There are lots of work being done to develop computer-assisted diagnosis and detection (CAD) technologies and systems to improve the diagnostic quality for pulmonary nodules. Another way to improve accuracy of diagnosis on new images is to recall or find images with similar features from archived historical images which already have confirmed diagnostic results, and the content-based image retrieval (CBIR) technology has been proposed for this purpose. In this paper, we present a method to find and select texture features of solitary pulmonary nodules (SPNs) detected by computed tomography (CT) and evaluate the performance of support vector machine (SVM)-based classifiers in differentiating benign from malignant SPNs. Seventy-seven biopsy-confirmed CT cases of SPNs were included in this study. A total of 67 features were extracted by a feature extraction procedure, and around 25 features were finally selected after 300 genetic generations. We constructed the SVM-based classifier with the selected features and evaluated the performance of the classifier by comparing the classification results of the SVM-based classifier with six senior radiologists' observations. The evaluation results not only showed that most of the selected features are characteristics frequently considered by radiologists and used in CAD analyses previously reported in classifying SPNs, but also indicated that some newly found features have important contribution in differentiating benign from malignant SPNs in SVM-based feature space. The results of this research can be used to build the highly efficient feature index of a CBIR system for CT images with pulmonary nodules.

No abstract

Numerous studies have reported soil damage from chemical fertilizer application and an obvious promotional effect of seaweed fertilizer fermented with Sargassum horneri on the growth of tomato roots and seedlings due to its alginate oligosaccharide. However, few studies have assessed the effects of the fermented seaweed fertilizer on ecological environment and microorganisms in soil. Herein, our objective is to uncover microbial and soil environmental responses to Sargassum horneri-fermented seaweed fertilizer. After treated tomato-planting plots with Sargassum horneri fermented seaweed fertilizer, soil bacterial community compositions based on 16S rRNA gene amplicon sequencing, enzyme activities in soil and crop yield were analyzed. The bacterial α-diversity was strongly influenced by seaweed fertilizer amendment after 60 days. Non-metric multidimensional scaling (NMDS) analysis showed that a difference in bacterial community compositions between day 0 and day 60 was obvious for soil treated with seaweed fertilizer. The community variation could be caused by invertase activity and dehydrogenase activity in canonical correlation analysis (CCA). Protease activity, polyphenol oxidase activity and urease activity showed an obvious correlation with community variation in the Mantel test. The fertilization increased tomato yield by 1.48-1.83 times, Vc content by 1.24-4.55 times and lycopene content by 1.20-2.33 times. In the present study, a possible reason for bacterial community variation was discovered, which will provide an economical dilution rate of seaweed fertilizer for optimal crop yield and quality. Meanwhile, our study will be beneficial for developing a possible substitute for chemical fertilizer and an improved understanding of soil microbial functions and soil sustainability.

The homologous genes BDF1 and BDF2 in Saccharomyces cerevisiae encode bromodomain-containing transcription factors. Although double deletion of BDF1 and BDF2 is lethal, single deletion does not affect cell viability. The bdf2Δ cells showed normal growth upon salt stress. However, the absence of Bdf1p resulted in a salt-sensitive phenotype, and the salt sensitivity was suppressed by overexpression of BDF2. In this study, we further demonstrated that BDF2 shows dosage compensation in suppressing the salt sensitivity of bdf1Δ. None of the tested domains replaced the function of intact Bdf1p. The 494-626 region in Bdf1p was more important than the other domains for salt resistance. In addition, Bdf1p negatively regulated the expression of BDF2 by binding its promoter at loci À387 to À48. However, Bdf2p did not affect the expression of BDF1. In addition, Bdf1p and its defective functional domain mutants could combine with Bdf2p. This physical interaction increased the salt tolerance of bdf1Δ. The mitochondrial dysfunctions caused by BDF1 deletion were restored by overexpression of BDF2 under salt stress conditions. Structured digital abstract• BDF2 physically interacts with BDF1 by anti tag coimmunoprecipitation (View interaction) • BDF2 physically interacts with BDF1 by pull down (View interaction)