Modified UNet Model for Brain Stroke Lesion Segmentation on Computed Tomography Images

The task of segmentation of brain regions affected by ischemic stroke is help to tackle important challenges of modern stroke imaging analysis. Unfortunately, at the moment, the models for solving this problem using machine learning methods are far from ideal. In this paper, we consider a modified 3D UNet architecture to improve the quality of stroke segmentation based on 3D computed tomography images. We use the ISLES 2018 (Ischemic Stroke Lesion Segmentation Challenge 2018) open dataset to train and test the proposed model. Interpretation of the obtained results, as well as the ideas for further experiments are included in the paper. Our evaluation is performed using the Dice or f1 score coefficient and the Jaccard index. Our architecture may simply be extended to ischemia segmentation and computed tomography image identification by selecting relevant hyperparameters. The Dice/f1 score similarity coefficient of our model shown 58% and results close to ground truth which is higher than the standard 3D UNet model, demonstrating that our model can accurately segment ischemic stroke. The modified 3D UNet model proposed by us uses an efficient averaging method inside a neural network. Since this set of ISLES is limited in number, using the data augmentation method and neural network regularization methods to prevent overfitting gave the best result. In addition, one of the advantages is the use of the Intersection over Union loss function, which is based on the assessment of the coincidence of the shapes of the recognized zones.     

Features of Polymethacrylic Acid and Poly-2-Methyl-5-Vinylpyridine Hydrogels Remote Interaction in an Aqueous Medium

The remote interaction of polymethacrylic acid hydrogel with a poly-2-methyl-5-vinylpyridine hydrogel was studied. The aim of work was to study the dependence of the swelling coefficient, the conductivity and the pH of the water solutions of intergel system at different mass ratios from time were studied. The goal was achieved by using following methods： pH-metry, conductometry and gravimetry.     

Swelling Behavior and Complex Formation Ability of Ternary Amphoteric Gels based on Allylamine Derivatives and Maleic Acid

Summary: The swelling behavior of an amphoteric gel composed of 50 mol‐% of maleic acid (MA), 25 mol‐% of N,N′‐dimethyldiallylammonium chloride (DMDAAC) and 25 mol‐% of diallylamine (DAA) was studied in aqueous and aqueous‐salt solutions. The isoelectric point (IEP) of the MA‐DMDAAC‐DAA gel determined from swelling experiments was about pH 4.6. Considerable gel swelling with increasing ionic strength was observed at the IEP. Dynamic swelling properties of the amphoteric gel in water with and without added salt were measured at various pH values including the IEP. The swelling behavior of the amphoteric gel was found to depend on the ionization state of the functional groups. It can be described by either a relaxation‐controlled or non‐Fickian (anomalous) mechanism. Swelling‐deswelling properties of the amphoteric gel were also studied in mixtures of water and organic solvents. The amphoteric gel was able to complex sodium poly(styrene sulfonate), sodium lauryl sulfate, the cationic drug richlocain, and the bivalent transition metal ions Cu²⁺, Ni²⁺, Co²⁺, and Zn²⁺. The sorption of polyelectrolyte, surfactant, drug, and metal ions by the amphoteric gel is accompanied by the contraction of the gel network. Partial release of the cationic drug molecules entrapped into the gel volume takes place at the IEP of the amphoteric gel with low activation energy, while neither the anionic polyelectrolyte nor the surfactants are released from the gel interior at the IEP. The swelling‐shrinking behavior of gel‐polyelectrolyte and gel‐surfactant complexes in dependence of pH and ionic strength of the outer solution is similar.

     

A regular,hydrophobically modified polyampholyte as novel pour point depressant

A new regular polyampholyte, namely poly(N,N‐diallyl‐N‐octadecylamine‐alt‐(maleic acid)), was studied as an additive to crude oil. The amphiphilic polyampholyte proved to be an efficient pour point depressant, to inhibit the deposition of wax, and to improve the viscosity of waxy crude oil from the Akshabulak oilfield (Western Kazakhstan). On optimizing the concentration of the polymer, both the kinematical viscosity and the pour point of waxy crude oils were found to be strongly decreased. The morphology of the paraffin aggregates formed was compared before and after heat treatment of the waxy crude oils, in the presence and the absence of the polymer. The rheological characteristics of the waxy crude oil were markedly improved, in particular, by decreasing the plastic viscosity and the yield stress values upon addition the polymer. The inhibition of wax deposits in the presence of the amphiphilic polyampholyte was interpreted in terms of its interference with the wax crystallization process because of the formation of inverse micellar structures. Although the interaction of the cationic and the anionic groups on the polymer backbone stabilizes the smaller size of the aggregates, the hydrophobic side chains of the polymer provide nucleation sites and cocrystallize with the paraffins, thus modifying the paraffin crystal structure. © 2005 Wiley Periodicals, Inc. J Appl Polym Sci 98: 2101–2108, 2005