Search

Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification., Comment: 12 pages, 8 figures. This work has been submitted to the IEEE TNNLS for possible publication. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media

Purpose: Congenital heart defect (CHD) is the most common birth defect. Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning method based on cardiac ultrasound video to assist in ASD diagnosis. Materials and methods: We select two standard views of the atrial septum (subAS) and low parasternal four-compartment view (LPS4C) as the two views to identify ASD. We enlist data from 300 children patients as part of a double-blind experiment for five-fold cross-validation to verify the performance of our model. In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training). We propose an echocardiography video-based atrial septal defect diagnosis system. In our model, we present a block random selection, maximal agreement decision and frame sampling strategy for training and testing respectively, resNet18 and r3D networks are used to extract the frame features and aggregate them to build a rich video-level representation. Results: We validate our model using our private dataset by five-cross validation. For ASD detection, we achieve 89.33 AUC, 84.95 accuracy, 85.70 sensitivity, 81.51 specificity and 81.99 F1 score. Conclusion: The proposed model is multiple instances learning-based deep learning model for video atrial septal defect detection which effectively improves ASD detection accuracy when compared to the performances of previous networks and clinical doctors.

This paper introduces the Efficient Decoupled Masked Autoencoder (EDMAE), a novel self-supervised method for recognizing standard views in pediatric echocardiography. EDMAE introduces a new proxy task based on the encoder-decoder structure. The EDMAE encoder is composed of a teacher and a student encoder. The teacher encoder extracts the potential representation of the masked image blocks, while the student encoder extracts the potential representation of the visible image blocks. The loss is calculated between the feature maps output by the two encoders to ensure consistency in the latent representations they extract. EDMAE uses pure convolution operations instead of the ViT structure in the MAE encoder. This improves training efficiency and convergence speed. EDMAE is pre-trained on a large-scale private dataset of pediatric echocardiography using self-supervised learning, and then fine-tuned for standard view recognition. The proposed method achieves high classification accuracy in 27 standard views of pediatric echocardiography. To further verify the effectiveness of the proposed method, the authors perform another downstream task of cardiac ultrasound segmentation on the public dataset CAMUS. The experimental results demonstrate that the proposed method outperforms some popular supervised and recent self-supervised methods, and is more competitive on different downstream tasks., Comment: 15 pages, 5 figures, 8 tables, Published in Biomedical Signal Processing and Control

This study aims to examine the spatial evolution of the geometrical features of the turbulent/turbulent interface (TTI) in a cylinder wake. The wake is exposed to various turbulent backgrounds in which the turbulence intensity and the integral length scale are independently varied and comparisons to a turbulent/non-turbulent interface (TNTI) are drawn. The turbulent wake was marked with a high-Schmidt-number ($Sc$) scalar and a planar laser induced fluorescence (PLIF) experiment was carried out to capture the interface between the wake and the ambient flow from $x/d$ = 5 to 40 where $x$ is the streamwise coordinate from the centre of the cylinder and $d$ is the cylinder's diameter. It is found that the TTI generally spreads faster toward the ambient flow than the TNTI. A transition region of the interfaces' spreading is found at $x/d \approx 15$, after which the interfaces propagate at a slower rate than previously (upstream) and the mean interface positions of both TNTI and TTI scale with the local wake half-width. The location of both the TNTI and TTI have non-Gaussian probability density functions (PDFs) in the near wake because of the influence of the large-scale coherent motions present within the flow. Further downstream, after the large-scale coherent motions have dissipated, the TNTI position PDF does become Gaussian. For the first time we explore the spatial variation of the ``roughness'' of the TTI, quantified via the fractal dimension, from near field to far field. The length scale in the background flow has a profound effect on the TTI fractal dimension in the near wake, whilst the turbulence intensity only becomes important for the fractal dimension farther downstream.

When the atomic layers in a non-centrosymmetric van der Waals structure slide against each other, the interfacial charge transfer results in a reversal of the structures spontaneous polarization. This phenomenon is known as sliding ferroelectricity and it is markedly different from conventional ferroelectric switching mechanisms relying on ion displacement. Here, we present layer dependence as a new dimension to control sliding ferroelectricity. By fabricating 3R MoS2 of various thicknesses into dual-gate field-effect transistors, we obtain anomalous intermediate polarization states in multilayer 3R MoS2. Using results from ab initio density functional theory calculations, we propose a generalized model to describe the ferroelectric switching process in multilayer 3R MoS2 and to explain the formation of these intermediate polarization states. This work reveals the critical roles that layer number and interlayer dipole coupling play in sliding ferroelectricity and presents a new strategy for the design of novel sliding ferroelectric devices., Comment: 25 pages, 4 figures

A theory of non-homogeneous turbulence is developed and is applied to boundary-free shear flows. The theory introduces assumptions of inner and outer similarity for the non-homogeneity of two-point statistics and predicts power law scalings of second-order structure functions which have some similarities with but also some differences from Kolmogorov scalings. These scalings arise as a consequence of these assumptions, of the general inter-scale and inter-space energy balance and of an inner-outer equivalence hypothesis for turbulence dissipation. They reduce to usual Kolmogorov scalings in stationary homogeneous turbulence. Comparisons with structure function data from three qualitatively different turbulent wakes provide support for the theory's predictions but also raise new questions for future research., Comment: 28 pages, 12 figures