Fully­automated deep­learning segmentation of pediatric cardiovascular magnetic resonance of patients with complex congenital heart diseases.

BACKGROUND: For the growing patient population with congenital heart disease (CHD), improving clinical workflow, accuracy of diagnosis, and efficiency of analyses are considered unmet clinical needs. Cardiovascular magnetic resonance (CMR) imaging offers non-invasive and non-ionizing assessment of CHD patients. However, although CMR data facilitates reliable analysis of cardiac function and anatomy, clinical workflow mostly relies on manual analysis of CMR images, which is time consuming. Thus, an automated and accurate segmentation platform exclusively dedicated to pediatric CMR images can significantly improve the clinical workflow, as the present work aims to establish. METHODS: Training artificial intelligence (AI) algorithms for CMR analysis requires large annotated datasets, which are not readily available for pediatric subjects and particularly in CHD patients. To mitigate this issue, we devised a novel method that uses a generative adversarial network (GAN) to synthetically augment the training dataset via generating synthetic CMR images and their corresponding chamber segmentations. In addition, we trained and validated a deep fully convolutional network (FCN) on a dataset, consisting of [Formula: see text] pediatric subjects with complex CHD, which we made publicly available. Dice metric, Jaccard index and Hausdorff distance as well as clinically-relevant volumetric indices are reported to assess and compare our platform with other algorithms including U-Net and cvi42, which is used in clinics. RESULTS: For congenital CMR dataset, our FCN model yields an average Dice metric of [Formula: see text] and [Formula: see text] for LV at end-diastole and end-systole, respectively, and [Formula: see text] and [Formula: see text] for RV at end-diastole and end-systole, respectively. Using the same dataset, the cvi42, resulted in [Formula: see text], [Formula: see text], [Formula: see text] and [Formula: see text] for LV and RV at end-diastole and end-systole, and the U-Net architecture resulted in [Formula: see text], [Formula: see text], [Formula: see text] and [Formula: see text] for LV and RV at end-diastole and end-systole, respectively. CONCLUSIONS: The chambers' segmentation results from our fully-automated method showed strong agreement with manual segmentation and no significant statistical difference was found by two independent statistical analyses. Whereas cvi42 and U-Net segmentation results failed to pass the t-test. Relying on these outcomes, it can be inferred that by taking advantage of GANs, our method is clinically relevant and can be used for pediatric and congenital CMR segmentation and analysis.

Generalizable fully automated multi-label segmentation of four-chamber view echocardiograms based on deep convolutional adversarial networks.

A major issue in translation of the artificial intelligence platforms for automatic segmentation of echocardiograms to clinics is their generalizability. The present study introduces and verifies a novel generalizable and efficient fully automatic multi-label segmentation method for four-chamber view echocardiograms based on deep fully convolutional networks (FCNs) and adversarial training. For the first time, we used generative adversarial networks for pixel classification training, a novel method in machine learning not currently used for cardiac imaging, to overcome the generalization problem. The method's performance was validated against manual segmentations as the ground-truth. Furthermore, to verify our method's generalizability in comparison with other existing techniques, we compared our method's performance with a state-of-the-art method on our dataset in addition to an independent dataset of 450 patients from the CAMUS (cardiac acquisitions for multi-structure ultrasound segmentation) challenge. On our test dataset, automatic segmentation of all four chambers achieved a dice metric of 92.1%, 86.3%, 89.6% and 91.4% for LV, RV, LA and RA, respectively. LV volumes' correlation between automatic and manual segmentation were 0.94 and 0.93 for end-diastolic volume and end-systolic volume, respectively. Excellent agreement with chambers' reference contours and significant improvement over previous FCN-based methods suggest that generative adversarial networks for pixel classification training can effectively design generalizable fully automatic FCN-based networks for four-chamber segmentation of echocardiograms even with limited number of training data.

Artificial intelligence in pediatric and adult congenital cardiac MRI: an unmet clinical need.

Cardiac MRI (CMR) allows non-invasive, non-ionizing assessment of cardiac function and anatomy in patients with congenital heart disease (CHD). The utility of CMR as a non-invasive imaging tool for evaluation of CHD have been growing exponentially over the past decade. The algorithms based on artificial intelligence (AI), and in particular, deep learning, have rapidly become a methodology of choice for analyzing CMR. A wide range of applications for AI have been developed to tackle challenges in various aspects of CMR, and significant advances have also been made from image acquisition to image analysis and diagnosis. We include an overview of AI definitions, different architectures, and details on well-known methods. This paper reviews the major deep learning concepts used for analyses of patients with CHD. In the end, we have summarized a list of open challenges and concerns to be considered for future studies.

Automatic segmentation of the right ventricle from cardiac MRI using a learning-based approach.

PURPOSE: This study aims to accurately segment the right ventricle (RV) from cardiac MRI using a fully automatic learning-based method. METHODS: The proposed method uses deep learning algorithms, i.e., convolutional neural networks and stacked autoencoders, for automatic detection and initial segmentation of the RV chamber. The initial segmentation is then combined with the deformable models to improve the accuracy and robustness of the process. We trained our algorithm using 16 cardiac MRI datasets of the MICCAI 2012 RV Segmentation Challenge database and validated our technique using the rest of the dataset (32 subjects). RESULTS: An average Dice metric of 82.5% along with an average Hausdorff distance of 7.85 mm were achieved for all the studied subjects. Furthermore, a high correlation and level of agreement with the ground truth contours for end-diastolic volume (0.98), end-systolic volume (0.99), and ejection fraction (0.93) were observed. CONCLUSION: Our results show that deep learning algorithms can be effectively used for automatic segmentation of the RV. Computed quantitative metrics of our method outperformed that of the existing techniques participated in the MICCAI 2012 challenge, as reported by the challenge organizers. Magn Reson Med 78:2439-2448, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

A 3-D Active Contour Method for Automated Segmentation of the Left Ventricle From Magnetic Resonance Images.

OBJECTIVE: This study's objective is to develop and validate a fast automated 3-D segmentation method for cardiac magnetic resonance imaging (MRI). The segmentation algorithm automatically reconstructs cardiac MRI DICOM data into a 3-D model (i.e., direct volumetric segmentation), without relying on prior statistical knowledge. METHODS: A novel 3-D active contour method was employed to detect the left ventricular cavity in 33 subjects with heterogeneous heart diseases from the York University database. Papillary muscles were identified and added to the chamber using a convex hull of the left ventricle and interpolation. The myocardium was then segmented using a similar 3-D segmentation method according to anatomic information. A multistage approach was taken to determine the method's efficacy. RESULTS: Our method demonstrated a significant improvement in segmentation performance when compared to manual segmentation and other automated methods. CONCLUSION AND SIGNIFICANCE: A true 3-D reconstruction technique without the need for training datasets or any user-driven segmentation has been developed. In this method, a novel combination of internal and external energy terms for active contour was utilized that exploits histogram matching for improving the segmentation performance. This method takes advantage of full volumetric imaging, does not rely on prior statistical knowledge, and employs a convex-hull interpolation to include the papillary muscles.

A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI.

Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are used to infer the LV shape. The inferred shape is incorporated into deformable models to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2-95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively.

Full-reference quality estimation for images with different spatial resolutions.

Multimedia communication is becoming pervasive because of the progress in wireless communications and multimedia coding. Estimating the quality of the visual content accurately is crucial in providing satisfactory service. State of the art visual quality assessment approaches are effective when the input image and reference image have the same resolution. However, finding the quality of an image that has spatial resolution different than that of the reference image is still a challenging problem. To solve this problem, we develop a quality estimator (QE), which computes the quality of the input image without resampling the reference or the input images. In this paper, we begin by identifying the potential weaknesses of previous approaches used to estimate the quality of experience. Next, we design a QE to estimate the quality of a distorted image with a lower resolution compared with the reference image. We also propose a subjective test environment to explore the success of the proposed algorithm in comparison with other QEs. When the input and test images have different resolutions, the subjective tests demonstrate that in most cases the proposed method works better than other approaches. In addition, the proposed algorithm also performs well when the reference image and the test image have the same resolution.

Power optimization of wireless media systems with space-time block codes.

We present analytical and numerical solutions to the problem of power control in wireless media systems with multiple antennas. We formulate a set of optimization problems aimed at minimizing total power consumption of wireless media systems subject to a given level of QoS and an available bit rate. Our formulation takes into consideration the power consumption related to source coding, channel coding, and transmission of multiple-transmit antennas. In our study, we consider Gauss-Markov and video source models, Rayleigh fading channels along with the Bernoulli/Gilbert-Elliott loss models, and space-time block codes.