Chromosome karyotype analysis is of great clinical importance in the diagnosis and treatment of diseases. Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis. However, the strip-shaped chromosomes easily overlap each other when imaged, significantly affecting the accuracy of the subsequent analysis and hindering the development of chromosome analysis instruments. In this paper, we present an adversarial, multiscale feature learning framework to improve the accuracy and adaptability of overlapping chromosome segmentation. We first adopt the nested U-shaped network with dense skip connections as the generator to explore the optimal representation of the chromosome images by exploiting multiscale features. Then we use the conditional generative adversarial network (cGAN) to generate images similar to the original ones; the training stability of the network is enhanced by applying the least-square GAN objective. Finally, we replace the common cross-entropy loss with the advanced Lovász-Softmax loss to improve the model’s optimization and accelerate the model’s convergence. Comparing with the established algorithms, the performance of our framework is proven superior by using public datasets in eight evaluation criteria, showing its great potential in overlapping chromosome segmentation. 相似文献
A cancer‐targeted conjugate of the selenadiazole derivative BSeC (benzo[1,2,5] selenadiazole‐5‐carboxylic acid) with RGD peptide as targeting molecule and PEI (polyethylenimine) as a linker is rationally designed and synthesized in the present study. The results show that RGD‐PEI‐BSeC forms nanoparticles in aqueous solution with a core–shell nanostructure and high stability under physiological conditions. This rational design effectively enhances the selective cellular uptake and cellular retention of BSeC in human glioma cells, and increases its selectivity between cancer and normal cells. The nanoparticles enter the cells through receptor‐mediated endocytosis via clathrin‐mediated and nystatin‐dependent lipid raft‐mediated pathways. Internalized nanoparticles trigger glioma cell apoptosis by activation of ROS‐mediated p53 phosphorylation. Therefore, this study provides a strategy for the rational design of selenium‐containing cancer‐targeted theranostics.
The first well‐controlled aqueous atom‐transfer radical polymerization (ATRP) conducted in the open air is reported. This air‐tolerant ATRP was enabled by the continuous conversion of oxygen to carbon dioxide catalyzed by glucose oxidase (GOx), in the presence of glucose and sodium pyruvate as sequential sacrificial substrates. Controlled polymerization using initiators for continuous activator regeneration (ICAR) ATRP of oligo(ethylene oxide) methyl ether methacrylate (OEOMA, Mn=500) yielded polymers with low dispersity (1.09≤?≤1.29) and molecular weights (MWs) close to theoretical values in the presence of pyruvate. Without added pyruvates, lower MWs were observed due to generation of new chains by H2O2 formed by reaction of O2 with GOx. Successful chain extension of POEOMA500 macroinitiator with OEOMA300 (?≤1.3) and Bovine Serum Albumin bioconjugates (?≤1.22) confirmed a well‐controlled polymerization. The reactions in the open air in larger scale (25 mL) were also successful. 相似文献