A novel transfer learning approach for the classification of histological images of colorectal cancer

Colorectal cancer (CRC) is the second most diagnosed cancer in the United States. It is identified by histopathological evaluations of microscopic images of the cancerous region, relying on a subjective interpretation. The Colorectal Histology dataset used in this study contains 5000 images, made available by the University Medical Center Mannheim. This approach proposes the automatic identification of eight types of tissues found in CRC histopathological evaluation. We apply Transfer Learning from architectures of Convolutional Neural Networks (CNNs). We modify the structures of CNNs to extract features from the images and input them to well-known machine learning methods: Naive Bayes, Multilayer Perceptron, k-Nearest Neighbors, Random Forest, and Support Vector Machine (SVM). We evaluated 108 extractor–classifier combinations. The one that achieved the best results is DenseNet169 with SVM (RBF), reaching an Accuracy of 92.083% and F1-Score of 92.117%. Therefore, our approach is capable of distinguishing tissues found in CRC histopathological evaluation.

     

The Efficiency of Application Nanosilver in Technological Processes of Making Red Wine

The efficiency of using nanostructured silver in technological processes of making red wine has been studied with the purpose of substituting sulfur dioxide. For preparation of research objects, we used dry wine material of red grape variety ＂Saperavi＂. After completion of malolactic fermentation, the second racking the wine material off the lees and its treatment with antiseptics were carried out. Sulfur dioxide （Kadifit） and different doses of nanostructured silver were used. Microbiological investigation was performed on the presence of lactic bacteria after completion of malolactic fermentation and racking off the lees. The investigation of phenolic compounds was conducted at the following stages of technological processes： （1） after completion of alcoholic fermentation and racking off the lees; （2） after completion of malolactic fermentation; （3） after the second racking off the lees and treatment with antiseptics. By means of the HPLC analysis, the amounts ofcatechins, phenolcarbonic acids and flavonols were determined. It has been established that after conduction of malolactic fermentation in the process of racking the wine material off the lees and storage, the application of 0.6 mg/L of nano-silver for blocking of lactic-acid bacteria and inhibition of oxidation of phenolic compounds has the same effect as sulfitization with 50 mg/L of Kadifit.     

Modulating the Ferromagnet/Molecule Spin Hybridization Using an Artificial Magnetoelectric

Spin‐polarized charge transfer at the interface between a ferromagnetic (FM) metal and a molecule can lead to ferromagnetic coupling and to a high spin polarization at room temperature. The magnetic properties of these interfaces can not only alter those of the ferromagnet but can also stabilize molecular spin chains with interesting opportunities toward quantum computing. With the aim to enhance an organic spintronic device's functionality, external control over this spin polarization may thus be achieved by altering the ferromagnet/molecule interface's magnetic properties. To do so, the magnetoelectric properties of an underlying ferroelectric/ferromagnetic interface are utilized. Switching the ferroelectric polarization state of a PbZr_0.2Ti_0.8O₃ (PZT) bottom layer within a PZT/Co/FePc‐based (Pc ‐ phthalocyanine) device alters the X‐ray magnetic circular dichroism of the Fe site within the phthalocyanine molecular top layer. Thus, how to electrically alter the magnetic properties of an interface with high spin polarization at room temperature is demonstrated. This expands electrical control over spin‐polarized FM/molecule interfaces, which is first demonstrated using ferroelectric molecules, to all molecular classes.     

Telecommunications' role in national development in Ghana

Ghana has recognized the need for efficient and reliable telecommunication services. The widespread availability of these services will promote the nation's economic advancement and the decentralization of the government's activities. To achieve the objective of bringing telecommunications to all the people of Ghana, private sector participation is considered essential as a source of management skills, technology, and financing that will be required for the provision of services. In order to attract such participation, Ghana is putting in place the necessary policy, institutional, and regulatory frameworks to create an enabling environment for private sector investment in the telecommunication sector     

The use of inductively coupled plasma mass spectrometry (ICP-MS) for the determination of toxic and essential elements in different types of food samples

This paper describes a simple method for the determination of sixteen elements in food samples by using inductively coupled plasma spectrometry (ICP-MS). Prior to analysis, 100–250 mg of powdered food samples were accurately weighed into a Teflon digestion vessel. Then, 4 ml of 20% v/v concentrated nitric acid and 2 ml of hydrogen peroxide were added. Decomposition of samples was carried out in a microwave digestion system. In order to verify the accuracy and precision of the proposed method, five Standard Reference Materials from the National Institute of Standards and Technology (NIST) (Whole Egg Powder RM 8415, Rice Flour SRM 1568a, Typical Diet SRM 1548a, Wheat Flour SRM 1567a and Bovine Muscle Powder RM 8414) were analyzed. Additional validation data are provided based on the analysis of 18 different types of food samples by the proposed method and using comparative methods with AAS as the detector.     

Automatic Detection of COVID-19 Infection Using Chest X-Ray Images Through Transfer Learning

The new coronavirus(COVID-19),declared by the World Health Organization as a pandemic,has infected more than 1 million people and killed more than 50 thousand.An infection caused by COVID-19 can develop into pneumonia,which can be detected by a chest X-ray exam and should be treated appropriately.In this work,we propose an automatic detection method for COVID-19 infection based on chest X-ray images.The datasets constructed for this study are composed of194 X-ray images of patients diagnosed with coronavirus and 194 X-ray images of healthy patients.Since few images of patients with COVID-19 are publicly available,we apply the concept of transfer learning for this task.We use different architectures of convolutional neural networks(CNNs)trained on Image Net,and adapt them to behave as feature extractors for the X-ray images.Then,the CNNs are combined with consolidated machine learning methods,such as k-Nearest Neighbor,Bayes,Random Forest,multilayer perceptron(MLP),and support vector machine(SVM).The results show that,for one of the datasets,the extractor-classifier pair with the best performance is the Mobile Net architecture with the SVM classifier using a linear kernel,which achieves an accuracy and an F1-score of 98.5%.For the other dataset,the best pair is Dense Net201 with MLP,achieving an accuracy and an F1-score of 95.6%.Thus,the proposed approach demonstrates efficiency in detecting COVID-19 in X-ray images.     

The importance for food security of maintaining rust resistance in wheat

Wheat is one of the main sources of calories and protein of the world’s population and therefore the pathogens that cause rust diseases of the crop are a real threat to food security. Besides the continuous evolution of rust pathogens which repeatedly results in overcoming the resistance of commercial varieties throughout the world, plant breeders are also now challenged by the impacts of global climatic changes. Agricultural practices will need to keep pace with the intensification of sustainable food production in order to face the challenge of feeding a world population estimated to reach about nine billion by 2050. Contemporary wheat breeding has increasingly focused on the future, culminating in the emergence of a global partnership for breeding new wheat varieties with resistance to rust pathogens. Plant breeding now employs a wide range of both long-established and frontier technologies aimed at achieving the United Nations Millennium Development Goals of ending hunger and extreme poverty (MDG1), while concurrently promoting environmental sustainability (MDG7) through global partnerships for development (MDG8).     

Characterisation of lactic acid bacteria isolated from the Georgian,yoghurt‐like Matsoni

Matsoni is a traditional Caucasian fermented milk product, characterised by a lactic acid bacteria (LAB) microbiota. Objectives of the present study were to isolate and identify the LAB of Matsoni samples collected from various Georgian areas and to study their technological characteristics. About 300 LAB from 71 samples of Matsoni were isolated and characterised. The species most representatives were Lactobacillus delbrueckii, Streptococcus thermophilus and Lactobacillus rhamnosus. This study highlighted a high degree of biodiversity and a specific geographical distribution of the dominant LAB present in artisanal Matsoni. Some strains showed technological features useful to design a multistrain starter culture for Matsoni.