Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

A bidirectional registration neural network for cardiac motion tracking using cine MRI images

Using cine magnetic resonance imaging (cine MRI) images to track cardiac motion helps users to analyze the myocardial strain, and is of great importance in clinical applications. At present, most of the automatic deep learning-based motion tracking methods compare two images without considering temporal information between MRI frames, which easily leads to the lack of consistency of the generated motion fields. Even though a small number of works take into account the temporal factor, they are usually computationally intensive or have limitations on image length. To solve this problem, we propose a bidirectional convolution neural network for motion tracking of cardiac cine MRI images. This network leverages convolutional blocks to extract spatial features from three-dimensional (3D) image registration pairs, and models the temporal relations through a bidirectional recurrent neural network to obtain the Lagrange motion field between the reference image and other images. Compared with previous pairwise registration methods, the proposed method can automatically learn spatiotemporal information from multiple images with fewer parameters. We evaluated our model on three public cardiac cine MRI datasets. The experimental results demonstrated that the proposed method can significantly improve the motion tracking accuracy. The average Dice coefficient between estimated segmentation and manual segmentation has reached almost 0.85 on the widely used Automatic Cardiac Diagnostic Challenge (ACDC) dataset.

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.

Dual-feature Fusion Attention Network for Small Object Segmentation

Accurate segmentation of medical images is an important step during radiotherapy planning and clinical diagnosis. However, manually marking organ or lesion boundaries is tedious, time-consuming, and prone to error due to subjective variability of radiologist. Automatic segmentation remains a challenging task owing to the variation (in shape and size) across subjects. Moreover, existing convolutional neural networks based methods perform poorly in small medical objects segmentation due to class imbalance and boundary ambiguity. In this paper, we propose a dual feature fusion attention network (DFF-Net) to improve the segmentation accuracy of small objects. It mainly includes two core modules: the dual-branch feature fusion module (DFFM) and the reverse attention context module (RACM). We first extract multi-resolution features by multi-scale feature extractor, then construct DFFM to aggregate the global and local contextual information to achieve information complementarity among features, which provides sufficient guidance for accurate small objects segmentation. Moreover, to alleviate the degradation of segmentation accuracy caused by blurred medical image boundaries, we propose RACM to enhance the edge texture of features. Experimental results on datasets NPC, ACDC, and Polyp demonstrate that our proposed method has fewer parameters, faster inference, and lower model complexity, and achieves better accuracy than more state-of-the-art methods.

Minimizing Estimated Risks on Unlabeled Data: A New Formulation for Semi-Supervised Medical Image Segmentation

Supervised segmentation can be costly, particularly in applications of biomedical image analysis where large scale manual annotations from experts are generally too expensive to be available. Semi-supervised segmentation, able to learn from both the labeled and unlabeled images, could be an efficient and effective alternative for such scenarios. In this work, we propose a new formulation based on risk minimization, which makes full use of the unlabeled images. Different from most of the existing approaches which solely explicitly guarantee the minimization of prediction risks from the labeled training images, the new formulation also considers the risks on unlabeled images. Particularly, this is achieved via an unbiased estimator, based on which we develop a general framework for semi-supervised image segmentation. We validate this framework on three medical image segmentation tasks, namely cardiac segmentation on ACDC2017, optic cup and disc segmentation on REFUGE dataset and 3D whole heart segmentation on MM-WHS dataset. Results show that the proposed estimator is effective, and the segmentation method achieves superior performance and demonstrates great potential compared to the other state-of-the-art approaches. Our code and data will be released via https://zmiclab.github.io/projects.html, once the manuscript is accepted for publication.

Reducing segmentation failures in cardiac MRI via late feature fusion and GAN-based augmentation

Cardiac magnetic resonance (CMR) image segmentation is an integral step in the analysis of cardiac function and diagnosis of heart related diseases. While recent deep learning-based approaches in automatic segmentation have shown great promise to alleviate the need for manual segmentation, most of these are not applicable to realistic clinical scenarios. This is largely due to training on mainly homogeneous datasets, without variation in acquisition, which typically occurs in multi-vendor and multi-site settings, as well as pathological data. Such approaches frequently exhibit a degradation in prediction performance, particularly on outlier cases commonly associated with difficult pathologies, artifacts and extensive changes in tissue shape and appearance. In this work, we present a model aimed at segmenting all three cardiac structures in a multi-center, multi-disease and multi-view scenario. We propose a pipeline, addressing different challenges with segmentation of such heterogeneous data, consisting of heart region detection, augmentation through image synthesis and a late-fusion segmentation approach. Extensive experiments and analysis demonstrate the ability of the proposed approach to tackle the presence of outlier cases during both training and testing, allowing for better adaptation to unseen and difficult examples. Overall, we show that the effective reduction of segmentation failures on outlier cases has a positive impact on not only the average segmentation performance, but also on the estimation of clinical parameters, leading to a better consistency in derived metrics.

FDCT: Fusion-Guided Dual-View Consistency Training for semi-supervised tissue segmentation on MRI

Accurate tissue segmentation on MRI is important for physicians to make diagnosis and treatment for patients. However, most of the models are only designed for single-task tissue segmentation, and tend to lack generality to other MRI tissue segmentation tasks. Not only that, the acquisition of labels is time-consuming and laborious, which remains a challenge to be solved. In this study, we propose the universal Fusion-Guided Dual-View Consistency Training(FDCT) for semi-supervised tissue segmentation on MRI. It can obtain accurate and robust tissue segmentation for multiple tasks, and alleviates the problem of insufficient labeled data. Especially, for building bidirectional consistency, we feed dual-view images into a single-encoder dual-decoder structure to obtain view-level predictions, then put them into a fusion module to generate image-level pseudo-label. Moreover, to improve boundary segmentation quality, we propose the Soft-label Boundary Optimization Module(SBOM). We have conducted extensive experiments on three MRI datasets to evaluate the effectiveness of our method. Experimental results demonstrate that our method outperforms the state-of-the-art semi-supervised medical image segmentation methods.

Multi-channel deep learning model-based myocardial spatial-temporal morphology feature on cardiac MRI cine images diagnoses the cause of LVH

BACKGROUND

To develop a fully automatic framework for the diagnosis of cause for left ventricular hypertrophy (LVH) via cardiac cine images.

METHODS

A total of 302 LVH patients with cine MRI images were recruited as the primary cohort. Another 53 LVH patients prospectively collected or from multi-centers were used as the external test dataset. Different models based on the cardiac regions (Model 1), segmented ventricle (Model 2) and ventricle mask (Model 3) were constructed. The diagnostic performance was accessed by the confusion matrix with respect to overall accuracy. The capability of the predictive models for binary classification of cardiac amyloidosis (CA), hypertrophic cardiomyopathy (HCM) or hypertensive heart disease (HHD) were also evaluated. Additionally, the diagnostic performance of best Model was compared with that of 7 radiologists/cardiologists.

RESULTS

Model 3 showed the best performance with an overall classification accuracy up to 77.4% in the external test datasets. On the subtasks for identifying CA, HCM or HHD only, Model 3 also achieved the best performance with AUCs yielding 0.895-0.980, 0.879-0.984 and 0.848-0.983 in the validation, internal test and external test datasets, respectively. The deep learning model showed non-inferior diagnostic capability to the cardiovascular imaging expert and outperformed other radiologists/cardiologists.

CONCLUSION

The combined model based on the mask of left ventricular segmented from multi-sequences cine MR images shows favorable and robust performance in diagnosing the cause of left ventricular hypertrophy, which could be served as a noninvasive tool and help clinical decision.

MRXCAT2.0: Synthesis of realistic numerical phantoms by combining left-ventricular shape learning, biophysical simulations and tissue texture generation

BACKGROUND

Standardised performance assessment of image acquisition, reconstruction and processing methods is limited by the absence of images paired with ground truth reference values. To this end, we propose MRXCAT2.0 to generate synthetic data, covering healthy and pathological function, using a biophysical model. We exemplify the approach by generating cardiovascular magnetic resonance (CMR) images of healthy, infarcted, dilated and hypertrophic left-ventricular (LV) function.

METHOD

In MRXCAT2.0, the XCAT torso phantom is coupled with a statistical shape model, describing population (patho)physiological variability, and a biophysical model, providing known and detailed functional ground truth of LV morphology and function. CMR balanced steady-state free precession images are generated using MRXCAT2.0 while realistic image appearance is ensured by assigning texturized tissue properties to the phantom labels.

FINDING

Paired CMR image and ground truth data of LV function were generated with a range of LV masses (85-140 g), ejection fractions (34-51%) and peak radial and circumferential strains (0.45 to 0.95 and - 0.18 to - 0.13, respectively). These ranges cover healthy and pathological cases, including infarction, dilated and hypertrophic cardiomyopathy. The generation of the anatomy takes a few seconds and it improves on current state-of-the-art models where the pathological representation is not explicitly addressed. For the full simulation framework, the biophysical models require approximately two hours, while image generation requires a few minutes per slice.

CONCLUSION

MRXCAT2.0 offers synthesis of realistic images embedding population-based anatomical and functional variability and associated ground truth parameters to facilitate a standardized assessment of CMR acquisition, reconstruction and processing methods.

Left ventricle segmentation combining deep learning and deformable models with anatomical constraints

Segmentation of the left ventricle is a key approach in Cardiac Magnetic Resonance Imaging for calculating biomarkers in diagnosis. Since there is substantial effort required from the expert, many automatic segmentation methods have been proposed, in which deep learning networks have obtained remarkable performance. However, one of the main limitations of these approaches is the production of segmentations that contain anatomical errors. To avoid this limitation, we propose a new fully-automatic left ventricle segmentation method combining deep learning and deformable models. We propose a new level set energy formulation that includes exam-specific information estimated from the deep learning segmentation and shape constraints. The method is part of a pipeline containing pre-processing steps and a failure correction post-processing step. Experiments were conducted with the Sunnybrook and ACDC public datasets, and a private dataset. Results suggest that the method is competitive, that it can produce anatomically consistent segmentations, has good generalization ability, and is often able to estimate biomarkers close to the expert.

Multilevel comparison of deep learning models for function quantification in cardiovascular magnetic resonance: On the redundancy of architectural variations

Background

Cardiac function quantification in cardiovascular magnetic resonance requires precise contouring of the heart chambers. This time-consuming task is increasingly being addressed by a plethora of ever more complex deep learning methods. However, only a small fraction of these have made their way from academia into clinical practice. In the quality assessment and control of medical artificial intelligence, the opaque reasoning and associated distinctive errors of neural networks meet an extraordinarily low tolerance for failure.

Aim

The aim of this study is a multilevel analysis and comparison of the performance of three popular convolutional neural network (CNN) models for cardiac function quantification.

Methods

U-Net, FCN, and MultiResUNet were trained for the segmentation of the left and right ventricles on short-axis cine images of 119 patients from clinical routine. The training pipeline and hyperparameters were kept constant to isolate the influence of network architecture. CNN performance was evaluated against expert segmentations for 29 test cases on contour level and in terms of quantitative clinical parameters. Multilevel analysis included breakdown of results by slice position, as well as visualization of segmentation deviations and linkage of volume differences to segmentation metrics via correlation plots for qualitative analysis.

Results

All models showed strong correlation to the expert with respect to quantitative clinical parameters (rz ' = 0.978, 0.977, 0.978 for U-Net, FCN, MultiResUNet respectively). The MultiResUNet significantly underestimated ventricular volumes and left ventricular myocardial mass. Segmentation difficulties and failures clustered in basal and apical slices for all CNNs, with the largest volume differences in the basal slices (mean absolute error per slice: 4.2 ± 4.5 ml for basal, 0.9 ± 1.3 ml for midventricular, 0.9 ± 0.9 ml for apical slices). Results for the right ventricle had higher variance and more outliers compared to the left ventricle. Intraclass correlation for clinical parameters was excellent (≥0.91) among the CNNs.

Conclusion

Modifications to CNN architecture were not critical to the quality of error for our dataset. Despite good overall agreement with the expert, errors accumulated in basal and apical slices for all models.

Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review

Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy regulations. Data augmentation techniques offer a solution by artificially increasing the number of training samples, but these techniques often produce limited and unconvincing results. To address this issue, a growing number of studies have proposed the use of deep generative models to generate more realistic and diverse data that conform to the true distribution of the data. In this review, we focus on three types of deep generative models for medical image augmentation: variational autoencoders, generative adversarial networks, and diffusion models. We provide an overview of the current state of the art in each of these models and discuss their potential for use in different downstream tasks in medical imaging, including classification, segmentation, and cross-modal translation. We also evaluate the strengths and limitations of each model and suggest directions for future research in this field. Our goal is to provide a comprehensive review about the use of deep generative models for medical image augmentation and to highlight the potential of these models for improving the performance of deep learning algorithms in medical image analysis.

Machine Learning and the Conundrum of Stroke Risk Prediction

Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.

PyMIC: A deep learning toolkit for annotation-efficient medical image segmentation

BACKGROUND AND OBJECTIVE

Open-source deep learning toolkits are one of the driving forces for developing medical image segmentation models that are essential for computer-assisted diagnosis and treatment procedures. Existing toolkits mainly focus on fully supervised segmentation that assumes full and accurate pixel-level annotations are available. Such annotations are time-consuming and difficult to acquire for segmentation tasks, which makes learning from imperfect labels highly desired for reducing the annotation cost. We aim to develop a new deep learning toolkit to support annotation-efficient learning for medical image segmentation, which can accelerate and simplify the development of deep learning models with limited annotation budget, e.g., learning from partial, sparse or noisy annotations.

METHODS

Our proposed toolkit named PyMIC is a modular deep learning library for medical image segmentation tasks. In addition to basic components that support development of high-performance models for fully supervised segmentation, it contains several advanced components that are tailored for learning from imperfect annotations, such as loading annotated and unannounced images, loss functions for unannotated, partially or inaccurately annotated images, and training procedures for co-learning between multiple networks, etc. PyMIC is built on the PyTorch framework and supports development of semi-supervised, weakly supervised and noise-robust learning methods for medical image segmentation.

RESULTS

We present several illustrative medical image segmentation tasks based on PyMIC: (1) Achieving competitive performance on fully supervised learning; (2) Semi-supervised cardiac structure segmentation with only 10% training images annotated; (3) Weakly supervised segmentation using scribble annotations; and (4) Learning from noisy labels for chest radiograph segmentation.

CONCLUSIONS

The PyMIC toolkit is easy to use and facilitates efficient development of medical image segmentation models with imperfect annotations. It is modular and flexible, which enables researchers to develop high-performance models with low annotation cost. The source code is available at:https://github.com/HiLab-git/PyMIC.

Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives

Transformer, one of the latest technological advances of deep learning, has gained prevalence in natural language processing or computer vision. Since medical imaging bear some resemblance to computer vision, it is natural to inquire about the status quo of Transformers in medical imaging and ask the question: can the Transformer models transform medical imaging? In this paper, we attempt to make a response to the inquiry. After a brief introduction of the fundamentals of Transformers, especially in comparison with convolutional neural networks (CNNs), and highlighting key defining properties that characterize the Transformers, we offer a comprehensive review of the state-of-the-art Transformer-based approaches for medical imaging and exhibit current research progresses made in the areas of medical image segmentation, recognition, detection, registration, reconstruction, enhancement, etc. In particular, what distinguishes our review lies in its organization based on the Transformer's key defining properties, which are mostly derived from comparing the Transformer and CNN, and its type of architecture, which specifies the manner in which the Transformer and CNN are combined, all helping the readers to best understand the rationale behind the reviewed approaches. We conclude with discussions of future perspectives.

MyoPS: A benchmark of myocardial pathology segmentation combining three-sequence cardiac magnetic resonance images

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on the myocardium is the key to this assessment. This work defines a new task of medical image analysis, i.e., to perform myocardial pathology segmentation (MyoPS) combining three-sequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. Note that MyoPS refers to both myocardial pathology segmentation and the challenge in this paper. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segmentation. In this article, we provide details of the challenge, survey the works from fifteen participants and interpret their methods according to five aspects, i.e., preprocessing, data augmentation, learning strategy, model architecture and post-processing. In addition, we analyze the results with respect to different factors, in order to examine the key obstacles and explore the potential of solutions, as well as to provide a benchmark for future research. The average Dice scores of submitted algorithms were 0.614±0.231 and 0.644±0.153 for myocardial scars and edema, respectively. We conclude that while promising results have been reported, the research is still in the early stage, and more in-depth exploration is needed before a successful application to the clinics. MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/myops20/).

N-Net: an UNet architecture with dual encoder for medical image segmentation

In order to assist physicians in diagnosis and treatment planning, accurate and automatic methods of organ segmentation are needed in clinical practice. UNet and its improved models, such as UNet +  + and UNt3 + , have been powerful tools for medical image segmentation. In this paper, we focus on helping the encoder extract richer features and propose a N-Net for medical image segmentation. On the basis of UNet, we propose a dual encoder model to deepen the network depth and enhance the ability of feature extraction. In our implementation, the Squeeze-and-Excitation (SE) module is added to the dual encoder model to obtain channel-level global features. In addition, the introduction of full-scale skip connections promotes the integration of low-level details and high-level semantic information. The performance of our model is tested on the lung and liver datasets, and compared with UNet, UNet +  + and UNet3 + in terms of quantitative evaluation with the Dice, Recall, Precision and F1 score and qualitative evaluation. Our experiments demonstrate that N-Net outperforms the work of UNet, UNet +  + and UNet3 + in these three datasets. By visual comparison of the segmentation results, N-Net produces more coherent organ boundaries and finer details.

Epoch and accuracy based empirical study for cardiac MRI segmentation using deep learning technique

Cardiac magnetic resonance imaging (CMRI) is a non-invasive imaging technique to analyse the structure and function of the heart. It was enhanced considerably over several years to deliver functional information for diagnosing and managing cardiovascular disease. CMRI image delivers non-invasive, clear access to the heart and great vessels. The segmentation of CMRI provides quantification parameters such as myocardial viability, ejection fraction, cardiac chamber volume, and morphological details. In general, experts interpret the CMR images by delineating the images manually. The manual segmentation process is time-consuming, and it has been observed that the final observation varied with the opinion of the different experts. Convolution neural network is a new-age technology that provides impressive results compared to manual ones. In this study convolution neural network model is used for the segmentation task. The neural network parameters have been optimized to perform on the novel data set for accurate predictions. With other parameters, epochs play an essential role in training the network, as the network should not be under-fitted or over-fitted. The relationship between the hyperparameter epoch and accuracy is established in the model. The model delivers the accuracy of 0.88 in terms of the IoU coefficient.

GANs for Medical Image Synthesis: An Empirical Study

Generative adversarial networks (GANs) have become increasingly powerful, generating mind-blowing photorealistic images that mimic the content of datasets they have been trained to replicate. One recurrent theme in medical imaging, is whether GANs can also be as effective at generating workable medical data, as they are for generating realistic RGB images. In this paper, we perform a multi-GAN and multi-application study, to gauge the benefits of GANs in medical imaging. We tested various GAN architectures, from basic DCGAN to more sophisticated style-based GANs, on three medical imaging modalities and organs, namely: cardiac cine-MRI, liver CT, and RGB retina images. GANs were trained on well-known and widely utilized datasets, from which their FID scores were computed, to measure the visual acuity of their generated images. We further tested their usefulness by measuring the segmentation accuracy of a U-Net trained on these generated images and the original data. The results reveal that GANs are far from being equal, as some are ill-suited for medical imaging applications, while others performed much better. The top-performing GANs are capable of generating realistic-looking medical images by FID standards, that can fool trained experts in a visual Turing test and comply to some metrics. However, segmentation results suggest that no GAN is capable of reproducing the full richness of medical datasets.

Machine Learning Approaches in Diagnosis, Prognosis and Treatment Selection of Cardiac Amyloidosis

Cardiac amyloidosis is an uncommon restrictive cardiomyopathy featuring an unregulated amyloid protein deposition that impairs organic function. Early cardiac amyloidosis diagnosis is generally delayed by indistinguishable clinical findings of more frequent hypertrophic diseases. Furthermore, amyloidosis is divided into various groups, according to a generally accepted taxonomy, based on the proteins that make up the amyloid deposits; a careful differentiation between the various forms of amyloidosis is necessary to undertake an adequate therapeutic treatment. Thus, cardiac amyloidosis is thought to be underdiagnosed, which delays necessary therapeutic procedures, diminishing quality of life and impairing clinical prognosis. The diagnostic work-up for cardiac amyloidosis begins with the identification of clinical features, electrocardiographic and imaging findings suggestive or compatible with cardiac amyloidosis, and often requires the histological demonstration of amyloid deposition. One approach to overcome the difficulty of an early diagnosis is the use of automated diagnostic algorithms. Machine learning enables the automatic extraction of salient information from “raw data” without the need for pre-processing methods based on the a priori knowledge of the human operator. This review attempts to assess the various diagnostic approaches and artificial intelligence computational techniques in the detection of cardiac amyloidosis.

MAE-TransRNet: An improved transformer-ConvNet architecture with masked autoencoder for cardiac MRI registration

The heart is a relatively complex non-rigid motion organ in the human body. Quantitative motion analysis of the heart takes on a critical significance to help doctors with accurate diagnosis and treatment. Moreover, cardiovascular magnetic resonance imaging (CMRI) can be used to perform a more detailed quantitative analysis evaluation for cardiac diagnosis. Deformable image registration (DIR) has become a vital task in biomedical image analysis since tissue structures have variability in medical images. Recently, the model based on masked autoencoder (MAE) has recently been shown to be effective in computer vision tasks. Vision Transformer has the context aggregation ability to restore the semantic information in the original image regions by using a low proportion of visible image patches to predict the masked image patches. A novel Transformer-ConvNet architecture is proposed in this study based on MAE for medical image registration. The core of the Transformer is designed as a masked autoencoder (MAE) and a lightweight decoder structure, and feature extraction before the downstream registration task is transformed into the self-supervised learning task. This study also rethinks the calculation method of the multi-head self-attention mechanism in the Transformer encoder. We improve the query-key-value-based dot product attention by introducing both depthwise separable convolution (DWSC) and squeeze and excitation (SE) modules into the self-attention module to reduce the amount of parameter computation to highlight image details and maintain high spatial resolution image features. In addition, concurrent spatial and channel squeeze and excitation (scSE) module is embedded into the CNN structure, which also proves to be effective for extracting robust feature representations. The proposed method, called MAE-TransRNet, has better generalization. The proposed model is evaluated on the cardiac short-axis public dataset (with images and labels) at the 2017 Automated Cardiac Diagnosis Challenge (ACDC). The relevant qualitative and quantitative results (e.g., dice performance and Hausdorff distance) suggest that the proposed model can achieve superior results over those achieved by the state-of-the-art methods, thus proving that MAE and improved self-attention are more effective and promising for medical image registration tasks. Codes and models are available at https://github.com/XinXiao101/MAE-TransRNet.

Adversarial co-training for semantic segmentation over medical images

BACKGROUND AND OBJECTIVE

Abundant labeled data drives the model training for better performance, but collecting sufficient labels is still challenging. To alleviate the pressure of label collection, semi-supervised learning merges unlabeled data into training process. However, the joining of unlabeled data (e.g., data from different hospitals with different acquisition parameters) will change the original distribution. Such a distribution shift leads to a perturbation in the training process, potentially leading to a confirmation bias. In this paper, we investigate distribution shift and develop methods to increase the robustness of our models, with the goal of improving performance in semi-supervised semantic segmentation of medical images. We study distribution shift and increase model robustness to it, for improving practical performance in semi-supervised segmentation over medical images.

METHODS

To alleviate the issue of distribution shift, we introduce adversarial training into the co-training process. We simulate perturbations caused by the distribution shift via adversarial perturbations and introduce the adversarial perturbation to attack the supervised training to improve the robustness against the distribution shift. Benefiting from label guidance, supervised training does not collapse under adversarial attacks. For co-training, two sub-models are trained from two views (over two disjoint subsets of the dataset) to extract different kinds of knowledge independently. Co-training outperforms single-model by integrating both views of knowledge to avoid confirmation bias.

RESULTS

For practicality, we conduct extensive experiments on challenging medical datasets. Experimental results show desirable improvements to state-of-the-art counterparts (Yu and Wang, 2019; Peng et al., 2020; Perone et al., 2019). We achieve a DSC score of 87.37% with only 20% of labels on the ACDC dataset, almost same to using 100% of labels. On the SCGM dataset with more distribution shift, we achieve a DSC score of 78.65% with 6.5% of labels, surpassing 10.30% over Peng et al. (2020). Our evaluative results show superior robustness against distribution shifts in medical scenarios.

CONCLUSION

Empirical results show the effectiveness of our work for handling distribution shift in medical scenarios.

Attri-VAE: Attribute-based interpretable representations of medical images with variational autoencoders

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.

Domain-Incremental Cardiac Image Segmentation With Style-Oriented Replay and Domain-Sensitive Feature Whitening

Contemporary methods have shown promising results on cardiac image segmentation, but merely in static learning, i.e., optimizing the network once for all, ignoring potential needs for model updating. In real-world scenarios, new data continues to be gathered from multiple institutions over time and new demands keep growing to pursue more satisfying performance. The desired model should incrementally learn from each incoming dataset and progressively update with improved functionality as time goes by. As the datasets sequentially delivered from multiple sites are normally heterogenous with domain discrepancy, each updated model should not catastrophically forget previously learned domains while well generalizing to currently arrived domains or even unseen domains. In medical scenarios, this is particularly challenging as accessing or storing past data is commonly not allowed due to data privacy. To this end, we propose a novel domain-incremental learning framework to recover past domain inputs first and then regularly replay them during model optimization. Particularly, we first present a style-oriented replay module to enable structure-realistic and memory-efficient reproduction of past data, and then incorporate the replayed past data to jointly optimize the model with current data to alleviate catastrophic forgetting. During optimization, we additionally perform domain-sensitive feature whitening to suppress model's dependency on features that are sensitive to domain changes (e.g., domain-distinctive style features) to assist domain-invariant feature exploration and gradually improve the generalization performance of the network. We have extensively evaluated our approach with the M&Ms Dataset in single-domain and compound-domain incremental learning settings. Our approach outperforms other comparison methods with less forgetting on past domains and better generalization on current domains and unseen domains.

Self-supervised contrastive learning with random walks for medical image segmentation with limited annotations

Medical image segmentation has seen significant progress through the use of supervised deep learning. Hereby, large annotated datasets were employed to reliably segment anatomical structures. To reduce the requirement for annotated training data, self-supervised pre-training strategies on non-annotated data were designed. Especially contrastive learning schemes operating on dense pixel-wise representations have been introduced as an effective tool. In this work, we expand on this strategy and leverage inherent anatomical similarities in medical imaging data. We apply our approach to the task of semantic segmentation in a semi-supervised setting with limited amounts of annotated volumes. Trained alongside a segmentation loss in one single training stage, a contrastive loss aids to differentiate between salient anatomical regions that conform to the available annotations. Our approach builds upon the work of Jabri et al. (2020), who proposed cyclical contrastive random walks (CCRW) for self-supervision on palindromes of video frames. We adapt this scheme to operate on entries of paired embedded image slices. Using paths of cyclical random walks bypasses the need for negative samples, as commonly used in contrastive approaches, enabling the algorithm to discriminate among relevant salient (anatomical) regions implicitly. Further, a multi-level supervision strategy is employed, ensuring adequate representations of local and global characteristics of anatomical structures. The effectiveness of reducing the amount of required annotations is shown on three MRI datasets. A median increase of 8.01 and 5.90 pp in the Dice Similarity Coefficient (DSC) compared to our baseline could be achieved across all three datasets in the case of one and two available annotated examples per dataset.

Dual encoder network with transformer-CNN for multi-organ segmentation

Medical image segmentation is a critical step in many imaging applications. Automatic segmentation has gained extensive concern using a convolutional neural network (CNN). However, the traditional CNN-based methods fail to extract global and long-range contextual information due to local convolution operation. Transformer overcomes the limitation of CNN-based models. Inspired by the success of transformers in computer vision (CV), many researchers focus on designing the transformer-based U-shaped method in medical image segmentation. The transformer-based approach cannot effectively capture the fine-grained details. This paper proposes a dual encoder network with transformer-CNN for multi-organ segmentation. The new segmentation framework takes full advantage of CNN and transformer to enhance the segmentation accuracy. The Swin-transformer encoder extracts global information, and the CNN encoder captures local information. We introduce fusion modules to fuse convolutional features and the sequence of features from the transformer. Feature fusion is concatenated through the skip connection to smooth the decision boundary effectively. We extensively evaluate our method on the synapse multi-organ CT dataset and the automated cardiac diagnosis challenge (ACDC) dataset. The results demonstrate that the proposed method achieves Dice similarity coefficient (DSC) metrics of 80.68% and 91.12% on the synapse multi-organ CT and ACDC datasets, respectively. We perform the ablation studies on the ACDC dataset, demonstrating the effectiveness of critical components of our method. Our results match the ground-truth boundary more consistently than the existing models. Our approach gains more accurate results on challenging 2D images for multi-organ segmentation. Compared with the state-of-the-art methods, our proposed method achieves superior performance in multi-organ segmentation tasks. Graphical Abstract The key process in medical image segmentation.

A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast

One of the limiting factors for the development and adoption of novel deep-learning (DL) based medical image analysis methods is the scarcity of labeled medical images. Medical image simulation and synthesis can provide solutions by generating ample training data with corresponding ground truth labels. Despite recent advances, generated images demonstrate limited realism and diversity. In this work, we develop a flexible framework for simulating cardiac magnetic resonance (MR) images with variable anatomical and imaging characteristics for the purpose of creating a diversified virtual population. We advance previous works on both cardiac MR image simulation and anatomical modeling to increase the realism in terms of both image appearance and underlying anatomy. To diversify the generated images, we define parameters: 1)to alter the anatomy, 2) to assign MR tissue properties to various tissue types, and 3) to manipulate the image contrast via acquisition parameters. The proposed framework is optimized to generate a substantial number of cardiac MR images with ground truth labels suitable for downstream supervised tasks. A database of virtual subjects is simulated and its usefulness for aiding a DL segmentation method is evaluated. Our experiments show that training completely with simulated images can perform comparable with a model trained with real images for heart cavity segmentation in mid-ventricular slices. Moreover, such data can be used in addition to classical augmentation for boosting the performance when training data is limited, particularly by increasing the contrast and anatomical variation, leading to better regularization and generalization. The database is publicly available at https://osf.io/bkzhm/ and the simulation code will be available at https://github.com/sinaamirrajab/CMRI.

MyI-Net: Fully Automatic Detection and Quantification of Myocardial Infarction from Cardiovascular MRI Images

Myocardial infarction (MI) occurs when an artery supplying blood to the heart is abruptly occluded. The "gold standard" method for imaging MI is cardiovascular magnetic resonance imaging (MRI) with intravenously administered gadolinium-based contrast (with damaged areas apparent as late gadolinium enhancement [LGE]). However, no "gold standard" fully automated method for the quantification of MI exists. In this work, we propose an end-to-end fully automatic system (MyI-Net) for the detection and quantification of MI in MRI images. It has the potential to reduce uncertainty due to technical variability across labs and the inherent problems of data and labels. Our system consists of four processing stages designed to maintain the flow of information across scales. First, features from raw MRI images are generated using feature extractors built on ResNet and MoblieNet architectures. This is followed by atrous spatial pyramid pooling (ASPP) to produce spatial information at different scales to preserve more image context. High-level features from ASPP and initial low-level features are concatenated at the third stage and then passed to the fourth stage where spatial information is recovered via up-sampling to produce final image segmentation output into: (i) background, (ii) heart muscle, (iii) blood and (iv) LGE areas. Our experiments show that the model named MI-ResNet50-AC provides the best global accuracy (97.38%), mean accuracy (86.01%), weighted intersection over union (IoU) of 96.47%, and bfscore of 64.46% for the global segmentation. However, in detecting only LGE tissue, a smaller model, MI-ResNet18-AC, exhibited higher accuracy (74.41%) than MI-ResNet50-AC (64.29%). New models were compared with state-of-the-art models and manual quantification. Our models demonstrated favorable performance in global segmentation and LGE detection relative to the state-of-the-art, including a four-fold better performance in matching LGE pixels to contours produced by clinicians.

Image-based estimation of the left ventricular cavity volume using deep learning and Gaussian process with cardio-mechanical applications

In this investigation, an image-based method has been developed to estimate the volume of the left ventricular cavity using cardiac magnetic resonance (CMR) imaging data. Deep learning and Gaussian processes have been applied to bring the estimations closer to the cavity volumes manually extracted. CMR data from 339 patients and healthy volunteers have been used to train a stepwise regression model that can estimate the volume of the left ventricular cavity at the beginning and end of diastole. We have decreased the root mean square error (RMSE) of cavity volume estimation approximately from 13 to 8 ml compared to the common practice in the literature. Considering the RMSE of manual measurements is approximately 4 ml on the same dataset, 8 ml of error is notable for a fully automated estimation method, which needs no supervision or user-hours once it has been trained. Additionally, to demonstrate a clinically relevant application of automatically estimated volumes, we inferred the passive material properties of the myocardium given the volume estimates using a well-validated cardiac model. These material properties can be further used for patient treatment planning and diagnosis.

Automatic uncertainty-based quality controlled T1 mapping and ECV analysis from native and post-contrast cardiac T1 mapping images using Bayesian vision transformer

Deep learning-based methods for cardiac MR segmentation have achieved state-of-the-art results. However, these methods can generate incorrect segmentation results which can lead to wrong clinical decisions in the downstream tasks. Automatic and accurate analysis of downstream tasks, such as myocardial tissue characterization, is highly dependent on the quality of the segmentation results. Therefore, it is of paramount importance to use quality control methods to detect the failed segmentations before further analysis. In this work, we propose a fully automatic uncertainty-based quality control framework for T1 mapping and extracellular volume (ECV) analysis. The framework consists of three parts. The first one focuses on segmentation of cardiac structures from a native and post-contrast T1 mapping dataset (n=295) using a Bayesian Swin transformer-based U-Net. In the second part, we propose a novel uncertainty-based quality control (QC) to detect inaccurate segmentation results. The QC method utilizes image-level uncertainty features as input to a random forest-based classifier/regressor to determine the quality of the segmentation outputs. The experimental results from four different types of segmentation results show that the proposed QC method achieves a mean area under the ROC curve (AUC) of 0.927 on binary classification and a mean absolute error (MAE) of 0.021 on Dice score regression, significantly outperforming other state-of-the-art uncertainty based QC methods. The performance gap is notably higher in predicting the segmentation quality from poor-performing models which shows the robustness of our method in detecting failed segmentations. After the inaccurate segmentation results are detected and rejected by the QC method, in the third part, T1 mapping and ECV values are computed automatically to characterize the myocardial tissues of healthy and cardiac pathological cases. The native myocardial T1 and ECV values computed from automatic and manual segmentations show an excellent agreement yielding Pearson coefficients of 0.990 and 0.975 (on the combined validation and test sets), respectively. From the results, we observe that the automatically computed myocardial T1 and ECV values have the ability to characterize myocardial tissues of healthy and cardiac diseases like myocardial infarction, amyloidosis, Tako-Tsubo syndrome, dilated cardiomyopathy, and hypertrophic cardiomyopathy.

Reviewing Federated Machine Learning and Its Use in Diseases Prediction

Machine learning (ML) has succeeded in improving our daily routines by enabling automation and improved decision making in a variety of industries such as healthcare, finance, and transportation, resulting in increased efficiency and production. However, the development and widespread use of this technology has been significantly hampered by concerns about data privacy, confidentiality, and sensitivity, particularly in healthcare and finance. The "data hunger" of ML describes how additional data can increase performance and accuracy, which is why this question arises. Federated learning (FL) has emerged as a technology that helps solve the privacy problem by eliminating the need to send data to a primary server and collect it where it is processed and the model is trained. To maintain privacy and improve model performance, FL shares parameters rather than data during training, in contrast to the typical ML practice of sending user data during model development. Although FL is still in its infancy, there are already applications in various industries such as healthcare, finance, transportation, and others. In addition, 32% of companies have implemented or plan to implement federated learning in the next 12-24 months, according to the latest figures from KPMG, which forecasts an increase in investment in this area from USD 107 million in 2020 to USD 538 million in 2025. In this context, this article reviews federated learning, describes it technically, differentiates it from other technologies, and discusses current FL aggregation algorithms. It also discusses the use of FL in the diagnosis of cardiovascular disease, diabetes, and cancer. Finally, the problems hindering progress in this area and future strategies to overcome these limitations are discussed in detail.

Artificial Intelligence in Cardiovascular CT and MR Imaging

The technological development of Artificial Intelligence (AI) has grown rapidly in recent years. The applications of AI to cardiovascular imaging are various and could improve the radiologists' workflow, speeding up acquisition and post-processing time, increasing image quality and diagnostic accuracy. Several studies have already proved AI applications in Coronary Computed Tomography Angiography and Cardiac Magnetic Resonance, including automatic evaluation of calcium score, quantification of coronary stenosis and plaque analysis, or the automatic quantification of heart volumes and myocardial tissue characterization. The aim of this review is to summarize the latest advances in the field of AI applied to cardiovascular CT and MR imaging.

Semi-Supervised Medical Image Segmentation Guided by Bi-Directional Constrained Dual-Task Consistency

BACKGROUND

Medical image processing tasks represented by multi-object segmentation are of great significance for surgical planning, robot-assisted surgery, and surgical safety. However, the exceptionally low contrast among tissues and limited available annotated data makes developing an automatic segmentation algorithm for pelvic CT challenging.

METHODS

A bi-direction constrained dual-task consistency model named PICT is proposed to improve segmentation quality by leveraging free unlabeled data. First, to learn more unmarked data features, it encourages the model prediction of the interpolated image to be consistent with the interpolation of the model prediction at the pixel, model, and data levels. Moreover, to constrain the error prediction of interpolation interference, PICT designs an auxiliary pseudo-supervision task that focuses on the underlying information of non-interpolation data. Finally, an effective loss algorithm for both consistency tasks is designed to ensure the complementary manner and produce more reliable predictions.

RESULTS

Quantitative experiments show that the proposed PICT achieves 87.18%, 96.42%, and 79.41% mean DSC score on ACDC, CTPelvic1k, and the individual Multi-tissue Pelvis dataset with gains of around 0.8%, 0.5%, and 1% compared to the state-of-the-art semi-supervised method. Compared to the baseline supervised method, the PICT brings over 3-9% improvements.

CONCLUSIONS

The developed PICT model can effectively leverage unlabeled data to improve segmentation quality of low contrast medical images. The segmentation result could improve the precision of surgical path planning and provide input for robot-assisted surgery.

Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging

Despite technological and medical advances, the detection, interpretation, and treatment of cancer based on imaging data continue to pose significant challenges. These include inter-observer variability, class imbalance, dataset shifts, inter- and intra-tumour heterogeneity, malignancy determination, and treatment effect uncertainty. Given the recent advancements in image synthesis, Generative Adversarial Networks (GANs), and adversarial training, we assess the potential of these technologies to address a number of key challenges of cancer imaging. We categorise these challenges into (a) data scarcity and imbalance, (b) data access and privacy, (c) data annotation and segmentation, (d) cancer detection and diagnosis, and (e) tumour profiling, treatment planning and monitoring. Based on our analysis of 164 publications that apply adversarial training techniques in the context of cancer imaging, we highlight multiple underexplored solutions with research potential. We further contribute the Synthesis Study Trustworthiness Test (SynTRUST), a meta-analysis framework for assessing the validation rigour of medical image synthesis studies. SynTRUST is based on 26 concrete measures of thoroughness, reproducibility, usefulness, scalability, and tenability. Based on SynTRUST, we analyse 16 of the most promising cancer imaging challenge solutions and observe a high validation rigour in general, but also several desirable improvements. With this work, we strive to bridge the gap between the needs of the clinical cancer imaging community and the current and prospective research on data synthesis and adversarial networks in the artificial intelligence community.

On the usability of synthetic data for improving the robustness of deep learning-based segmentation of cardiac magnetic resonance images

Deep learning-based segmentation methods provide an effective and automated way for assessing the structure and function of the heart in cardiac magnetic resonance (CMR) images. However, despite their state-of-the-art performance on images acquired from the same source (same scanner or scanner vendor) as images used during training, their performance degrades significantly on images coming from different domains. A straightforward approach to tackle this issue consists of acquiring large quantities of multi-site and multi-vendor data, which is practically infeasible. Generative adversarial networks (GANs) for image synthesis present a promising solution for tackling data limitations in medical imaging and addressing the generalization capability of segmentation models. In this work, we explore the usability of synthesized short-axis CMR images generated using a segmentation-informed conditional GAN, to improve the robustness of heart cavity segmentation models in a variety of different settings. The GAN is trained on paired real images and corresponding segmentation maps belonging to both the heart and the surrounding tissue, reinforcing the synthesis of semantically-consistent and realistic images. First, we evaluate the segmentation performance of a model trained solely with synthetic data and show that it only slightly underperforms compared to the baseline trained with real data. By further combining real with synthetic data during training, we observe a substantial improvement in segmentation performance (up to 4% and 40% in terms of Dice score and Hausdorff distance) across multiple data-sets collected from various sites and scanner. This is additionally demonstrated across state-of-the-art 2D and 3D segmentation networks, whereby the obtained results demonstrate the potential of the proposed method in tackling the presence of the domain shift in medical data. Finally, we thoroughly analyze the quality of synthetic data and its ability to replace real MR images during training, as well as provide an insight into important aspects of utilizing synthetic images for segmentation.

Myocardial Segmentation of Tagged Magnetic Resonance Images with Transfer Learning Using Generative Cine-To-Tagged Dataset Transformation

The use of deep learning (DL) segmentation in cardiac MRI has the potential to streamline the radiology workflow, particularly for the measurement of myocardial strain. Recent efforts in DL motion tracking models have drastically reduced the time needed to measure the heart's displacement field and the subsequent myocardial strain estimation. However, the selection of initial myocardial reference points is not automated and still requires manual input from domain experts. Segmentation of the myocardium is a key step for initializing reference points. While high-performing myocardial segmentation models exist for cine images, this is not the case for tagged images. In this work, we developed and compared two novel DL models (nnU-net and Segmentation ResNet VAE) for the segmentation of myocardium from tagged CMR images. We implemented two methods to transform cardiac cine images into tagged images, allowing us to leverage large public annotated cine datasets. The cine-to-tagged methods included (i) a novel physics-driven transformation model, and (ii) a generative adversarial network (GAN) style transfer model. We show that pretrained models perform better (+2.8 Dice coefficient percentage points) and converge faster (6×) than models trained from scratch. The best-performing method relies on a pretraining with an unpaired, unlabeled, and structure-preserving generative model trained to transform cine images into their tagged-appearing equivalents. Our state-of-the-art myocardium segmentation network reached a Dice coefficient of 0.828 and 95th percentile Hausdorff distance of 4.745 mm on a held-out test set. This performance is comparable to existing state-of-the-art segmentation networks for cine images.

Dilated convolution network with edge fusion block and directional feature maps for cardiac MRI segmentation

Cardiac magnetic resonance imaging (MRI) segmentation task refers to the accurate segmentation of ventricle and myocardium, which is a prerequisite for evaluating the soundness of cardiac function. With the development of deep learning in medical imaging, more and more heart segmentation methods based on deep learning have been proposed. Due to the fuzzy boundary and uneven intensity distribution of cardiac MRI, some existing methods do not make full use of multi-scale characteristic information and have the problem of ambiguity between classes. In this paper, we propose a dilated convolution network with edge fusion block and directional feature maps for cardiac MRI segmentation. The network uses feature fusion module to preserve boundary information, and adopts the direction field module to obtain the feature maps to improve the original segmentation features. Firstly, multi-scale feature information is obtained and fused through dilated convolutional layers of different scales while downsampling. Secondly, in the decoding stage, the edge fusion block integrates the edge features into the side output of the encoder and concatenates them with the upsampled features. Finally, the concatenated features utilize the direction field to improve the original segmentation features and generate the final result. Our propose method conducts comprehensive comparative experiments on the automated cardiac diagnosis challenge (ACDC) and myocardial pathological segmentation (MyoPS) datasets. The results show that the proposed cardiac MRI segmentation method has better performance compared to other existing methods.

Cross-convolutional transformer for automated multi-organs segmentation in a variety of medical images

Objective.It is a huge challenge for multi-organs segmentation in various medical images based on a consistent algorithm with the development of deep learning methods. We therefore develop a deep learning method based on cross-convolutional transformer for these automated- segmentation to obtain better generalization and accuracy.Approach.We propose a cross-convolutional transformer network (C2Former) to solve the segmentation problem. Specifically, we first redesign a novel cross-convolutional self-attention mechanism in terms of the algorithm to integrate local and global contexts and model long-distance and short-distance dependencies to enhance the semantic feature understanding of images. Then multi-scale feature edge fusion module is proposed to combine the image edge features, which effectively form multi-scale feature streams and establish reliable relational connections in the global context. Finally, we use three different modalities, imaging three different anatomical regions to train and test multi organs and evaluate segmentation performance.Main results.We use the evaluation metrics of Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) for each dataset. Experiments showed the average DSC of 83.22% and HD95 of 17.55 mm on the Synapse dataset (CT images of abdominal multi-organ), the average DSC of 91.42% and HD95 of 1.06 mm on the ACDC dataset (MRI of cardiac substructures) and the average DSC of 86.78% and HD95 of 16.85 mm on the ISIC 2017 dataset (skin cancer images). In each dataset, our proposed method consistently outperforms the compared networks.Significance.The proposed deep learning network provides a generalized and accurate solution method for multi-organ segmentation in the three different datasets. It has the potential to be applied to a variety of medical datasets for structural segmentation.

Deep learning can yield clinically useful right ventricular segmentations faster than fully manual analysis

Right ventricular (RV) volumes are commonly obtained through time-consuming manual delineations of cardiac magnetic resonance (CMR) images. Deep learning-based methods can generate RV delineations, but few studies have assessed their ability to accelerate clinical practice. Therefore, we aimed to develop a clinical pipeline for deep learning-based RV delineations and validate its ability to reduce the manual delineation time. Quality-controlled delineations in short-axis CMR scans from 1114 subjects were used for development. Time reduction was assessed by two observers using 50 additional clinical scans. Automated delineations were subjectively rated as (A) sufficient for clinical use, or as needing (B) minor or (C) major corrections. Times were measured for manual corrections of delineations rated as B or C, and for fully manual delineations on all 50 scans. Fifty-eight % of automated delineations were rated as A, 42% as B, and none as C. The average time was 6 min for a fully manual delineation, 2 s for an automated delineation, and 2 min for a minor correction, yielding a time reduction of 87%. The deep learning-based pipeline could substantially reduce the time needed to manually obtain clinically applicable delineations, indicating ability to yield right ventricular assessments faster than fully manual analysis in clinical practice. However, these results may not generalize to clinics using other RV delineation guidelines.

Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients

Scar quantification on cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in risk stratifying patients with hypertrophic cardiomyopathy (HCM) due to the importance of scar burden in predicting clinical outcomes. We aimed to develop a machine learning (ML) model that contours left ventricular (LV) endo- and epicardial borders and quantifies CMR LGE images from HCM patients.We retrospectively studied 2557 unprocessed images from 307 HCM patients followed at the University Health Network (Canada) and Tufts Medical Center (USA). LGE images were manually segmented by two experts using two different software packages. Using 6SD LGE intensity cutoff as the gold standard, a 2-dimensional convolutional neural network (CNN) was trained on 80% and tested on the remaining 20% of the data. Model performance was evaluated using the Dice Similarity Coefficient (DSC), Bland-Altman, and Pearson's correlation. The 6SD model DSC scores were good to excellent at 0.91 ± 0.04, 0.83 ± 0.03, and 0.64 ± 0.09 for the LV endocardium, epicardium, and scar segmentation, respectively. The bias and limits of agreement for the percentage of LGE to LV mass were low (-0.53 ± 2.71%), and correlation high (r = 0.92). This fully automated interpretable ML algorithm allows rapid and accurate scar quantification from CMR LGE images. This program does not require manual image pre-processing, and was trained with multiple experts and software, increasing its generalizability.

Automatic Cerebral Hemisphere Segmentation in Rat MRI with Ischemic Lesions via Attention-based Convolutional Neural Networks

We present MedicDeepLabv3+, a convolutional neural network that is the first completely automatic method to segment cerebral hemispheres in magnetic resonance (MR) volumes of rats with ischemic lesions. MedicDeepLabv3+ improves the state-of-the-art DeepLabv3+ with an advanced decoder, incorporating spatial attention layers and additional skip connections that, as we show in our experiments, lead to more precise segmentations. MedicDeepLabv3+ requires no MR image preprocessing, such as bias-field correction or registration to a template, produces segmentations in less than a second, and its GPU memory requirements can be adjusted based on the available resources. We optimized MedicDeepLabv3+ and six other state-of-the-art convolutional neural networks (DeepLabv3+, UNet, HighRes3DNet, V-Net, VoxResNet, Demon) on a heterogeneous training set comprised by MR volumes from 11 cohorts acquired at different lesion stages. Then, we evaluated the trained models and two approaches specifically designed for rodent MRI skull stripping (RATS and RBET) on a large dataset of 655 MR rat brain volumes. In our experiments, MedicDeepLabv3+ outperformed the other methods, yielding an average Dice coefficient of 0.952 and 0.944 in the brain and contralateral hemisphere regions. Additionally, we show that despite limiting the GPU memory and the training data, our MedicDeepLabv3+ also provided satisfactory segmentations. In conclusion, our method, publicly available at https://github.com/jmlipman/MedicDeepLabv3Plus , yielded excellent results in multiple scenarios, demonstrating its capability to reduce human workload in rat neuroimaging studies.

Hybrid-scale contextual fusion network for medical image segmentation

Medical image segmentation result is an essential reference for disease diagnosis. Recently, with the development and application of convolutional neural networks, medical image processing has significantly developed. However, most existing automatic segmentation tasks are still challenging due to various positions, sizes, and shapes, resulting in poor segmentation performance. In addition, most of the current methods use the encoder-decoder architecture for feature extraction, focusing on the acquisition of semantic information but ignoring the specific target and global context information. In this work, we propose a hybrid-scale contextual fusion network to capture the richer spatial and semantic information. First, a hybrid-scale embedding layer (HEL) is employed before the transformer. By mixing each embedding with multiple patches, the object information of different scales can be captured availably. Further, we present a standard transformer to model long-range dependencies in the first two skip connections. Meanwhile, the pooling transformer (PTrans) is employed to handle long input sequences in the following two skip connections. By leveraging the global average pooling operation and the corresponding transformer block, the spatial structure information of the target will be learned effectively. In the last, dual-branch channel attention module (DCA) is proposed to focus on crucial channel features and conduct multi-level features fusion simultaneously. By utilizing the fusion scheme, richer context and fine-grained features are captured and encoded efficiently. Extensive experiments on three public datasets demonstrate that the proposed method outperforms state-of-the-art methods.

A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR

Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss functions, ignorant of the spatially extended features that characterise anatomy. Therefore, whilst sharing a high spatial overlap with the ground truth, inferred CNN-based segmentations can lack coherence, including spurious connected components, holes and voids. Such results are implausible, violating anticipated anatomical topology. In response, (single-class) persistent homology-based loss functions have been proposed to capture global anatomical features. Our work extends these approaches to the task of multi-class segmentation. Building an enriched topological description of all class labels and class label pairs, our loss functions make predictable and statistically significant improvements in segmentation topology using a CNN-based post-processing framework. We also present (and make available) a highly efficient implementation based on cubical complexes and parallel execution, enabling practical application within high resolution 3D data for the first time. We demonstrate our approach on 2D short axis and 3D whole heart CMR segmentation, advancing a detailed and faithful analysis of performance on two publicly available datasets.

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning

Background

Radiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task.

Purpose

The purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC.

Materials and methods

Contrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient (Dice), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs.

Results

CNN models trained from scratch on canine data or by using transfer learning obtained mean test set Dice scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean Dice performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set Dice scores of 0.69 for both approaches.

Conclusion

In conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients.

Hierarchical volumetric transformer with comprehensive attention for medical image segmentation

Transformer is widely used in medical image segmentation tasks due to its powerful ability to model global dependencies. However, most of the existing transformer-based methods are two-dimensional networks, which are only suitable for processing two-dimensional slices and ignore the linguistic association between different slices of the original volume image blocks. To solve this problem, we propose a novel segmentation framework by deeply exploring the respective characteristic of convolution, comprehensive attention mechanism, and transformer, and assembling them hierarchically to fully exploit their complementary advantages. Specifically, we first propose a novel volumetric transformer block to help extract features serially in the encoder and restore the feature map resolution to the original level in parallel in the decoder. It can not only obtain the information of the plane, but also make full use of the correlation information between different slices. Then the local multi-channel attention block is proposed to adaptively enhance the effective features of the encoder branch at the channel level, while suppressing the invalid features. Finally, the global multi-scale attention block with deep supervision is introduced to adaptively extract valid information at different scale levels while filtering out useless information. Extensive experiments demonstrate that our proposed method achieves promising performance on multi-organ CT and cardiac MR image segmentation.

Generative myocardial motion tracking via latent space exploration with biomechanics-informed prior

Myocardial motion and deformation are rich descriptors that characterize cardiac function. Image registration, as the most commonly used technique for myocardial motion tracking, is an ill-posed inverse problem which often requires prior assumptions on the solution space. In contrast to most existing approaches which impose explicit generic regularization such as smoothness, in this work we propose a novel method that can implicitly learn an application-specific biomechanics-informed prior and embed it into a neural network-parameterized transformation model. Particularly, the proposed method leverages a variational autoencoder-based generative model to learn a manifold for biomechanically plausible deformations. The motion tracking then can be performed via traversing the learnt manifold to search for the optimal transformations while considering the sequence information. The proposed method is validated on three public cardiac cine MRI datasets with comprehensive evaluations. The results demonstrate that the proposed method can outperform other approaches, yielding higher motion tracking accuracy with reasonable volume preservation and better generalizability to varying data distributions. It also enables better estimates of myocardial strains, which indicates the potential of the method in characterizing spatiotemporal signatures for understanding cardiovascular diseases.

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.