Background: Antinuclear antibody pattern recognition is vital for autoimmune disease diagnosis but labor-intensive for manual interpretation. To develop an automated pattern recognition system, we established machine learning models based on the International Consensus on Antinuclear Antibody Patterns (ICAP) at a competent level, mixed patterns recognition, and evaluated their consistency with human reading. Methods: 51,694 human epithelial cells (HEp-2) cell images with patterns assigned by experienced medical technologists collected in a medical center were used to train six machine learning algorithms and were compared by their performance. Next, we choose the best performing model to test the consistency with five experienced readers and two beginners. Results: The mean F1 score in each classification of the best performing model was 0.86 evaluated by Testing Data 1. For the inter-observer agreement test on Testing Data 2, the average agreement was 0.849 (?) among five experienced readers, 0.844 between the best performing model and experienced readers, 0.528 between experienced readers and beginners. The results indicate that the proposed model outperformed beginners and achieved an excellent agreement with experienced readers. Conclusions: This study demonstrated that the developed model could reach an excellent agreement with experienced human readers using machine learning methods.

A low-temperature solution approach (90-95 degrees C) using FeCl(3) and urea was carried out to synthesize beta-FeOOH nanorods in aqueous solution. The as-synthesized beta-FeOOH nanorods were further calcined at 300 degrees C to form porous nanorods with compositions including both beta-FeOOH and alpha-Fe(2)O(3). The derived porous nanorods were engineered to assemble with four layers of polyelectrolytes (polyacrylic acid (PAA)/polyethylenimine(PEI)/PAA/PEI) on their surfaces as polyelectrolyte multilayer nanocapsules. Fluorescein isothiocyanate (FITC) molecules were loaded into the polyelectrolyte multilayer nanocapsules in order to investigate drug release and intracellular delivery in Hela cells. The as-prepared nanocapsules showed ionic strength-dependent control of the permeability of the polyelectrolyte shells. The release behavior of the entrapped FITC from the FITC-loaded nanocapsules exhibited either controlled- or sustained-release trends, depending on the compactness of the polyelectrolyte shells on the nanorod surfaces. Cytotoxicity measurements demonstrate that the native nanorods and the polymer-coated nanorods have excellent biocompatibility in all dosages between 0.1 ng mL(-1) and 100 microgm L(-1). The time dependence of uptake of FITC-loaded nanocapsules by Hela cancer cells observed by laser confocal microscopy indicates that the nanocapsules can readily be taken up by cancer cells in 15 min, a relatively short period of time, while the slow release of the FITC from the initial perimembrane space into the cytoplasm was followed by release into the nucleus after 24 h.

A new cholesterol organogelator 4 was synthesized and its gelation property was evaluated. It was confirmed that 4 was an effective gelator for various organic solvents and could self-assemble into network fibers with a bilayer of folded conformation in some organic solvents. Moreover, organogelator 4 could act as a template for the synthesis of novel pearl-necklace porous CdS nanofibers. The transcription process of organogel fibers into CdS nanofibers was investigated, and it was found that Cd2+ ions were coated on the organogel fibers by the interaction with ester groups of 4, which might lead to the change of the arrangement of the organogelator and seemed to serve as nucleation sites for metalization. The further growth of CdS began with these nucleation sites along the organogel fibers. Meanwhile, parts of 4 free from organogel fibers have an effect on the formation of the CdS nanofibers consisting of the network and wormlike CdS particles.

Abstract-Work on decentralized discrete-event control systems is extended to handle the case when, instead of always observing or never observing an event, a supervisor may observe only some occurrences of a particular event. Results include a necessary and sufficient condition for solving this version of the decentralized problem (which is analogous to the co-observability property used in the standard version of the problem) and a method for checking when this condition holds. In this paper, whether an event is observed by a given agent is dependent on that agent's state (or the string of events that agent has seen so far). This model of event observation is applicable to problems where a supervisor communicates observations of event occurrences to another supervisor to help the other one make control decisions.

No abstract