Current Signal Transduction Therapy - Volume 16, Issue 2, 2021

Background: The present study proceeds to incorporate feature selection as a means for selecting the most relevant features affecting the prediction of cash prices in Iran in terms of health economics. Health economics is an academic field that aids in ameliorating health conditions so as to make better decisions in regard to the economy such as determining cash prices. Methods: Accordingly, a series of search algorithms, namely the Best-First, Greedy-Stepwise, and Ranker methods, are deployed in order to extract the most relevant features from among 500 data samples. The validity of the methods was evaluated via the LMT procedure. The corresponding dataset used for this study constitutes a variety of features including net cash flow, dividends, revenue from short and long-term deposits, cash flow from investment returns, income tax, fixed asset purchases, fixed asset sales, long-term investment purchases, long-term investment sales, total cash flow from investment activities, financial facilities, and repayment of financial facilities. Results: The results were indicative of the superiority of the Ranker model using the RelieFAttribute- Eval tool in Weka over the remaining classification methods. Ergo, the LMT approach could be employed to remove data redundancies and accelerate the estimation process, while saving time and money. The results of the multi-layer perceptron (MLP) further confirmed the high accuracy of the proposed method in estimating cash prices. Conclusion: The present research attempts to reduce the volume of data required for predicting the end cash by means of employing a feature selection method so as to save both the precious money and time.

Introduction: Recently, deep learning based methods have become an important approach to the accurate analysis of medical images. Materials and Methods: This paper provides a comprehensive survey of the most important deep learning based methods that have been developed for medical image processing. A number of important contributions made in the last five years are summarized and surveyed. Results: Specifically, deep learning-based algorithms developed for image segmentation, image classification, registration, object detection and other important problems are reviewed. Conclusion: In addition, an overview of challenges that currently exist in the field and potential directions for future research is provided at the end of the survey.

Background: Multi-Service Streams Network (MSSN) has become such a popular technique in modern applications including, medical fields for E-health applications, such as medical systems and patient monitoring network systems. Recent E-health researches intend to compare MSSN data communications with traditional methods such as the internet. Methods: Based on the above-mentioned fact, the proposed work in this paper is directed to obtain a detailed analysis of the MSSN applied over E-health, using the G/G/1 analysis method, including traffic probabilistic-time characteristics to establish its self-similar processes. Moreover, the paper proposes the purpose of estimating the queue service efficiency and overload management by the essential criterion, which takes into account the time delay, time jitter, and the packet loss probability expected in the E-health applications. Based on the necessary standard for the proposed uses, the results of queue operations and also relevant buffer space algorithms are evaluated. Moreover, the estimated qualitative measurement of the network development for the proposed model is obtained and compared with the most common techniques adapted in E-health applications. Results: The collected results show that MSSN is an applicable technique to be applied over the Ehealth applications mainly on its excellent time delay, jitter, packet losses probability, and others. Conclusion: The main aim of this paper is to obtain a fully detailed analysis of the MSSN that is applied over E-health applications, using the mass service capacity for the mathematical model class G/G/1 in the most general case of a single-channel system.

The serum and glucocorticoid inducible protein kinase (SGK) family signals downstream of phosphoinositide-3-kinase (PI3K) and is made up of three isoforms: SGK1, 2, and 3. respectively, and their activity is dependent on growth factor activation. Among these SGK families, one such potential target and a less explored enzyme is SGK3. SGK3 regulates a range of basic cellular processes, such as cell proliferation, migration and survival, thus playing an important role in cancer development. These kinase-signaling pathways present both opportunities and challenges for cancer therapy. In this paper, we reviewed the status of SGK3 regulation and its role in normal cell physiology and transformation. In addition, the potential roles of SGK3 signal transduction in breast cancer and prostate cancer are discussed.

Background: With the enhancement in manageability and robustness, ultrasound discovers growing usage in an eclectic variety of applications. The capability to accomplish and construe an outsized variability of ultrasound investigations is marvelously revealed by Physicians, nurses and medical officers, and the use of ultrasound in the developing world is unequivocally supported by a growing body of literature. This paper delivers a general idea of the technological and engineering developments that succor in the progression of ultrasonic applications. This paper reviews the prevailing literature in the aid of ultrasound use in the emerging biosphere. It also endorses imminent guidelines for ultrasound usage and exploration in order to develop investigative capability and patient care in the utmost far-flung regions of the world. Methods: A well-thought-out examination of bibliographic records in quest of peer-reviewed research accomplishments by means of an intensive assessment interrogation was carried out. Good quality papers were included in the review based on their features. With the intention of analyzing the verdicts of the considered investigations, we employed an inferential scrutiny approach centered on the quality of the content. Results: A total of 152 papers were included in this review, including a massive volume of literature works on various ultrasonic applications. These ultrasonic applications included food processing, cleaning, and nanostructured material synthesis along with a variety of therapeutic and clinical applications. This review identified the captivating improvements and ground-breaking applications of ultrasound worldwide together with a few of its prospective applications. Conclusion: The utilization of ultrasound in processing crafts innovative and attention-grabbing approaches, which have an eclectic scope for further research both from industrial and academic perspectives. Various areas, for instance: crystallization, degassing, drying, extraction, filtration, freezing, homogenization, meat tenderization, sterilization, etc.; have been acknowledged with prodigious potential for forthcoming improvements in food processing and preservation. Enriched extraction of heat-sensitive bioactive and food constituents at lower processing temperatures can be carried out using UAE. There is also a prospective for attaining concurrent extrication and encapsulation of extracted constituents via ultrasonic. Nevertheless, its utilization in the diagnosis of certain syndromes still remains controversial. In the near future, tumor ablation would necessitate the most important use of high intensity focused ultrasound in medicine. These applications, predominantly the treatment of uterine fibroids, are projected to encounter stretched out usage globally. With the proliferation of additional ablation techniques, a number of electrifying enhancements and innovative applications lie on the vista; together with application for targeted drug delivery and gene therapies, and treatment of an eclectic variety of brain ailments. There is an urgent need to broaden the research to assess the impression of ultrasound in resource-limited settings in the arena of Clinician-performed bedside ultrasonography in an attempt to draw inferences regarding the long-term sustainability and further expansion of ultrasound programs in the developing world. Ultrasonic processing, still in its embryonic stage, entails significant future research with the aim of developing technology and elucidating the effects of ultrasound.

The main objective of image fusion for multimodal medical images is to retrieve valuable information by combining multiple images obtained from various sources into a single image suitable for better diagnosis. In this paper, a detailed survey on various existing medical image fusion algorithms, with a comparative discussion is presented. Image fusion algorithms available in the current literature are categorized into various methods known as (1) morphological methods, (2) human value system operator based methods, (3) sub-band decomposition methods, (4) neural n++32w1etwork based methods, and (5) fuzzy logic based methods. This research concludes that even though there exist a few open-ended creative and logical difficulties, the fusion of medical images in many combinations assists in utilizing medical image fusion for medicinal diagnostics and examination. There is a tremendous progress in the fields of deep learning, artificial intelligence and bio-inspired optimization techniques. Effective utilization of these techniques can be used to further improve the efficiency of image fusion algorithms.

Background: Long non-coding ribonucleic acid (lncRNA) are known as similar transcripts of messenger RNA (mRNA) whose size discrepancy is between 100 and 200 nucleotides. Recent studies in this area have revealed that lncRNAs are involved in cancer tumorigenesis and progression. Such molecules are transcribed from genome regions that lack open reading frame (ORF) and fail to encode any protein. LncRNAs are characterized by tumorigenic behaviors, which can be considered as new biomarkers. Among all types of thyroid cancer (TC), papillary thyroid carcinoma (PTC) is the most common one. Methods: This review was prepared via searching of the databases of Science Direct, Directory of Open Access Journals (DOAJ), Google Scholar, Pub-Med (NLM), Scopus, Web of Science, and hand searching using relative keywords. The selected papers were fully reviewed and the required information for the review was extracted and summarized. Results: Previous studies indicated that BRAF-activated non-protein coding RNA (BANCR) expression had been increased in thyroid tumors compared with adjacent normal tissues. Additionally, BANCR had mediated epithelial-mesenchymal transition (EMT) through regulating the expression of epithelial (E)-cadherin, vimentin, and neuronal (N)-cadherin. Moreover, H19 was an example of a lncRNA that could function either as a tumor promoter or suppressor. An important part of this study was dedicated to reviewing signaling pathways involved in TC including extracellular-signal-regulated kinase (ERK) pathway and mitogen-activated protein kinase (ERK/MAPK), transforming growth factor-β/ (TGF-ß)/Smads, the Janus kinase/signal transducers and activators of transcription (JAK/STAT), P53, as well as other pathways. Conclusion: Briefly, this study provided an overview of the current understanding of the function of lncRNA and micro RNAs (miRNAs) along with their interactions in TC.

Introduction: In recent years, resting-state functional magnetic resonance imaging (rsfMRI) has been increasingly used as a noninvasive and practical method in different areas of neuroscience and psychology for recognizing brain’s mechanism as well as diagnosing neurological diseases. In this work, we use rs-fMRI data for diagnosing Alzheimer's disease. Materials and Methods: To do that, by using the rs-fMRI of a patient, we computed the time series of some anatomical regions and then applied the Latent Low Rank Representation method to extract suitable features. Next, based on the extracted features, we apply a Support Vector Machine (SVM) classifier to determine whether the patient belongs to a healthy category, mild stage of the disease or Alzheimer's stage. Results: The obtained classification accuracy for the proposed method is more than 97.5%. Conclusion: We performed different experiments on a database of rs-fMRI data containing the images of 43 healthy subjects, 36 mild cognitive impairment patients and 32 Alzheimer’s patients and the obtained results demonstrated that the best performance is achieved when the SVM with Gaussian kernel and the features of only 7 regions were used.

Background: Scanning Laser Ophthalmoscope (SLO) image can be used to detect retinal diseases. However detecting retinal area is a major task as retina artefacts such as eyelashes and eyelids are also captured. Huge part of retina can be viewed if it is done with the help of encroachment of SLO.Vision loss can be avoided with the help of retinal disease treatment. In olden days retinal diseases are recognized using manual techniques. Alteration of zooming and contrast are imparted by Optometrists and ophthalmologists. It is done to deduce images and diagnose results based on familiarity and domain knowledge. These diagnostic methods are always a time consuming process. Thus execution time can be reduced using mechanical examination of retinal images. It is better to glimpse at the images which could screen more patients and more unswerving diagnoses can be given in a time efficient manner. Scanning Laser Ophthalmoscope images gives the outcome of 2-D retinal scans. However it contains artefacts such as eyelids and eyelashes along with true retinal area. So the main confront is to eliminate these artefacts from the captured retinal image. Objective: Scanning Laser Ophthalmoscope (SLO) image can be used to detect retinal diseases. However detecting retinal area is a major task as retina artefacts such as eyelashes and eyelids are also captured. Huge part of retina can be viewed if it is done with the help of encroachment of SLO. In this paper our novel technique helps in detecting the true retinal area based on image processing techniques. To the SLO image two dimensional Variational Mode Decomposition (VMD) is applied. Methods: In this paper our novel technique helps in detecting the true retinal area based on image processing techniques. To the SLO image two dimensional Variational Mode Decomposition (VMD) is applied. As a result of this different modes are obtained. Mode 1 is chosed as it has high frequency. Then mode1 is pre-processed using median filtering. After this preprocessed mode1 image is grouped into pixels based on regional size and compactness called superpixels. Superpixels are generated to reduce complexity. Superpixel merging is done subsequent to Superpixel generation. It is done to reduce further difficulty and to enhance the speed. From the merged superpixels feature generation is performed using Regional, Gradient and textural features. It is done to eliminate artefacts and to detect the retinal area. Also feature selection will reduce the processing time and increase the speed. A classifier is constructed using Adaptive Network Fuzzy Inference System (ANFIS) for classification of features and its performance is compared with Artificial Neural Network (ANN). Results: By this novel approach we got a classification accuracy of 98.5%. Conclusion: Thus 2D-VMD gives six different modes. Based on high frequency mode1 is chosen. This further makes the process easier and it helps to achieve accuracy level higher. ANFIS is able to achieve higher accuracy when compared with ANN. Using ANFIS 98.5.