Arrhythmic sudden death survival prediction using deep learning analysis of scarring in the heart.

Sudden cardiac death from arrhythmia is a major cause of mortality worldwide. Here, we develop a novel deep learning (DL) approach that blends neural networks and survival analysis to predict patient-specific survival curves from contrast-enhanced cardiac magnetic resonance images and clinical covariates for patients with ischemic heart disease. The DL-predicted survival curves offer accurate predictions at times up to 10 years and allow for estimation of uncertainty in predictions. The performance of this learning architecture was evaluated on multi-center internal validation data and tested on an independent test set, achieving concordance index of 0.83 and 0.74, and 10-year integrated Brier score of 0.12 and 0.14. We demonstrate that our DL approach with only raw cardiac images as input outperforms standard survival models constructed using clinical covariates. This technology has the potential to transform clinical decision-making by offering accurate and generalizable predictions of patient-specific survival probabilities of arrhythmic death over time.

Anatomically informed deep learning on contrast-enhanced cardiac magnetic resonance imaging for scar segmentation and clinical feature extraction.

Background: Visualizing fibrosis on cardiac magnetic resonance (CMR) imaging with contrast enhancement (late gadolinium enhancement; LGE) is paramount in characterizing disease progression and identifying arrhythmia substrates. Segmentation and fibrosis quantification from LGE-CMR is intensive, manual, and prone to interobserver variability. There is an unmet need for automated LGE-CMR image segmentation that ensures anatomical accuracy and seamless extraction of clinical features. Objective: This study aimed to develop a novel deep learning solution for analysis of contrast-enhanced CMR images that produces anatomically accurate myocardium and scar/fibrosis segmentations and uses these to calculate features of clinical interest. Methods: Data sources were 155 2-dimensional LGE-CMR patient scans (1124 slices) and 246 synthetic "LGE-like" scans (1360 slices) obtained from cine CMR using a novel style-transfer algorithm. We trained and tested a 3-stage neural network that identified the left ventricle (LV) region of interest (ROI), segmented ROI into viable myocardium and regions of enhancement, and postprocessed the segmentation results to enforce conforming to anatomical constraints. The segmentations were used to directly compute clinical features, such as LV volume and scar burden. Results: Predicted LV and scar segmentations achieved 96% and 75% balanced accuracy, respectively, and 0.93 and 0.57 Dice coefficient when compared to trained expert segmentations. The mean scar burden difference between manual and predicted segmentations was 2%. Conclusion: We developed and validated a deep neural network for automatic, anatomically accurate expert-level LGE- CMR myocardium and scar/fibrosis segmentation, allowing direct calculation of clinical measures. Given the training set heterogeneity, our approach could be extended to multiple imaging modalities and patient pathologies.

Optimal ECG-lead selection increases generalizability of deep learning on ECG abnormality classification.

Deep learning (DL) has achieved promising performance in detecting common abnormalities from the 12-lead electrocardiogram (ECG). However, diagnostic redundancy exists in the 12-lead ECG, which could impose a systematic overfitting on DL, causing poor generalization. We, therefore, hypothesized that finding an optimal lead subset of the 12-lead ECG to eliminate the redundancy would help improve the generalizability of DL-based models. In this study, we developed and evaluated a DL-based model that has a feature extraction stage, an ECG-lead subset selection stage and a decision-making stage to automatically interpret multiple common ECG abnormality types. The data analysed in this study consisted of 6877 12-lead ECG recordings from CPSC 2018 (labelled as normal rhythm or eight types of ECG abnormalities, split into training (approx. 80%), validation (approx. 10%) and test (approx. 10%) sets) and 3998 12-lead ECG recordings from PhysioNet/CinC 2020 (labelled as normal rhythm or four types of ECG abnormalities, used as external text set). The ECG-lead subset selection module was introduced within the proposed model to efficiently constrain model complexity. It detected an optimal 4-lead ECG subset consisting of leads II, aVR, V1 and V4. The proposed model using the optimal 4-lead subset significantly outperformed the model using the complete 12-lead ECG on the validation set and on the external test dataset. The results demonstrated that our proposed model successfully identified an optimal subset of 12-lead ECG; the resulting 4-lead ECG subset improves the generalizability of the DL model in ECG abnormality interpretation. This study provides an outlook on what channels are necessary to keep and which ones may be ignored when considering an automated detection system for cardiac ECG abnormalities. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

A machine learning approach for magnetic resonance image-based mouse brain modeling and fast computation in controlled cortical impact.

Computational modeling of the brain is crucial for the study of traumatic brain injury. An anatomically accurate model with refined details could provide the most accurate computational results. However, computational models with fine mesh details could take prolonged computation time that impedes the clinical translation of the models. Therefore, a way to construct a model with low computational cost while maintaining a computational accuracy comparable with that of the high-fidelity model is desired. In this study, we constructed magnetic resonance (MR) image-based finite element (FE) models of a mouse brain for simulations of controlled cortical impact. The anatomical details were kept by mapping each image voxel to a corresponding FE mesh element. We constructed a super-resolution neural network that could produce computational results of a refined FE model with a mesh size of 70 µm from a coarse FE model with a mesh size of 280 µm. The peak signal-to-noise ratio of the reconstructed results was 33.26 dB, while the computational speed was increased by 50-fold. This proof-of-concept study showed that using machine learning techniques, MR image-based computational modeling could be applied and evaluated in a timely fashion. This paved ways for fast FE modeling and computation based on MR images. Results also support the potential clinical applications of MR image-based computational modeling of the human brain in a variety of scenarios such as brain impact and intervention.Graphical abstract MR image-based FE models with different mesh sizes were generated for CCI. The training and testing data sets were computed with 5 different impact locations and 3 different impact velocities. High-resolution strain maps were estimated using a SR neural network with greatly reduced computational cost.

Viscoelastic characterization of injured brain tissue after controlled cortical impact (CCI) using a mouse model.

BACKGROUND: Mechanical properties of the brain tissue are crucial to understand the mechanisms of traumatic brain injury (TBI). Injured brain tissue could induce changes of mechanical properties and anatomical structures. However, limited data is available for the injured tissue. NEW METHOD: We developed a custom-built device to introduce controlled cortical impact (CCI) to brain with controlled impact velocity and direction. A study protocol for measuring the viscoelastic properties of injured brain tissue was also developed. Micro-scale morphological changes of the vasculature were quantified by analyzing confocal images of the brain tissue using CLARITY method. RESULTS: Results showed significant differences of the instantaneous shear modulus of the impact region from different impact angles. However, no significant differences were found for long-term shear modulus by varying the impact angles and velocities. Analysis of the vasculature showed an increased radius of the vessels in the injured tissue compared with that in the control group. COMPARISON WITH EXISTING METHODS: A combination of three different impact velocities and three different impact angles were adopted for producing injury to the brain. In addition, viscoelastic properties were compared between the injured and non-injured regions. The corresponding morphological changes of the vasculature system were also investigated. CONCLUSIONS: The instantaneous shear modulus at the impact region was significantly different for the three impact angles. Compared to that of the control group, increased radius of the vasculature was also observed in the injured brain tissue. Results indicated that the biomechanical and structural changes of the injured tissue were closely related to the impact angles and velocities. Viscoelastic measurements could also help validation of computational models.

Measurement of Intra-Orbital Structures in Normal Chinese Adults Based on a Three-Dimensional Coordinate System.

PURPOSE OF THE STUDY: This study was to establish a three-dimensional (3D) coordinate system and to study the normal dimensions of intra-orbital structures in Chinese adults. MATERIALS AND METHODS: One hundred and forty-five adult Chinese were selected from patients who had undergone cranio-facial computed tomography scans with diagnosis other than orbital or ocular abnormality. An orbital 3D coordinate system was built on the basis of the scans. Morphological variables of intra-orbital structures were measured in this coordinate system. Bilateral symmetry, sexual dimorphism, and correlations between variables were investigated. RESULTS: No evident laterality was found in bilateral intra-orbital structures. The distance from the center of the eyeball to the prechiasmatic groove, the length of the optic nerve, and the thickness of rectus extraocular muscles were larger in males than in females. No sex-related difference was observed in the anteroposterior diameter of the eyeball or the exophthalmometric value. The exophthalmometric value was found to be related to the anteroposterior diameter of the eyeball, whereas the y-coordinate of the center of the eyeball had no correlation with the anteroposterior diameter of the eyeball. The optic nerve length was closely correlated to the distance from the center of the eyeball to the prechiasmatic groove. CONCLUSIONS: The 3D coordinate system and measurement method established in this study can be applied to the standardization of orbital morphometry. The measurements obtained from normal Chinese adults may provide reference values for the morphology of intra-orbital structures.