Automatic segmentation of organs-at-risks of nasopharynx cancer and lung cancer by cross-layer attention fusion network with TELD-Loss.

PURPOSE: Radiotherapy is one of the main treatments of nasopharyngeal cancer (NPC) and lung cancer. Accurate segmentation of organs at risks (OARs) in CT images is a key step in radiotherapy planning for NPC and lung cancer. However, the segmentation of OARs is influenced by the highly imbalanced size of organs, which often results in very poor segmentation results for small and difficult-to-segment organs. In addition, the complex morphological changes and fuzzy boundaries of OARs also pose great challenges to the segmentation task. In this paper, we propose a cross-layer attention fusion network (CLAF-CNN) to solve the problem of accurately segmenting OARs. METHODS: In CLAF-CNN, we integrate the spatial attention maps of the adjacent spatial attention modules to make the segmentation targets more accurately focused, so that the network can capture more target-related features. In this way, the spatial attention modules in the network can be learned and optimized together. In addition, we introduce a new Top-K exponential logarithmic Dice loss (TELD-Loss) to solve the imbalance problem in OAR segmentation. The TELD-Loss further introduces a Top-K optimization mechanism based on Dice loss and exponential logarithmic loss, which makes the network pay more attention to small organs and difficult-to-segment organs, so as to enhance the overall performance of the segmentation model. RESULTS: We validated our framework on the OAR segmentation datasets of the head and neck and lung CT images in the StructSeg 2019 challenge. Experiments show that the CLAF-CNN outperforms the state-of-the-art attention-based segmentation methods in the OAR segmentation task with average Dice coefficient of 79.65% for head and neck OARs and 88.39% for lung OARs. CONCLUSIONS: This work provides a new network named CLAF-CNN which contains cross-layer spatial attention map fusion architecture and TELD-Loss for OAR segmentation. Results demonstrated that the proposed method could obtain accurate segmentation results for OARs, which has a potential of improving the efficiency of radiotherapy planning for nasopharynx cancer and lung cancer.

Hyaluronic Acid-Functionalized Hollow Mesoporous Silica Nanoparticles as pH-Sensitive Nanocarriers for Cancer Chemo-Photodynamic Therapy.

Hollow mesoporous silica nanoparticles (HMSNs) served as nanocarriers for transporting doxorubicin hydrochloride (DOX) and indocyanine green (ICG) and were incorporated into a pH-sensitive targeted drug delivery system (DDS). Boronate ester bonds were employed to link HMSNs and dopamine-modified hyaluronic acid (DA-HA), which acted as both the "gatekeeper" and targeting agents (HMSNs-B-HA). Well-dispersed HMSNs-B-HA with a diameter of about 170 nm was successfully constructed. The conclusion was drawn from the in vitro drug release experiment that ICG and DOX (ID) co-loaded nanoparticles (ID@HMSNs-B-HA) with high drug loading efficiency could sustain drug release under acidic conditions. More importantly, in vitro cell experiments perfectly showed that ID@HMSNs-B-HA could well inhibit murine mammary carcinoma (4T1) cells via chemotherapy combined with photodynamic therapy and accurately target 4 T1 cells. In summary, all test results sufficiently demonstrated that the prepared ID@HMSNs-B-HA was a promising nano-DDS for cancer photodynamic combined with chemotherapy.

A Novel Approach for Atrial Fibrillation Signal Identification Based on Temporal Attention Mechanism.

Atrial fibrillation (AF) is a common heart rhythm which occurs when the upper chambers of the heart beat irregularly. With the rapid development of the deep learning algorithm, the Convolutional Neural Networks (CNN) is widely investigated for the ECG classification task. However, for AF detection, the performance of CNN is greatly limited due to the lack of consideration for temporal characteristic of the ECG signal. In order to improve the discriminative ability of CNN, we introduce the attention mechanism to help the network concentrate on the informative parts and obtain the temporal features of the signals. Inspired by this idea, we propose a temporal attention block (TA-block) and a temporal attention convolutional neural network (TACNN) for the AF detection tasks. The TA-block can adaptively learn the temporal features of the signal and generate the attention weights to enhance informative features. With a stack architecture of TA-blocks, the TA-CNN obtains better performance as a result of paying more attention to the informative parts of the signal. We validate our approach on the single lead ECG classification dataset of The PhysioNet Computing in Cardiology Challenge 2017. The experimental results indicate that the proposed framework outperform state-of-the-arts classification networks.Clinical Relevance-The proposed algorithm can be potentially applied to the portable cardiovascular monitoring devices reducing the danger of AF.

Hyaluronic acid targeted and pH-responsive nanocarriers based on hollow mesoporous silica nanoparticles for chemo-photodynamic combination therapy.

In this work, a pH-responsive and tumor targeted multifunctional drug delivery system (RB-DOX@HMSNs-N = C-HA) was designed to realize chemo-photodynamic combination therapy. Hollow mesoporous silica nanoparticles (HMSNs) was served as the host material to encapsulate doxorubicin (DOX) and photosensitizer rose bengal (RB). Hyaluronic acid (HA) was modified on the surface of HMSNs via pH-sensitive Schiff base bonds as gatekeeper as well as targeted agent. Characterization results indicated the successful preparation of HMSNs-N = C-HA with appropriate diameter of 170 nm around and the nanocarriers displayed superior drug loading capacity (15.30 % for DOX and 12.78 % for RB). Notably, the results of in vitro drug release experiments confirmed that the system possessed good pH-sensitivity, which made it possible to release cargoes in slight acid tumor micro-environments. Significantly, the in vitro cell uptake and cytotoxicity assay results fully proved that RB-DOX@HMSNs-N = C-HA could precisely target murine mammary carcinoma (4T1) cells and effectively inhibit tumor cells viability with chemo-photodynamic synergistic therapy. Overall, our work (RB-DOX@HMSNs-N = C-HA) provides an efficient approach for the development of chemo-photodynamic combination therapy.

Polydopamine coated hollow mesoporous silica nanoparticles as pH-sensitive nanocarriers for overcoming multidrug resistance.

A nanocarrier system of methoxypolyethylene glycol amine (mPEG-NH2) functionalized polydopamine (PDA) coated hollow mesoporous silica nanoparticles (HMSNs-PDA-PEG) was developed with pH-responsive, which combined doxorubicin hydrochloride (DOX) and quercetin (QUR) to reverse multidrug resistance (MDR) and improved anticancer effects on taxol (TAX) and DOX double resistant human colorectal cancer cell line HCT-8 (HCT-8/TAX cells). Well-dispersed nanoparticles (HMSNs-PDA-PEG) were prepared with a dimension of around 170 nm. The surface morphology and chemical properties of HMSNs-PDA-PEG were also successfully characterized by transmission electron microscopy (TEM), X-ray photoelectron spectroscopy (XPS), thermal gravimetric analysis (TGA), X-ray diffraction (XRD), Brunauer-Emmett-Teller (BET) method, Fourier transform infrared spectroscopy (FT-IR) and dynamic light scattering (DLS). Drug release experiments results indicated that DOX and QUR (QD) loaded nanoparticles (HMSNs-PDA-PEG@QD) had similar release kinetic profiles of each drug, which all exhibited highly sensitive to pH value due to the surface PDA coating. Additionally, the HCT-8 cells or HCT-8/TAX cells were employed to assess the cellular uptake and cytotoxicity of various drug-free or drug-loaded HMSNs samples. Meanwhile, a series of biological evaluations demonstrated that the HMSNs-PDA-PEG@QD exhibited remarkable ability to overcome MDR compared with free DOX and HMSNs-PDA-PEG@DOX. Taken together, these results revealed that HMSNs-PDA-PEG@QD was suitable as a prospective and efficient drug delivery nanosystem for overcoming multidrug resistance.

Impact of Heterogeneity and Secrecy on the Capacity of Wireless Sensor Networks.

This paper investigates the achievable secrecy throughput of an inhomogeneous wireless sensor network. We consider the impact of topology heterogeneity and the secrecy constraint on the throughput. For the topology heterogeneity, by virtue of percolation theory, a set of connected highways and information pipelines is established; while for the secrecy constraint, the concept of secrecy zone is adopted to ensure secrecy transmission. The secrecy zone means there is no eavesdropper around the legitimate node. The results demonstrate that, if the eavesdropper's intensity is λ(e)= o((log n)(-(3δ-4)/(δ-2))), a per-node secrecy rate of Ω [formula: see text] can be achieved on the highways, where δ is the exponent of heterogeneity, n and n(v) represent the number of nodes and clusters in the network, respectively. It is also shown that, with the density of the eavesdropper λ(e) = o((log(n Φ Ì² ))(-2)), the per-node secrecy rate of Ω (√(Φ Ì² /n)) can be obtained in the information pipelines, where Φ Ì² denotes the minimum node density in the network.