Medical image semantic segmentation based on deep learning

The image semantic segmentation has been extensively studying. The modern methods rely on the deep convolutional neural networks, which can be trained to address this problem. A few years ago networks require the huge dataset to be trained. However, the recent advances in deep learning allow training networks on the small datasets, which is a critical issue for medical images, since the hospitals and research organizations usually do not provide the huge amount of data. In this paper, we address medical image semantic segmentation problem by applying the modern CNN model. Moreover, the recent achievements in deep learning allow processing the whole image per time by applying concepts of the fully convolutional neural network. Our qualitative and quantitate experiment results demonstrated that modern CNN can successfully tackle the medical image semantic segmentation problem.

     

A base for building codes and construction methods in karst-prone regions

The history of the development of methodical and regulatory documents relative to construction in karst-prone areas is cited. The basic content of existing regulatory documents is presented, and attention is focused on some of their deficiencies. Specific approaches to the development of a standard for construction in karst-prone areas are proposed. __________ Translated from Osnovaniya, Fundamenty i Mekhanika Gruntov, No. 6, pp. 21–24, November–December, 2006.     

Spatial distributions of the intensity of optical emission lines studied during bismuth ferrite film deposition in high-frequency discharge plasma

We have studied spatial distributions of the intensity of optical emission lines in plasma of the RF discharge in oxygen during the deposition of bismuth ferrite (BiFeO₃) films. The intensities of characteristic emission lines in the visible, near-UV and near-IR spectral ranges have been measured as functions of the distance from the probed plasma layer to the target. The intensity profiles of the emission lines of oxygen ions, oxygen atoms, and iron atoms exhibit different behavior. Differences in the spatial distributions of intensity have been also observed for the two characteristic emission lines (at 613.7 and 688.6 nm) of iron.     

Ion funnel trap interface for orthogonal time-of-flight mass spectrometry

A combined electrodynamic ion funnel and ion trap coupled to an orthogonal acceleration (oa)-time-of-flight mass spectrometer was developed and characterized. The ion trap was incorporated through the use of added terminal electrodynamic ion funnel electrodes enabling control over the axial dc gradient in the trap section. The ion trap operates efficiently at a pressure of approximately 1 Torr, and measurements indicate a maximum charge capacity of approximately 3 x 10(7) charges. An order of magnitude increase in sensitivity was observed in the analysis of low concentration peptides mixtures with orthogonal acceleration (oa)-time-of-flight mass spectrometry (oa-TOF MS) in the trapping mode as compared to the continuous regime. A signal increase in the trapping mode was accompanied by reduction in the chemical background, due to more efficient desolvation of, for example, solvent related clusters. Controlling the ion trap ejection time was found to result in efficient removal of singly charged species and improving signal-to-noise ratio (S/N) for the multiply charged analytes.     

Peculiarities of film growth in glow discharge with runaway electrons

We have studied the properties of films deposited in gas discharge with a beam of runaway electrons and observed for the first time an anomalous behavior of the intensity of a probing light beam reflected from a film on substrate upon switching off of the discharge. The observed phenomenon is interpreted in the framework of a two-layer model of the film growth on a substrate, according to which an optically homogeneous surface layer of unknown nature appears on the film during growth in discharge and fully decomposes when the discharge is switched off.     

Thermodynamics of methane adsorption on X type zeolites at supercritical temperatures

Methods describing isotherms and thermodynamic properties of methane adsorption on various cationic forms of X-type zeolite at temperatures above critical ones are considered.     

Mass measurement accuracy in analyses of highly complex mixtures based upon multidimensional recalibration

Mass spectrometry combined with a range of on-line separation techniques has become a powerful tool for characterization of complex mixtures, including protein digests in proteomics studies. Accurate mass measurements can be compromised due to variations that occur in the course of an on-line separation, e.g., due to excessive space charge in an ion trap, temperature changes, or other sources of instrument "drift". We have developed a multidimensional recalibration approach that utilizes existing information on the likely mixture composition, taking into account variable conditions of mass measurements, and that corrects the mass calibration for sets of individual peaks binned by, for example, the total ion count for the mass spectrum, the individual peak abundance, m/z value, and liquid chromatography separation time. The multidimensional recalibration approach uses a statistical matching of measured masses in such measurements, often exceeding 105, to a significant number of putative known species likely to be present in the mixture (i.e., having known accurate masses), to identify a subset of the detected species that serve as effective calibrants. The recalibration procedure involves optimization of the mass accuracy distribution (histogram), to provide a more confident distinction between true and false identifications. We report the mass accuracy improvement obtained for data acquired using a TOF and several FTICR mass spectrometers. We show that the multidimensional recalibration better compensates for systematic mass measurement errors and also significantly reduces the mass error spread: i.e., both the accuracy and precision of mass measurements are improved. The mass measurement improvement is found to be virtually independent of the initial instrument calibration, allowing, for example, less frequent calibration. We show that this recalibration can provide sub-ppm mass measurement accuracy for measurements of a complex fungal proteome tryptic digest and provide improved confidence or numbers of peptide identifications.     

A noncavity scheme of optical detection of high-frequency magnetic and cyclotron resonances in semiconductors and nanostructures

To perform optical detection of high-frequency magnetic resonance (ODMR) and cyclotron resonance (ODCR) with a spatial resolution, we have proposed a noncavity scheme of an ODMR-ODCR spectrometer using a quasi-optical microwave channel. The efficiency of this scheme for obtaining information on the spin properties of ZnO quantum dots and CdMnTe quantum wells and on the effective masses of carriers in crystalline silicon films with a spatial resolution within a focused laser beam is illustrated.