Seg-CapNet: A Capsule-Based Neural Network for the Segmentation of Left Ventricle from Cardiac Magnetic Resonance Imaging.

Deep neural networks (DNNs) have been extensively studied in medical image segmentation. However, existing DNNs often need to train shape models for each object to be segmented, which may yield results that violate cardiac anatomical structure when segmenting cardiac magnetic resonance imaging (MRI). In this paper, we propose a capsule-based neural network, named Seg-CapNet, to model multiple regions simultaneously within a single training process. The Seg-CapNet model consists of the encoder and the decoder. The encoder transforms the input image into feature vectors that represent objects to be segmented by convolutional layers, capsule layers, and fully-connected layers. And the decoder transforms the feature vectors into segmentation masks by up-sampling. Feature maps of each down-sampling layer in the encoder are connected to the corresponding up-sampling layers, which are conducive to the backpropagation of the model. The output vectors of Seg-CapNet contain low-level image features such as grayscale and texture, as well as semantic features including the position and size of the objects, which is beneficial for improving the segmentation accuracy. The proposed model is validated on the open dataset of the Automated Cardiac Diagnosis Challenge 2017 (ACDC 2017) and the Sunnybrook Cardiac Magnetic Resonance Imaging (MRI) segmentation challenge. Experimental results show that the mean Dice coefficient of Seg-CapNet is increased by 4.7% and the average Hausdorff distance is reduced by 22%. The proposed model also reduces the model parameters and improves the training speed while obtaining the accurate segmentation of multiple regions. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11390-021-0782-5.

Self-Assembled Hexagonal Superparamagnetic Cone Structures for Fabrication of Cell Cluster Arrays.

In this study, we demonstrated that arrays of cell clusters can be fabricated by self-assembled hexagonal superparamagnetic cone structures. When a strong out-of-plane magnetic field was applied to the ferrofluid on a glass substrate, it will induce the magnetic poles on the upper/lower surfaces of the continuous ferrofluid to increase the magnetostatic energy. The ferrofluid will then experience hydrodynamic instability and be split into small droplets with cone structures because of the compromising surface tension energy and magnetostatic energy to minimize the system's total energy. Furthermore, the ferrofluid cones were orderly self-assembled into hexagonal arrays to reach the lowest energy state. After dehydration of these liquid cones to form solid cones, polydimethylsiloxane was cast to fix the arrangement of hexagonal superparamagnetic cone structures and prevent the leakage of magnetic nanoparticles. The U-343 human neuronal glioblastoma cells were labeled with magnetic nanoparticles through endocytosis in co-culture with a ferrofluid. The number of magnetic nanoparticles internalized was (4.2 ± 0.84) × 106 per cell by the cell magnetophoresis analysis. These magnetically labeled cells were attracted and captured by hexagonal superparamagnetic cone structures to form cell cluster arrays. As a function of the solid cone size, the number of cells captured by each hexagonal superparamagnetic cone structure was increased from 48 to 126 under a 2000 G out-of-plane magnetic field. The local magnetic field gradient of the hexagonal superparamagnetic cone was 117.0-140.9 G/mm from the cell magnetophoresis. When an external magnetic field was applied, we observed that the number of protrusions of the cell edge decreased from the fluorescence images. It showed that the local magnetic field gradient caused by the hexagonal superparamagnetic cones restricted the cell growth and migration.

ML-Net: Multi-Channel Lightweight Network for Detecting Myocardial Infarction.

Due to the complexity of myocardial infarction (MI) waveform, most traditional automatic diagnosis models rarely detect it, while those able to detect MI often require high computing and storage capacity, rendering them unsuitable for portable devices. Therefore, in order for convenient real-time MI detection, it is essential to design lightweight models suitable for resource-limited portable devices. This paper proposes a novel multi-channel lightweight model (ML-Net), that provides a new solution for portable detection devices with limited resources. In ML-Net, each electrocardiogram (ECG) lead is assigned an independent channel, ensuring data independence and preserve the ECG characteristics of different angles represented by different leads. Moreover, convolution kernels of heterogeneous sizes are utilized to achieve accurate classification with only a small amount of lead data. Extensive experiments over actual ECG data from the PTB diagnostic database are conducted to evaluate ML-Net. The results show that ML-Net outperforms comparable schemes in diagnosing MI, and it requires lower computational cost and less memory, so that portable devices can be more widely used in the field of Internet of Medical Things(IoMT).

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.