Perfect prosthetic heart valve: generative design with machine learning, modeling, and optimization.

Majority of modern techniques for creating and optimizing the geometry of medical devices are based on a combination of computer-aided designs and the utility of the finite element method This approach, however, is limited by the number of geometries that can be investigated and by the time required for design optimization. To address this issue, we propose a generative design approach that combines machine learning (ML) methods and optimization algorithms. We evaluate eight different machine learning methods, including decision tree-based and boosting algorithms, neural networks, and ensembles. For optimal design, we investigate six state-of-the-art optimization algorithms, including Random Search, Tree-structured Parzen Estimator, CMA-ES-based algorithm, Nondominated Sorting Genetic Algorithm, Multiobjective Tree-structured Parzen Estimator, and Quasi-Monte Carlo Algorithm. In our study, we apply the proposed approach to study the generative design of a prosthetic heart valve (PHV). The design constraints of the prosthetic heart valve, including spatial requirements, materials, and manufacturing methods, are used as inputs, and the proposed approach produces a final design and a corresponding score to determine if the design is effective. Extensive testing leads to the conclusion that utilizing a combination of ensemble methods in conjunction with a Tree-structured Parzen Estimator or a Nondominated Sorting Genetic Algorithm is the most effective method in generating new designs with a relatively low error rate. Specifically, the Mean Absolute Percentage Error was found to be 11.8% and 10.2% for lumen and peak stress prediction respectively. Furthermore, it was observed that both optimization techniques result in design scores of approximately 95%. From both a scientific and applied perspective, this approach aims to select the most efficient geometry with given input parameters, which can then be prototyped and used for subsequent in vitro experiments. By proposing this approach, we believe it will replace or complement CAD-FEM-based modeling, thereby accelerating the design process and finding better designs within given constraints. The repository, which contains the essential components of the study, including curated source code, dataset, and trained models, is publicly available at https://github.com/ViacheslavDanilov/generative_design.

Use of semi-synthetic data for catheter segmentation improvement.

In the era of data-driven machine learning algorithms, data is the new oil. For the most optimal results, datasets should be large, heterogeneous and, crucially, correctly labeled. However, data collection and labeling are time-consuming and labor-intensive processes. In the field of medical device segmentation, present during minimally invasive surgery, this leads to a lack of informative data. Motivated by this drawback, we developed an algorithm generating semi-synthetic images based on real ones. The concept of this algorithm is to place a randomly shaped catheter in an empty heart cavity, where the shape of the catheter is generated by forward kinematics of continuum robots. Having implemented the proposed algorithm, we generated new images of heart cavities with various artificial catheters. We compared the results of deep neural networks trained purely on real datasets with respect to networks trained on both real and semi-synthetic datasets, highlighting that semi-synthetic data improves catheter segmentation accuracy. A modified U-Net trained on combined datasets performed the segmentation with a Dice similarity coefficient of 92.6 ± 2.2%, while the same model trained only on real images achieved a Dice similarity coefficient of 86.5 ± 3.6%. Therefore, using semi-synthetic data allows for the decrease of accuracy spread, improves model generalization, reduces subjectivity, shortens the labeling routine, increases the number of samples, and improves the heterogeneity.

Cardiovascular and Renal Comorbidities Included into Neural Networks Predict the Outcome in COVID-19 Patients Admitted to an Intensive Care Unit: Three-Center, Cross-Validation, Age- and Sex-Matched Study.

Here, we performed a multicenter, age- and sex-matched study to compare the efficiency of various machine learning algorithms in the prediction of COVID-19 fatal outcomes and to develop sensitive, specific, and robust artificial intelligence tools for the prompt triage of patients with severe COVID-19 in the intensive care unit setting. In a challenge against other established machine learning algorithms (decision trees, random forests, extra trees, neural networks, k-nearest neighbors, and gradient boosting: XGBoost, LightGBM, and CatBoost) and multivariate logistic regression as a reference, neural networks demonstrated the highest sensitivity, sufficient specificity, and excellent robustness. Further, neural networks based on coronary artery disease/chronic heart failure, stage 3-5 chronic kidney disease, blood urea nitrogen, and C-reactive protein as the predictors exceeded 90% sensitivity and 80% specificity, reaching AUROC of 0.866 at primary cross-validation and 0.849 at secondary cross-validation on virtual samples generated by the bootstrapping procedure. These results underscore the impact of cardiovascular and renal comorbidities in the context of thrombotic complications characteristic of severe COVID-19. As aforementioned predictors can be obtained from the case histories or are inexpensive to be measured at admission to the intensive care unit, we suggest this predictor composition is useful for the triage of critically ill COVID-19 patients.

Automatic scoring of COVID-19 severity in X-ray imaging based on a novel deep learning workflow.

In this study, we propose a two-stage workflow used for the segmentation and scoring of lung diseases. The workflow inherits quantification, qualification, and visual assessment of lung diseases on X-ray images estimated by radiologists and clinicians. It requires the fulfillment of two core stages devoted to lung and disease segmentation as well as an additional post-processing stage devoted to scoring. The latter integrated block is utilized, mainly, for the estimation of segment scores and computes the overall severity score of a patient. The models of the proposed workflow were trained and tested on four publicly available X-ray datasets of COVID-19 patients and two X-ray datasets of patients with no pulmonary pathology. Based on a combined dataset consisting of 580 COVID-19 patients and 784 patients with no disorders, our best-performing algorithm is based on a combination of DeepLabV3 + , for lung segmentation, and MA-Net, for disease segmentation. The proposed algorithms' mean absolute error (MAE) of 0.30 is significantly reduced in comparison to established COVID-19 algorithms; BS-net and COVID-Net-S, possessing MAEs of 2.52 and 1.83 respectively. Moreover, the proposed two-stage workflow was not only more accurate but also computationally efficient, it was approximately 11 times faster than the mentioned methods. In summary, we proposed an accurate, time-efficient, and versatile approach for segmentation and scoring of lung diseases illustrated for COVID-19 and with broader future applications for pneumonia, tuberculosis, pneumothorax, amongst others.

Biomaterials Based on Carbon Nanotube Nanocomposites of Poly(styrene-b-isobutylene-b-styrene): The Effect of Nanotube Content on the Mechanical Properties, Biocompatibility and Hemocompatibility.

Nanocomposites based on poly(styrene-block-isobutylene-block-styrene) (SIBS) and single-walled carbon nanotubes (CNTs) were prepared and characterized in terms of tensile strength as well as bio- and hemocompatibility. It was shown that modification of CNTs using dodecylamine (DDA), featured by a long non-polar alkane chain, provided much better dispersion of nanotubes in SIBS as compared to unmodified CNTs. As a result of such modification, the tensile strength of the nanocomposite based on SIBS with low molecular weight (Mn = 40,000 g mol-1) containing 4% of functionalized CNTs was increased up to 5.51 ± 0.50 MPa in comparison with composites with unmodified CNTs (3.81 ± 0.11 MPa). However, the addition of CNTs had no significant effect on SIBS with high molecular weight (Mn~70,000 g mol-1) with ultimate tensile stress of pure polymer of 11.62 MPa and 14.45 MPa in case of its modification with 1 wt% of CNT-DDA. Enhanced biocompatibility of nanocomposites as compared to neat SIBS has been demonstrated in experiment with EA.hy 926 cells. However, the platelet aggregation observed at high CNT concentrations can cause thrombosis. Therefore, SIBS with higher molecular weight (Mn~70,000 g mol-1) reinforced by 1-2 wt% of CNTs is the most promising material for the development of cardiovascular implants such as heart valve prostheses.

Indirect supervision applied to COVID-19 and pneumonia classification.

The novel coronavirus 19 (COVID-19) continues to have a devastating effect around the globe, leading many scientists and clinicians to actively seek to develop new techniques to assist with the tackling of this disease. Modern machine learning methods have shown promise in their adoption to assist the healthcare industry through their data and analytics-driven decision making, inspiring researchers to develop new angles to fight the virus. In this paper, we aim to develop a CNN-based method for the detection of COVID-19 by utilizing patients' chest X-ray images. Developing upon the inclusion of convolutional units, the proposed method makes use of indirect supervision based on Grad-CAM. This technique is used in the training process where Grad-CAM's attention heatmaps support the network's predictions. Despite recent progress, scarcity of data has thus far limited the development of a robust solution. We extend upon existing work by combining publicly available data across 5 different sources and carefully annotate the comprising images across three categories: normal, pneumonia, and COVID-19. To achieve a high classification accuracy, we propose a training pipeline based on indirect supervision of traditional classification networks, where the guidance is directed by an external algorithm. With this method, we observed that the widely used, standard networks can achieve an accuracy comparable to tailor-made models, specifically for COVID-19, with one network in particular, VGG-16, outperforming the best of the tailor-made models.

Aortography Keypoint Tracking for Transcatheter Aortic Valve Implantation Based on Multi-Task Learning.

Currently, transcatheter aortic valve implantation (TAVI) represents the most efficient treatment option for patients with aortic stenosis, yet its clinical outcomes largely depend on the accuracy of valve positioning that is frequently complicated when routine imaging modalities are applied. Therefore, existing limitations of perioperative imaging underscore the need for the development of novel visual assistance systems enabling accurate procedures. In this paper, we propose an original multi-task learning-based algorithm for tracking the location of anatomical landmarks and labeling critical keypoints on both aortic valve and delivery system during TAVI. In order to optimize the speed and precision of labeling, we designed nine neural networks and then tested them to predict 11 keypoints of interest. These models were based on a variety of neural network architectures, namely MobileNet V2, ResNet V2, Inception V3, Inception ResNet V2 and EfficientNet B5. During training and validation, ResNet V2 and MobileNet V2 architectures showed the best prediction accuracy/time ratio, predicting keypoint labels and coordinates with 97/96% accuracy and 4.7/5.6% mean absolute error, respectively. Our study provides evidence that neural networks with these architectures are capable to perform real-time predictions of aortic valve and delivery system location, thereby contributing to the proper valve positioning during TAVI.

Real-time coronary artery stenosis detection based on modern neural networks.

Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.

Efficient workflow for automatic segmentation of the right heart based on 2D echocardiography.

The present study aimed to present a workflow algorithm for automatic processing of 2D echocardiography images. The workflow was based on several sequential steps. For each step, we compared different approaches. Epicardial 2D echocardiography datasets were acquired during various open-chest beating-heart surgical procedures in three porcine hearts. We proposed a metric called the global index that is a weighted average of several accuracy coefficients, indices and the mean processing time. This metric allows the estimation of the speed and accuracy for processing each image. The global index ranges from 0 to 1, which facilitates comparison between different approaches. The second step involved comparison among filtering, sharpening and segmentation techniques. During the noise reduction step, we compared the median filter, total variation filter, bilateral filter, curvature flow filter, non-local means filter and mean shift filter. To clarify the endocardium borders of the right heart, we used the linear sharpen. Lastly, we applied watershed segmentation, clusterisation, region-growing, morphological segmentation, image foresting segmentation and isoline delineation. We assessed all the techniques and identified the most appropriate workflow for echocardiography image segmentation of the right heart. For successful processing and segmentation of echocardiography images with minimal error, we found that the workflow should include the total variation filter/bilateral filter, linear sharpen technique, isoline delineation/region-growing segmentation and morphological post-processing. We presented an efficient and accurate workflow for the precise diagnosis of cardiovascular diseases. We introduced the global index metric for image pre-processing and segmentation estimation.