Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis.

Aim: Accurate severity grading of lumbar spine disease by magnetic resonance images (MRIs) plays an important role in selecting appropriate treatment for the disease. However, interpreting these complex MRIs is a repetitive and time-consuming workload for clinicians, especially radiologists. Here, we aim to develop a multi-task classification model based on artificial intelligence for automated grading of lumbar disc herniation (LDH), lumbar central canal stenosis (LCCS) and lumbar nerve roots compression (LNRC) at lumbar axial MRIs. Methods: Total 15254 lumbar axial T2W MRIs as the internal dataset obtained from the Fifth Affiliated Hospital of Sun Yat-sen University from January 2015 to May 2019 and 1273 axial T2W MRIs as the external test dataset obtained from the Third Affiliated Hospital of Southern Medical University from June 2016 to December 2017 were analyzed in this retrospective study. Two clinicians annotated and graded all MRIs using the three international classification systems. In agreement, these results served as the reference standard; In disagreement, outcomes were adjudicated by an expert surgeon to establish the reference standard. The internal dataset was randomly split into an internal training set (70%), validation set (15%) and test set (15%). The multi-task classification model based on ResNet-50 consists of a backbone network for feature extraction and three fully-connected (FC) networks for classification and performs the classification tasks of LDH, LCCS, and LNRC at lumbar MRIs. Precision, accuracy, sensitivity, specificity, F1 scores, confusion matrices, receiver-operating characteristics and interrater agreement (Gwet k) were utilized to assess the model's performance on the internal test dataset and external test datasets. Results: A total of 1115 patients, including 1015 patients from the internal dataset and 100 patients from the external test dataset [mean age, 49 years ± 15 (standard deviation); 543 women], were evaluated in this study. The overall accuracies of grading for LDH, LCCS and LNRC were 84.17% (74.16%), 86.99% (79.65%) and 81.21% (74.16%) respectively on the internal (external) test dataset. Internal and external testing of three spinal diseases showed substantial to the almost perfect agreement (k, 0.67 - 0.85) for the multi-task classification model. Conclusion: The multi-task classification model has achieved promising performance in the automated grading of LDH, LCCS and LNRC at lumbar axial T2W MRIs.

Comparative analysis of the dust retention capacity and leaf microstructure of 11 Sophora japonica clones.

We used fresh leaves of Sophora japonica L. variety 'Qingyun 1' (A0) and 10 superior clones of the same species (A1-A10) to explore leaf morphological characteristics and total particle retention per unit leaf area under natural and artificial simulated dust deposition treatments. Our objectives were to explore the relationship between the two methods and to assess particle size distribution, X-ray fluorescence (XRF) heavy metal content, and scanning electron and atomic force microscopy (SEM and AFM) characteristics of leaf surface microstructure. Using the membership function method, we evaluated the dust retention capacity of each clone based on the mean degree of membership of its dust retention index. Using correlation analysis, we selected leaf morphological and SEM and AFM indices related significantly to dust retention capacity. Sophora japonica showed excellent overall dust retention capacity, although this capacity differed among clones. A5 had the strongest overall retention capacity, A2 had the strongest retention capacity for PM2.5, A9 had the strongest retention capacity for PM2.5-10, A0 had the strongest retention capacity for PM>10, and A2 had the strongest specific surface area (SSA) and heavy metal adsorption capacity. Overall, A1 had the strongest comprehensive dust retention ability, A5 was intermediate, and A7 had the weakest capacity. Certain leaf morphological and SEM and AFM characteristic indices correlated significantly with the dust retention capacity.

The first complete chloroplast genome sequences of Ulmus species by de novo sequencing: Genome comparative and taxonomic position analysis.

Elm (Ulmus) has a long history of use as a high-quality heavy hardwood famous for its resistance to drought, cold, and salt. It grows in temperate, warm temperate, and subtropical regions. This is the first report of Ulmaceae chloroplast genomes by de novo sequencing. The Ulmus chloroplast genomes exhibited a typical quadripartite structure with two single-copy regions (long single copy [LSC] and short single copy [SSC] sections) separated by a pair of inverted repeats (IRs). The lengths of the chloroplast genomes from five Ulmus ranged from 158,953 to 159,453 bp, with the largest observed in Ulmus davidiana and the smallest in Ulmus laciniata. The genomes contained 137-145 protein-coding genes, of which Ulmus davidiana var. japonica and U. davidiana had the most and U. pumila had the fewest. The five Ulmus species exhibited different evolutionary routes, as some genes had been lost. In total, 18 genes contained introns, 13 of which (trnL-TAA+, trnL-TAA-, rpoC1-, rpl2-, ndhA-, ycf1, rps12-, rps12+, trnA-TGC+, trnA-TGC-, trnV-TAC-, trnI-GAT+, and trnI-GAT) were shared among all five species. The intron of ycf1 was the longest (5,675bp) while that of trnF-AAA was the smallest (53bp). All Ulmus species except U. davidiana exhibited the same degree of amplification in the IR region. To determine the phylogenetic positions of the Ulmus species, we performed phylogenetic analyses using common protein-coding genes in chloroplast sequences of 42 other species published in NCBI. The cluster results showed the closest plants to Ulmaceae were Moraceae and Cannabaceae, followed by Rosaceae. Ulmaceae and Moraceae both belonged to Urticales, and the chloroplast genome clustering results were consistent with their traditional taxonomy. The results strongly supported the position of Ulmaceae as a member of the order Urticales. In addition, we found a potential error in the traditional taxonomies of U. davidiana and U. davidiana var. japonica, which should be confirmed with a further analysis of their nuclear genomes. This study is the first report on Ulmus chloroplast genomes, which has significance for understanding photosynthesis, evolution, and chloroplast transgenic engineering.

[Effects of salt stress on physiological characters and salt-tolerance of Ulmus pumila in different habitats].

Taking the Ulmus pumila seedlings from three different habitats (medium-, mild-, and non-saline soils) as test materials, an experiment was conducted to study their salt-tolerance thresholds and physiological characteristic under different levels (0, 2, 4, 6, 8, and 10 g X kg(-1)) of salt stress. With increasing level of the salt stress, the seedlings taken from medium- and mild- saline habitats had a lower increment of leaf membrane permeability, Na+ content, and Na+/K+ but a higher increment of leaf proline, soluble sugar, and K+ contents, and a lower decrement of leaf starch content, net photosynthetic rate, transpiration rate, intercellular CO2 concentration, and stomatic conductance, as compared with the seedlings taken from non-saline habitat. The salt-tolerance thresholds of the seedlings taken from different habitats were in the order of medium- saline habitat (7.76 g X kg(-1)) > mild- saline habitat (7.37 g X kg(-1)) > non-saline habitat (6.95 g X kg(-1)). It was suggested that the U. pumila seedlings in medium- and mild-saline habitats had a stronger adaptability to saline soil environment than the U. pumila seedlings in non-saline soil environment.

[Effects of NaCl stress on the exogenous gene expression in transgenic poplar plants].

The expressions of BtCry1Ac insect-resistance genes and rhizogenesis genes and their response to NaCl stress were studied using tissue culture plants of high transgenic insect-resistant 'poplar 741' and transpolygenes 741 (insect-resistant genes and T-DNA of Ri plasmid). The results showed that IAA and GA contents increased quickly, plant root number increased and root length reduced after rhizogenesis and hormone synthesis related gene in Ri T-DNA were inserted into the genome of poplar (Figs.2, 3, 8 and 9). Plant height, root number, chlorophyll content, IAA and GA contents decreased gradually with an increase in NaCl stress intensity (Figs.1, 2, 4-6, 8 and 9). Apiece index change extent of transgenic rol gene plant was smaller than transgenic Bt gene plant and non-transgenic plant. Bt toxin protein content of transgenic rol gene plant increased significantly under NaCl stress (Fig.7). Our results indicate that the expressions of the foreign genes changed with the changes of the environmental conditions.

[Allozyme variability of provenance populations of Robinia pseudoacacia from Middle Europe].

Using starch gel and polyacrylamide gel electrophoresis, 11 enzyme systems of two-year-old seedlings from 18 provences of Robinia pseudoacacia distributing in the middle Europe and America were investigated. There were 14 polymorphic loci with a proportion of 70.0% in twenty loci. Twelve polymorphic loci in 7 enzyme systems were calculated. In the 12 polymorphic loci, the mean and effective numbers of alleles per locus were 2.733 and 1.794, as well as the mean observed and expected heterozygosities were 0.368 and 0.400, respectively. Fixation index in most of the loci was slightly higher than zero with a mean value of 0.080. The most population genetic parameters (A, Ae, Ho, He) at the Fe-b and Lap-a loci correlated closely with the mean number of the twelve loci, and such relation was not evident among other loci which may be more important. The genetic distance among the 8 provenances in Germany changed between 0.09 and 0.26, while in contrast, that of the 6 provenances in Hungary were very small and most of them were below 0.11. The genetic distance among the provenances in Germany, Hungary and Slovakia varied from 0.09 to 0.24. Among the 2 provenances in America and provenances in Europe, the genetic distance changed from 0.09 to 0.23, which was not higher than the differences among that of the Europe provenances. Genetic parameters and heredity diversities of the 8 provenances in Hungary and Slovakia were higher than those of the Germany provenances. The differentiation coefficient of the two countries changed from 2.92% to 9.97%, indicting that the genetic difference among the provenances in Hungary and Slovakia was smaller than in Germany provenances. Interpopulational differentiation coefficient in Germany provenances was higher compared with that in Hungary and Slovakia provenances. We took a country as one unit of provenance population, and then the differentiation coefficient of the genetic parameters of the four populations, changing between 3.870% and 5.139%, was rather small. This indicated that it was not evident for the interpopulational geographic differentiations of Robinia pseudoacacia. Therefore, it is suggested that Robinia pseudoacacia has higher genetic diversity and the breeding programs might have been concentrated on intrapopulational variation.