AI-Supported Autonomous Uterus Reconstructions: First Application in MRI Using 3D SPACE with Iterative Denoising.

RATIONALE AND OBJECTIVES: T2-weighted imaging in at least two orthogonal planes is recommended for assessment of the uterus. To determine whether a convolutional neural network-based algorithm could be used for the re-constructions of uterus axes derived from a 3D SPACE with iterative denoising. MATERIALS AND METHODS: 50 patients aged 18-81 (mean: 42) years who underwent an MRI examination of the uterus participated voluntarily in this prospective study after informed consent. In addition to a standard MRI pelvis protocol, a 3D SPACE research application sequence was acquired in sagittal orientation. Reconstructions for both the cervix and the cavum in the short and long axes were performed by a research trainee (T), an experienced radiologist (E), and the prototype software (P). In the next step, the reconstructions were evaluated anonymously by two experienced readers according to 5-point-Likert-Scales. In addition, the length of the cervical canal, the length of the cavum and the distance between the tube angles were measured on all reconstructions. Interobserver agreement was assessed for all ratings. RESULTS: For all axes, significant differences were found between the scores of the reconstructions by research T, E and P. P received higher scores and was preferred significantly more often with the exception of the comparison of the reconstruction Cervix short of E (Cervix short: P vs. T: p = 0.02; P vs. E: p = 0.26; Cervix long: P vs. T: p = 0.01; P vs. E: p < 0.01; Cavum short: P vs. T: p = 0.01; P vs. E: p = 0.02; Cavum long: P vs. T: p < 0.01; P vs. E: p < 0.01). Regarding the measured diameters, (length of cervical canal/cavum/distance between tube angles) significantly larger diameters were recorded for P compared to E and T (Cervix long (mm): T: 25.43; E: 25.65; P: 26.65; Cavum short (mm): T: 26.24; E: 25.04; P: 27.33; Cavum long (mm): T: 31.98; E: 32.91; P: 34.41; P vs. T: p < 0.01); P vs. E: p = 0.04). Moderate to substantial agreement was found between Reader 1 and Reader 2 (range: 0.39-0.67). CONCLUSION: P was able to reconstruct the axes at least as well as or better than E and T. P could thereby lead to workflow facilitation and enable more efficient reporting of uterine MRI.

Microstructure and Properties of Atmospheric Plasma Sprayed (Al,Cr)2O3-TiO2 Coatings from Blends.

Coatings prepared from chromia-rich (Al,Cr)2O3 solid solution (ss) feedstock powders are intended to improve the properties of Cr2O3 coatings, but are rarely studied so far. In this work, the processability of a commercial (Al,Cr)2O3 solid solution (ss) powder containing 78 wt.% Cr2O3 by atmospheric plasma spraying (APS), the corresponding coating microstructures and properties were investigated. Possible further improvements were expected by blending with 2, 23 and 54 wt.% TiOx powder. For comparison, plain Cr2O3 and TiOx coatings were studied as well. The microstructures were analyzed using SEM, EDS and XRD measurements. Hardness (HV0.3) was measured, as well as the dry unidirectional sliding wear resistance and the abrasion wear resistance (ASTM G65). Moreover, the corrosion and electrical insulating properties were measured. The (Al,Cr)2O3 ss showed only a small change of the composition, and the formation of γ-Al2O3, as found for alumina-rich (Al,Cr)2O3 ss powders, was avoided. Compared to the plain chromia coating, some improvements of the processability and coating properties for the ss (Al,Cr)2O3 coating were found. The most balanced coating performance was achieved by blending the ss (Al,Cr)2O3 with 2 wt.% TiOx, as this coating showed both a high sliding and abrasion wear resistance, in combination with a high corrosion resistance.

Changes in the Coating Composition Due to APS Process Conditions for Al2O3-Cr2O3-TiO2 Ternary Powder Blends.

Thermally sprayed coatings from the single oxides and binary compositions of the Al2O3-Cr2O3-TiO2 system show multifunctional properties. Ternary compositions are promising for further improvement in their performance. The stability of the composition during coating formation is an important issue for blended feedstock powders in order to obtain the desired properties. This work focuses on the compositional changes of a ternary blend of Al2O3, Cr2O3 and TiOx powders of equal content by mass in a conventional atmospheric plasma spraying (APS) process using an Ar/H2 plasma gas mixture. By increasing the argon flow rate at constant hydrogen flow rate, the total plasma gas flow rate and the Ar/H2 ratio were varied. For the highest argon flow rate, this resulted in an average particle velocity of 140% and an average particle temperature of 90% of the initial values, respectively. Coating composition and microstructure were studied by optical microscopy, SEM, including EDS analyses, and XRD. In addition, the coating hardness and electrical impedance were also measured. Differences in the "difficulty of melting factor" (DMF) and the thermal diffusivity of the three oxides appear to be responsible for the dramatic change of the coating composition with an increasing argon flow rate. For the highest argon flow rate applied, besides TiO2, the coating contains only 8 wt.% Al2O3, while the Cr2O3 content remained almost constant. At the same time, the change of the Ar/H2 ratio resulted in the formation of stoichiometric TiO2 in the coating by oxidation of TiOx in the feedstock powder. Moreover, a small content of titanium was found in the Cr2O3 splats, showing that there are only limited interactions between the large oxide powder particles. Thus, the study has shown that stability of the chemical composition during spraying of ternary powder blends is strongly influenced by the process conditions.

LigMate: A Multifeature Integration Algorithm for Ligand-Similarity-Based Virtual Screening.

Ligand-similarity-based virtual screening is one of the most applicable computer-aided drug design techniques. The current methodology relies heavily on several descriptors of molecular features, including atoms (zero-dimensional, 0D), the presence or absence of structural features (one-dimensional, 1D), topological descriptors (two-dimensional, 2D), geometry and volume (three-dimensional, 3D), or stereoelectronic and stereodynamic properties (four-dimensional, 4D). These descriptors have been frequently used in virtual screening; however, they are usually used independently without integration, which may hinder effective and precise virtual screening. In this study, we developed a multifeature integration algorithm named LigMate, which employs a Hungarian algorithm-based matching and a machine learning-based nonlinear combination of various descriptors, including the new relevant descriptors focusing on the maximum common substructures (maximum common substructure score, MCSS), the relative distance of atoms from the ligand mass center (intraligand distance score, ILDS), as well as the ring differences (ring score, RS). In the benchmark tests, LigMate achieved an overall enrichment factor of the first percent (EF1) of 36.14 and an area under the curve (AUC) value of 0.81 on the DUD-E data set, as well as an EF1 of 15.44 and an AUC of 0.69 on the maximum unbiased validation (MUV) data set, outperforming the control methods that are based on single descriptors. Thus, our study provides a new framework for multiple feature integration, which can benefit ligand-similarity-based virtual screening. LigMate is freely available for noncommercial users at http://cao.labshare.cn/ligmate/.

CB-Dock: a web server for cavity detection-guided protein-ligand blind docking.

As the number of elucidated protein structures is rapidly increasing, the growing data call for methods to efficiently exploit the structural information for biological and pharmaceutical purposes. Given the three-dimensional (3D) structure of a protein and a ligand, predicting their binding sites and affinity are a key task for computer-aided drug discovery. To address this task, a variety of docking tools have been developed. Most of them focus on docking in the preset binding sites given by users. To automatically predict binding modes without information about binding sites, we developed a user-friendly blind docking web server, named CB-Dock, which predicts binding sites of a given protein and calculates the centers and sizes with a novel curvature-based cavity detection approach, and performs docking with a popular docking program, Autodock Vina. This method was carefully optimized and achieved ~70% success rate for the top-ranking poses whose root mean square deviation (RMSD) were within 2 Å from the X-ray pose, which outperformed the state-of-the-art blind docking tools in our benchmark tests. CB-Dock offers an interactive 3D visualization of results, and is freely available at http://cao.labshare.cn/cb-dock/.

xVis: a web server for the schematic visualization and interpretation of crosslink-derived spatial restraints.

The identification of crosslinks by mass spectrometry has recently been established as an integral part of the hybrid structural analysis of protein complexes and networks. The crosslinking analysis determines distance restraints between two covalently linked amino acids which are typically summarized in a table format that precludes the immediate and comprehensive interpretation of the topological data. xVis displays crosslinks in clear schematic representations in form of a circular, bar or network diagram. The interactive graphs indicate the linkage sites and identification scores, depict the spatial proximity of structurally and functionally annotated protein regions and the evolutionary conservation of amino acids and facilitate clustering of proteins into subcomplexes according to the crosslink density. Furthermore, xVis offers two options for the qualitative assessment of the crosslink identifications by filtering crosslinks according to identification scores or false discovery rates and by displaying the corresponding fragment ion spectrum of each crosslink for the manual validation of the mass spectrometric data. Our web server provides an easy-to-use tool for the fast topological and functional interpretation of distance information on protein complex architectures and for the evaluation of crosslink fragment ion spectra. xVis is available under a Creative Commons Attribution-ShareAlike 4.0 International license at http://xvis.genzentrum.lmu.de/.