Mechanism of balloon burst during transcatheter aortic valve replacement pre-dilatation: Image observation and validation by finite element analysis.

BACKGROUND: Balloon burst during transcatheter aortic valve replacement (TAVR) is serious complication. This study pioneers a novel approach by combining image observation and computer simulation validation to unravel the mechanism of balloon burst in a patient with bicuspid aortic valve (BAV) stenosis. METHOD: A new computational model for balloon pre-dilatation was developed by incorporating the element failure criteria according to the Law of Laplace. The effects of calcification and aortic tissue material parameters, friction coefficients, balloon types and aortic anatomy classification were performed to validate and compare the expansion behavior and rupture mode of actual balloon. RESULTS: Balloon burst was dissected into three distinct stages based on observable morphological changes. The mechanism leading to the complete transverse burst of the non-compliant balloon initiated at the folding edges, where contacted with heavily calcified masses at the right coronary sinus, resulting in high maximum principal stress. Local sharp spiked calcifications facilitated rapid crack propagation. The elastic moduli of calcification significantly influenced balloon expansion behavior and crack morphology. The simulation case of the calcific elastic modulus was set at 12.6 MPa could closely mirror clinical appearance of expansion behavior and crack pattern. Furthermore, the case of semi-compliant balloons introduced an alternative rupture mechanism as pinhole rupture, driven by local sharp spiked calcifications. CONCLUSIONS: The computational model of virtual balloons could effectively simulate balloon dilation behavior and burst mode during TAVR pre-dilation. Further research with a larger cohort is needed to investigate the balloon morphology during pre-dilation by using this method to guide prosthesis sizing for potential favorable outcomes.

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.

Enhancement method with naturalness preservation and artifact suppression based on an improved Retinex variational model for color retinal images.

Retinal images are widely used for the diagnosis of various diseases. However, low-quality retinal images with uneven illumination, low contrast, or blurring may seriously interfere with diagnosis by ophthalmologists. This study proposes an enhancement method for low-quality retinal color images. In this paper, an improved variational Retinex model for color retinal images is first proposed and applied to each channel of the RGB color space to obtain the illuminance and reflectance layers. Subsequently, the Naka-Rushton equation is introduced to correct the illumination layer, and an enhancement operator is constructed to improve the clarity of the reflectance layer. Finally, the corrected illuminance and enhanced reflectance are recombined. Contrast-limited adaptive histogram equalization is introduced to further improve the clarity and contrast. To demonstrate the effectiveness of the proposed method, this method is tested on 527 images from four publicly available datasets and 40 local clinical images from Tianjin Eye Hospital (China). Experimental results show that the proposed method outperforms the other four enhancement methods and has obvious advantages in naturalness preservation and artifact suppression.

Analysis of the incidence and influencing factors associated with binary restenosis of target lesions after drug-coated balloon angioplasty for patients with in-stent restenosis.

BACKGROUND: Drug-coated balloon (DCB) is a novel and effective device for coronary artery disease patients with in-stent restenosis (ISR). However, the incidence and possible influencing factors associated with binary restenosis have not yet been adequately assessed. METHODS: The data are extracted from a prospective, multicenter, randomized controlled trial. A total of 211 patients with ISR were enrolled at 13 centers from August 2017 to October 2018 and treated with DCB. At the 9-month coronary angiographic follow-up, patients were divided into restenosis and non-restenosis groups, and demographic data, lesion features, and laboratory tests were retrospectively reviewed. Furthermore, logistic regression analysis was used to identify possible influencing factors. RESULTS: All patients successfully underwent treatment, and 166 patients with 190 lesions took part in angiography follow-ups at 9 months. Of these, 41 patients with 44 target lesions developed restenosis following treatment, and the incidence of ISR was 24.7%. There were significant differences in the average length of target lesions and the number of multivessel lesions and fasting plasma glucose (FBG) between the two groups (p < 0.05). Demographic data, cardiac risk factors, left ventricular ejection fractions (LVEF), blood routine tests, biochemical tests, and other features of devices and lesions showed no difference. Logistic regression analyses showed that FBG > 6.1 mmol/L (OR: 7.185 95% CI: 2.939-17.567 P < 0.001) and length of lesion (OR:1.046 95% CI: 1.001-1.093 P = 0.046) were associated risk factors. CONCLUSIONS: The longer length of lesions, more target lesions and FBG > 6.1 mmol/L per individual may be characteristics of patients showing ISR following treatment. Studies with larger sample size, and more complete follow-up data are needed in the future to expend on these findings. TRIAL REGISTRATION: No.: NCT04213378, first posted date (30/12/2019).

Fusion network based on the dual attention mechanism and atrous spatial pyramid pooling for automatic segmentation in retinal vessel images.

Accurate segmentation of retinal blood vessels from retinal images is crucial to aid in the detection and diagnosis of many eye diseases. In this paper, a fusion network based on the dual attention mechanism and atrous spatial pyramid pooling (DAANet) is proposed for vessel segmentation. First, we propose a dual attention module consisting of a position attention module and a channel attention module, which aims to adaptively recalibrate features to extract effective features. And full-scale skip connections are used in the encoder to provide multi-scale feature maps for the dual attention modules. Then, atrous spatial pyramid pooling (ASPP) allows the network to capture features at multiple scales and combine high-level semantic information with low-level features through the encoder-decoder architecture. We qualitatively evaluate the model using five metrics: sensitivity, specificity, accuracy, AUC, and F1 score on DRIVE, CHASED_B1, and STARE datasets. The DAANet outperforms the work of 10 state-of-the-art predecessors in these three datasets. Furthermore, we apply the trained model to clinical retinal images. The model obtains gratifying accurate and detailed segmentation results, which demonstrates a promising application prospect in medical practices.

ULNet for the detection of coronavirus (COVID-19) from chest X-ray images.

Novel coronavirus disease 2019 (COVID-19) is an infectious disease that spreads very rapidly and threatens the health of billions of people worldwide. With the number of cases increasing rapidly, most countries are facing the problem of a shortage of testing kits and resources, and it is necessary to use other diagnostic methods as an alternative to these test kits. In this paper, we propose a convolutional neural network (CNN) model (ULNet) to detect COVID-19 using chest X-ray images. The proposed architecture is constructed by adding a new downsampling side, skip connections and fully connected layers on the basis of U-net. Because the shape of the network is similar to UL, it is named ULNet. This model is trained and tested on a publicly available Kaggle dataset (consisting of a combination of 219 COVID-19, 1314 normal and 1345 viral pneumonia chest X-ray images), including binary classification (COVID-19 vs. Normal) and multiclass classification (COVID-19 vs. Normal vs. Viral Pneumonia). The accuracy of the proposed model in the detection of COVID-19 in the binary-class and multiclass tasks is 99.53% and 95.35%, respectively. Based on these promising results, this method is expected to help doctors diagnose and detect COVID-19. Overall, our ULNet provides a quick method for identifying patients with COVID-19, which is conducive to the control of the COVID-19 pandemic.

IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge.

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on "Diabetic Retinopathy - Segmentation and Grading" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.