MIA: An Open Source Standalone Deep Learning Application for Microscopic Image Analysis

In recent years the amount of data generated by imaging techniques has grown rapidly along with increasing computational power and the development of deep learning algorithms. To address the need for powerful automated image analysis tools for a broad range of applications in the biomedical sciences, we present the Microscopic Image Analyzer (MIA). MIA combines a graphical user interface that obviates the need for programming skills with state-of-the-art deep learning algorithms for segmentation, object detection, and classification. It runs as a standalone, platform-independent application and is compatible with commonly used open source software packages. The software provides a unified interface for easy image labeling, model training and inference. Furthermore the software was evaluated in a public competition and performed among the top three for all tested data sets. The source code is available on https://github.com/MIAnalyzer/MIA.

Non-microbiological turbidity of beer: Part 2 – a case study

Non-microbial beer turbidity of lager beers often indicates a technological problem. Therefore, the occurrence of permanent haze in filtered and stabilized beer should not be underestimated. In this study, practical examples from industrial breweries, where several types of non-microbiological haze of colloidal were identified, are presented. These examples of haze were caused by slightly different factors, and as a result, they had a different microscopic image. It is often accompanied by mechanical impurities and sometimes by microorganisms that function as nucleation centers. Moreover, a very interesting example of almost brilliant permanent beer haze caused by the destruction of yeast cells with the following pouring intracellular contents of cells into beer is introduced. This phenomenon, which could be called “precedent”, was caused by a bad physiological condition of yeasts cells and inappropriately chosen yeast separation technology.

Rapid and concise quantification of mycelial growth by microscopic image intensity model and application to mass cultivation of fungi

The microbial food fermentation industry requires real-time monitoring and accurate quantification of cells. However, filamentous fungi are difficult to quantify as they have complex cell types such as pellet, spores, and dispersed hyphae. In this study, numerous data of microscopic image intensity (MII) were used to develop a simple and accurate quantification method of Cordyceps mycelium. The dry cell weight (DCW) of the sample collected during the fermentation was measured. In addition, the intensity values were obtained through the ImageJ program after converting the microscopic images. The prediction model obtained by analyzing the correlation between MII and DCW was evaluated through a simple linear regression method and found to be statistically significant (R2 = 0.941, p < 0.001). In addition, validation with randomly selected samples showed significant accuracy, thus, this model is expected to be used as a valuable tool for predicting and quantifying fungal growth in various industries.

Profile Microscopic Profile of Mice (Mus Musculus) Kidney Tissue Fixed with 10% Honey Concentration for 24 Hours

Fixation is used to maintain tissue structure in its original form “life-like state” and can protect proteins and tissue components from degeneration. The solution commonly used is 10% NBF. Formaldehyde is chemical substance that is toxic and not environmentally friendly, several studies have shown alternative substitutes fixation, one of which is the honey solution. The study of Mohammed et al (2020) fixated tissue with honey 10% and 20% shown good coloring properties and similar clarity to fixated with formalin 10%. Honey has acidic and dehydrating properties allow most microorganisms to be killed so that tissues will last for a long time. The research objective is to findout the description of microscopic of mice (Mus musculus) kidney tissue which were fixation using 10% honey solution for 24 hours. The research is included in qualitative descriptive research. The research design used was a non-eksperimental with a purposive sampling study approach. The sample used was 32 preparation with total of microscopic overview is 160. Microscopic image of mice (Mus musculus) kidney tissue fixed using 10% honey solution for 24 hours in 80 visual fields were 12.5% of the preparations is not good and 87.5% is good preparations. The microscopic image of mice (Mus musculus) kidney tissue fixed using 10% NBF is better than of the microscopic image of mice (Mus musculus) kidney tissue fixed with 10% honey for 24 hours.

Binocular Indirect Fundus Microscope in Vitreoretinal Surgery

With the rapid development of computer technology, the application of computer technology in various fields is more and more common, and it also plays an increasingly important role in biomedicine. In recent years, microscopic image processing has always been an important part of biomedicine, and binocular indirect fundus microscope is playing an increasingly important role in vitreoretinal surgery. The purpose of this paper is to study the application effect of binocular indirect fundus microscope in vitreoretinal surgery, and to master the role of binocular indirect fundus microscope, which is important for biomedicine. This paper studies the effect of binocular indirect fundus microscope in vitreoretinal surgery through the study of the role of vitreous and binocular indirect fundus microscope, as well as the investigation of experimental methods. It highlights that the effect of binocular indirect fundus microscope is better than that of direct microscope in retinal surgery.The results show that binocular indirect fundus microscope is more suitable for vitreoretinal surgery. 85% of the patients with vitreoretinal surgery have better effect after surgery. No matter from the comparison of visual acuity improvement or retinal thickness, binocular indirect fundus microscope has better effect in vitreoretinal surgery. It also provides reference for how to prevent vitreoretinal diseases disease has positive significance. We expect to produce effective methods as soon as possible to solve the problems related to vitreous diseases, which can bring the bright future to ophthalmic patients.

Rapid and Concise Quantification of Mycelial Growth by Microscopic Image Intensity Model and Application to Mass Cultivation of Fungi

The microbial food fermentation industry requires real-time monitoring and accurate quantification of cells. However, filamentous fungi are difficult to quantify as they have complex cell types such as pellet, spores, and dispersed hyphae. In this study, numerous data of microscopic image intensity (MII) were used to develop a simple and accurate quantification method of Cordyceps mycelium. The dry cell weight (DCW) of the sample collected during the fermentation was measured. In addition, the intensity values were obtained through the ImageJ program after converting the microscopic images. The prediction model obtained by analyzing the correlation between MII and DCW was evaluated through a simple linear regression method and found to be statistically significant (R2 = 0.941, p <0.001). In addition, validation with randomly selected samples showed significant accuracy, thus, this model is expected to be used as a valuable tool for predicting and quantifying fungal growth in various industries.

Multi-Fusion Approach for Wood Microscopic Images Identification Based on Deep Transfer Learning

With the wide increase in global forestry resources trade, the demand for wood is increasing day by day, especially rare wood. Finding a computer-based method that can identify wood species has strong practical value and very important significance for regulating the wood trade market and protecting the interests of all parties, which is one of the important problems to be solved by the wood industry. This article firstly studies the establishment of wood microscopic images dataset through a combination of traditional image amplification technology and Mix-up technology expansion strategy. Then with the traditional Faster Region-based Convolutional Neural Networks (Faster RCNN) model, the receptive field enhancement Spatial Pyramid Pooling (SPP) module and the multi-scale feature fusion of Feature Pyramid Networks (FPN) module are introduced to construct a microscopic image identification model based on the migration learning fusion model and analyzes the three factors (Mix-up, Enhanced SPP and FPN modules) affecting the wood microscopic image detection model. The experimental results show that the proposed approach can identify 10 kinds of wood microscopic images, and the accuracy rate has increased from 77.8% to 83.8%, which provides convenient conditions for further in-depth study of the microscopic characteristics of wood cells and is of great significance to the field of wood science.

Non-microbiological turbidity of beer: Part 1 – semireview

Beer is a complex mixture consisting of hundreds of chemical substances. Some of them are macromolecules, such as proteins and polysaccharides that together with polyphenolic compounds form poorly soluble complexes causing beer turbidity or cold colloidal turbidity. Furthermore, beer turbidity can be caused also by procedural particles entering into beer during brewing process (filtration and stabilization aids) or by foreign particles from external environment (mechanical impurities). If turbidity, sediment or individual particles occur in filtered and stabilized beer, their origin must be determined since brilliant visual impression of the filtered beer influences an opinion of customers on a specific product. The identification of different species of turbidity using microscopic image, particle staining, enzymatic analysis or identification precursors is clearly described in this paper. The study includes pictorial documentation of various particles that may be part of beer turbidity.