U-DAVIS-Deep Learning Based Arm Venous Image Segmentation Technique for Venipuncture.

Arm Venous Segmentation plays a crucial role in smart venipuncture. The difficulties faced in locating veins for intravenous procedures can be diminished using computer vision for vein imaging. To facilitate this, a high-resolution dataset consisting of arm images was curated and has been presented in this study. Leveraging the ability of Near Infrared Imaging to easily detect veins, ambient lighting conditions were created inside a small enclosure to capture the images. The acquired images were annotated to create the corresponding masks for the dataset. To extend the scope and assert the usability of the dataset, the images, and corresponding masks were used to train an image segmentation model. In addition to using basic preprocessing and image augmentation based techniques, a U-Net based algorithmic architecture has been used to facilitate the task of segmentation. Subsequently, the results of performing image segmentation after applying the preprocessing methods have been compared using various evaluation metrics and have been visualised in the study. Furthermore, the possible applications of the presented dataset have been investigated in the study.

Face mask detection in COVID-19: a strategic review.

With the outbreak of the Coronavirus Disease in 2019, life seemed to be had come to a standstill. To combat the transmission of the virus, World Health Organization (WHO) announced wearing of face mask as an imperative way to limit the spread of the virus. However, manually ensuring whether people are wearing face masks or not in a public area is a cumbersome task. The exigency of monitoring people wearing face masks necessitated building an automatic system. Currently, distinct methods using machine learning and deep learning can be used effectively. In this paper, all the essential requirements for such a model have been reviewed. The need and the structural outline of the proposed model have been discussed extensively, followed by a comprehensive study of various available techniques and their respective comparative performance analysis. Further, the pros and cons of each method have been analyzed in depth. Subsequently, sources to multiple datasets are mentioned. The several software needed for the implementation are also discussed. And discussions have been organized on the various use cases, limitations, and observations for the system, and the conclusion of this paper with several directions for future research.

Applications and Challenges in Healthcare Big Data: A Strategic Review.

Big data has been a topic of interest for many researchers and industries for the past few decades. Due to the exponential growth of technology, a tremendous amount of data is generated every minute. This article provides a strategic review of big data in the healthcare sector. In particular, this article highlights various applications and issues faced by the healthcare industry using big data by evaluating various journal articles between 2016 and 2021. Multiple issues related to data mining, storing, analyzing, and sharing of big data in healthcare, briefly summarizing deep-learning-based tools available for big data analytics, have been covered in this article. This article aims to benefit the research community by summarizing various research tools and processes available today to manage big data in healthcare.

Prediction of face age progression with generative adversarial networks.

Face age progression, goals to alter the individual's face from a given face image to predict the future appearance of that image. In today's world that demands more security and a touchless unique identification system, face aging attains tremendous attention. The existing face age progression approaches have the key problem of unnatural modifications of facial attributes due to insufficient prior knowledge of input images and nearly visual artifacts in the generated output. Research has been continuing in face aging to handle the challenge to generate aged faces accurately. So, to solve the issue, the proposed work focuses on the realistic face aging method using AttentionGAN and SRGAN. AttentionGAN uses two separate subnets in a generator. One subnet for generating multiple attention masks and the other for generating multiple content masks. Then attention mask is multiplied with the corresponding content mask along with an input image to finally achieve the desired results. Further, the regex filtering process is performed to separates the synthesized face images from the output of AttentionGAN. Then image sharpening with edge enhancement is done to give high-quality input to SRGAN, which further generates the super-resolution face aged images. Thus, presents more detailed information in an image because of its high quality. Moreover, the experimental results are obtained from five publicly available datasets: UTKFace, CACD, FGNET, IMDB-WIKI, and CelebA. The proposed work is evaluated with quantitative and qualitative methods, produces synthesized face aged images with a 0.001% error rate, and is also evaluated with the comparison to prior methods. The paper focuses on the various practical applications of super-resolution face aging using Generative Adversarial Networks (GANs).

Deep learning-based bird eye view social distancing monitoring using surveillance video for curbing the COVID-19 spread.

The escalating transmission intensity of COVID-19 pandemic is straining the healthcare systems worldwide. Due to the unavailability of effective pharmaceutical treatment and vaccines, monitoring social distancing is the only viable tool to strive against asymptomatic transmission. Pertaining to the need of monitoring the social distancing at populated areas, a novel bird eye view computer vision-based framework implementing deep learning and utilizing surveillance video is proposed. This proposed method employs YOLO v3 object detection model and uses key point regressor to detect the key feature points. Additionally, as the massive crowd is detected, the bounding boxes on objects are received, and red boxes are also visible if social distancing is violated. When empirically tested over real-time data, proposed method is established to be efficacious than the existing approaches in terms of inference time and frame rate.

Alteration of Neurotrophic Factors After Transplantation of Bone Marrow Derived Lin-ve Stem Cell in NMDA-Induced Mouse Model of Retinal Degeneration.

Retinal ganglion cell layer (RGCs) is one of the important layers of retina, depleted in Glaucoma. Loss of RGC neurons is a major cellular mechanism involved in its pathogenesis resulting in severe vision loss. Stem cell therapy has emerged as a potential strategy to arrest the apoptotic loss of RGCs and also replace the degenerative cells in damaged retina. Here, we have investigated the incorporation and survival of mouse bone marrow derived Lin-ve stem cells in N-methyl-d-aspartate (NMDA)-induced mouse model of retinal degeneration. Two days after intravitreal injection of NMDA (100 mM) showed significant decrease in ganglion cell number and increase in TUNEL positive apoptotic cells in retinal layers. The injury was further characterized by immunohistochemical expression of Brn3b, GFAP, Bcl2, pCREB, CNTF, GDNF, and BDNF in retinal layers. Lin-ve cells (100,000 dose) were intravitreally transplanted after 2 days of injury and evaluated after 7, 14, and 21 days of transplantation. Transplanted cells were found to have migrated from intravitreal space and incorporated into injured retina at 7, 14, and 21 days post-transplantation. At 21 days Brn3b, CNTF, and BDNF expression was found to be upregulated whereas GDNF was downregulated when compared to respective injury time points. Molecular data showed decrease in the expression of Brn3b, BDNF, CNTF, and GDNF post transplantation when compared with injury groups. This study reveals that Lin-ve stem cells may exert neuroprotective effect in damaged retina mediated by participation of neurotrophic factors induced by stem cell transplantation at the site of injury. J. Cell. Biochem. 118: 1699-1711, 2017. © 2016 Wiley Periodicals, Inc.

Does DcR1 (TNF-related apoptosis-inducing-ligand Receptor 3) have any role in human AMD pathogenesis?

It has been postulated that there is a link between age related degenerative diseases and cancer. The TNF-related apoptosis-inducing ligand (TRAIL) has been shown to selectively kill tumor cells by binding to pro-apoptotic and anti-apoptotic receptors. Our aim was to study the levels of anti-apoptotic receptor (DcR1) in age related macular degeneration (AMD) and controls. AMD patients (115) were classified into two groups: Dry and Wet AMD. Wet AMDs were further classified into occult, predominant classic and minimal classic. 61 healthy individuals were recruited as normal controls. After normalization with total protein, DcR1 levels were analyzed by ELISA. Mann Whitney U-statistic was used for analysis of DcR1 ELISA results. We have observed DcR1 levels in serum sample which were significantly lower in AMD patients as compared to controls (p = 0.001). On the other hand, we did not find difference in DcR1 levels between wet and dry AMD. The present study defines the plausible role of DcR1 in AMD pathology signifying a new therapeutic target for AMD.

Characterization of Lin-ve CD34 and CD117 cell population reveals an increased expression in bone marrow derived stem cells.

The purpose of the study was to evaluate the expression of CD45, CD34, Sca-1 and CD117 in mouse bone marrow, Lin-ve and Lin+ve population. Bone marrow cells were isolated from C57/BL6J mouse and mononuclear population was separated from rest of the cell population. With the help of Magnetic associated cell sorter (MACS), Linve and Lin+ve cells were separated from the bone marrow. The expression of CD45, CD34, Sca1 and CD117 was evaluated in bone marrow, Lin-ve and Lin+ve population by flow cytometry. We found a significant increase in the expression of CD34 and CD117 in Lin-ve as compared to the bone marrow and Lin+ve population. These findings suggest that Lin-ve population has higher expression of stem cell progenitor markers and could be useful for tissue repair and regeneration.

The emerging role of stem cells in ocular neurodegeneration: hype or hope?

Affecting over a hundred million individuals worldwide, retinal diseases are among the leading causes of irreversible visual impairment and blindness. Thus, an appropriate study models, especially animal models, are essential to furthering our understanding of the etiology, pathology, and progression of these diseases. In this review, we provide an overview of retinal disorders in the context of biotherapeutic approaches in these disorders.