mean squared error (MSE) of unwrapping the phantom experiment data at 0 dB signal-to-noise ratio were 1.6, 2.7 and 6.1 with FCN, QGPU and RTIE techniques. Human data classification accuracies were F1 = 0.95 (Dice = 0.96) with FCN and F1 = 0.94 (Dice = 0.95) with RTIE. GLS results from FCN and RTIE were -16 ± 3% vs. -16 ± 3% (C-α = 0.9) for patients and -20 ± 3% vs. -20 ± 3% (C-α = 0.9) for healthy subjects. The low MSE from the phantom validation demonstrates accuracy of phase-unwrapping with the FCN and comparable human subject results versus RTIE demonstrate GLS analysis accuracy. A deep-learning methodology for phase-unwrapping in medical images and GLS computation was developed and validated in a heterogeneous cohort.

Feasibility of cardiac-synchronized quantitative T1 and T2 mapping on a hybrid 1.5 Tesla magnetic resonance imaging and linear accelerator system

Background and Purpose

Materials and methods

Results

Conclusions

Two-Stage Segmentation Framework Based on Distance Transformation

With the rise of deep learning, using deep learning to segment lesions and assist in diagnosis has become an effective means to promote clinical medical analysis. However, the partial volume effect of organ tissues leads to unclear and blurred edges of ROI in medical images, making it challenging to achieve high-accuracy segmentation of lesions or organs. In this paper, we assume that the distance map obtained by performing distance transformation on the ROI edge can be used as a weight map to make the network pay more attention to the learning of the ROI edge region. To this end, we design a novel framework to flexibly embed the distance map into the two-stage network to improve left atrium MRI segmentation performance. Furthermore, a series of distance map generation methods are proposed and studied to reasonably explore how to express the weight of assisting network learning. We conduct thorough experiments to verify the effectiveness of the proposed segmentation framework, and experimental results demonstrate that our hypothesis is feasible.

CyCMIS: Cycle-consistent Cross-domain Medical Image Segmentation via diverse image augmentation

Domain shift, a phenomenon when there exists distribution discrepancy between training dataset (source domain) and test dataset (target domain), is very common in practical applications and may cause significant performance degradation, which hinders the effective deployment of deep learning models to clinical settings. Adaptation algorithms to improve the model generalizability from source domain to target domain has significant practical value. In this paper, we investigate unsupervised domain adaptation (UDA) technique to train a cross-domain segmentation method which is robust to domain shift, and which does not require any annotations on the test domain. To this end, we propose Cycle-consistent Cross-domain Medical Image Segmentation, referred as CyCMIS, integrating online diverse image translation via disentangled representation learning and semantic consistency regularization into one network. Different from learning one-to-one mapping, our method characterizes the complex relationship between domains as many-to-many mapping. A novel diverse inter-domain semantic consistency loss is then proposed to regularize the cross-domain segmentation process. We additionally introduce an intra-domain semantic consistency loss to encourage the segmentation consistency between the original input and the image after cross-cycle reconstruction. We conduct comprehensive experiments on two publicly available datasets to evaluate the effectiveness of the proposed method. Results demonstrate the efficacy of the present approach.