Multiscale self-calibrated pulmonary nodule detection network fusing dual attention mechanism.

Objective. In this study, we propose a model called DEPMSCNet (a multiscale self-calibration network) that has a high sensitivity and low false positive rate for detecting pulmonary nodules.Approach. First, at the feature extraction stage, we propose to use the REPSA-MSC module instead of the traditional convolutional neural network. The module extracts multiscale information from the feature map based on the image pyramid strategy while introducing adaptive convolutional branches to detect contextual information at each position of the multiscale, thereby expanding the receptive field and improving sensitivity. At the same time, multiple branches are adaptively weighted by channel attention, and the weights of different branches are adjusted to better generate pixel-level attention. Secondly, the proposed DSAM (dual-path spatial attention module) operates at the information fusion stage. This module fully exploits the rich spatial information of CT scans, obtains receptive field information from two branches, combines low-level feature map information with high-level semantic information, and enhances location-related information to effectively improve specificity. Thirdly, the focal loss function is used to solve the problem of positive and negative sample imbalance.Mainresults. The proposed model has been evaluated on the public lung nodule analysis (LUNA16) challenge dataset. The technique outperforms the most recent state-of-the-art detection algorithms in terms of sensitivity and specificity, obtaining a sensitivity of 0.988 and a competitive performance metric (CPM) of 0.963.Significance. Ablation experiments show that the two modules proposed in this paper effectively reduce false positives and improve sensitivity. This model effectively reduces the number of false positive nodules that doctors see on CT scans.

Modulating the glycemic response of starch-based foods using organic nanomaterials: strategies and opportunities.

Traditionally, diverse natural bioactive compounds (polyphenols, proteins, fatty acids, dietary fibers) are used as inhibitors of starch digestive enzymes for lowering glycemic index (GI) and preventing type 2 diabetes mellitus (T2DM). In recent years, organic nanomaterials (ONMs) have drawn a great attention because of their ability to overcome the stability and solubility issues of bioactive. This review aimed to elucidate the implications of ONMs in lowering GI and as encapsulating agents of enzymes inhibitors. The major ONMs are presented. The mechanisms underlying the inhibition of enzymes, the stability within the gastrointestinal tract (GIT) and safety of ONMs are also provided. As a result of encapsulation of bioactive in ONMs, a more pronounced inhibition of enzymes was observed compared to un-encapsulated bioactive. More importantly, the lower the size of ONMs, the higher their inhibitory effects due to facile binding with enzymes. Additionally, in vivo studies exhibited the potentiality of ONMs for protection and sustained release of insulin for GI management. Overall, regulating the GI using ONMs could be a safe, robust and viable alternative compared to synthetic drugs (acarbose and voglibose) and un-encapsulated bioactive. Future researches should prioritize ONMs in real food products and evaluate their safety on a case-by-case basis.

Intrafibrillar Mineralized Collagen-Hydroxyapatite-Based Scaffolds for Bone Regeneration.

As one of the major challenges in the field of tissue engineering, large skeletal defects have attracted wide attention from researchers. Collagen (Col) and hydroxyapatite (HA), the most abundant protein and the main component in natural bone, respectively, are usually used as a biomimetic composite material in tissue engineering due to their excellent biocompatibility and biodegradability. In this study, novel intrafibrillar mineralized Col-HA-based scaffolds, constructed in either cellular or lamellar microstructures, were established through a biomimetic method to enhance the new bone-regenerating capability of tissue engineering scaffolds. Moreover, iron (Fe) and manganese (Mn), two of the essential trace elements in the body, were successfully incorporated into the lamellar scaffold to further improve the osteoinductivity of these biomaterials. It was found that the lamellar scaffolds demonstrated better osteogenic abilities compared to both in-house and commercial Col-HA-based cellular scaffolds in vitro and in vivo. Meanwhile, Fe/Mn incorporation further amplified the osteogenic promotion of the lamellar scaffolds. More importantly, a synergistic effect was observed in the Fe and Mn dual-element-incorporated lamellar scaffolds for both in vitro osteogenic differentiation of bone marrow mesenchymal stem cells (BMSCs) and in vivo bone regeneration loaded with fresh bone marrow cells. This study provides a simple but practical strategy for the creation of functional scaffolds for bone regeneration.