Cardiac Magnetic Resonance Image Segmentation Method Based on Multi-Scale Feature Fusion and Sequence Relationship Learning.

Accurate segmentation of the left atrial structure using magnetic resonance images provides an important basis for the diagnosis of atrial fibrillation (AF) and its treatment using robotic surgery. In this study, an image segmentation method based on sequence relationship learning and multi-scale feature fusion is proposed for 3D to 2D sequence conversion in cardiac magnetic resonance images and the varying scales of left atrial structures within different slices. Firstly, a convolutional neural network layer with an attention module was designed to extract and fuse contextual information at different scales in the image, to strengthen the target features using the correlation between features in different regions within the image, and to improve the network's ability to distinguish the left atrial structure. Secondly, a recurrent neural network layer oriented to two-dimensional images was designed to capture the correlation of left atrial structures in adjacent slices by simulating the continuous relationship between sequential image slices. Finally, a combined loss function was constructed to reduce the effect of positive and negative sample imbalance and improve model stability. The Dice, IoU, and Hausdorff distance values reached 90.73%, 89.37%, and 4.803 mm, respectively, based on the LASC2013 (left atrial segmentation challenge in 2013) dataset; the corresponding values reached 92.05%, 89.41% and 9.056 mm, respectively, based on the ASC2018 (atrial segmentation challenge at 2018) dataset.

Analysis on influencing factors of health-related quality of life in designated drivers / 中国职业医学

@#Abstract: Objective - To analyze the status and influencing factors of health related quality of life of designated drivers. Methods ， ， Atotalof327designateddriversinBeijingCity TianjinCity HangzhouCityandZunyiCitywereselectedasstudy - （ - ） subjects by convenience sampling method. The EuroQol Five Dimensional Questionnaire EQ 5D was used to investigate the ， - ， ， ， utility index of five dimensions which include mobility self care daily activities pain or discomfort and anxiety or ， - （ - ） depression and the score of EQ 5D vertical visual analogue scale EQ VAS . The related influencing factors were analyzed. Results - The median and the 25th and 75th percentile of the utility index of the five dimensions and EQ VAS score of （ ， ） （ ， ）， - designateddriverswere1.0 1.0 1.0 and100.0 90.0 100.0 respectively.Mostoftheself assessmentofdesignateddrivers “ ”， in the five dimensions was without any difficulties reaching more than 93.0%. The designated drivers rated themselves as “ ” ， ， having a little difficulty/discomfort in the pain or discomfort anxiety or depression dimensions were 4.6% and 6.4% respectively. The multiple linear regression analysis showed that the utility index of the five dimensions in designated drivers （P< ） ， withoutsleepproblemswashigh 0.05 .Thedesignateddriverswithnosleepproblems nofatigueandvegetableintake≥250 - （ P< ）Conclusion - g/dhadhighEQ VASscores all 0.05 . Themainriskfactorsaffectingthehealth relatedqualityoflifeofthe ， ， designateddriversarepainordiscomfort anxietyordepression.Itisnecessaryfordesignateddriverstoensureadequatesleep

Design and construction of polymerized-chitosan coated Fe3O4 magnetic nanoparticles and its application for hydrophobic drug delivery.

In this study, a novel hydrogel, chitosan (CS) crosslinked carboxymethyl-ß-cyclodextrin (CM-ß-CD) polymer modified Fe3O4 magnetic nanoparticles was synthesized for delivering hydrophobic anticancer drug 5-fluorouracil (CS-CDpoly-MNPs). Carboxymethyl-ß-cyclodextrin being grafted on the Fe3O4 nanoparticles (CDpoly-MNPs) contributed to an enhancement of adsorption capacities because of the inclusion abilities of its hydrophobic cavity with insoluble anticancer drugs through host-guest interactions. Experimental results indicated that the amounts of crosslinking agent and bonding times played a crucial role in determining morphology features of the hybrid nanocarriers. The nanocarriers exhibited a high loading efficiency (44.7±1.8%) with a high saturation magnetization of 43.8emu/g. UV-Vis spectroscopy results showed that anticancer drug 5-fluorouracil (5-Fu) could be successfully included into the cavities of the covalently linked CDpoly-MNPs. Moreover, the free carboxymethyl groups could enhance the bonding interactions between the covalently linked CDpoly-MNPs and anticancer drugs. In vitro release studies revealed that the release behaviors of CS-CDpoly-MNPs carriers were pH dependent and demonstrated a swelling and diffusion controlled release. A lower pH value led to swelling effect and electrostatic repulsion contributing to the protonation amine impact of NH3(+), and thus resulted in a higher release rate of 5-Fu. The mechanism of 5-Fu encapsulated into the magnetic chitosan nanoparticles was tentatively proposed.