Depression is a major depressive disorder characterized by persistent sadness and a sense of worthlessness, as well as a loss of interest in pleasurable activities, which leads to a variety of physical and emotional problems. It is a worldwide illness that affects millions of people and should be detected at an early stage to prevent negative effects on an individual's life. Electroencephalogram (EEG) is a non-invasive technique for detecting depression that analyses brain signals to determine the current mental state of depressed subjects. In this study, we propose a method for automatic feature extraction to detect depression by first constructing a graph from the dataset where the nodes represent the subjects in the dataset and where the edge weights obtained using the Euclidean distance reflect the relationship between them. The Node2vec algorithmic framework is then used to compute feature representations for nodes in a graph in the form of node embeddings ensuring that similar nodes in the graph remain near in the embedding. These node embeddings act as useful features which can be directly used by classification algorithms to determine whether a subject is depressed thus reducing the effort required for manual handcrafted feature extraction. To combine the features collected from the multiple channels of the EEG data, the method proposes three types of fusion methods: graph-level fusion, feature-level fusion, and decision-level fusion. The proposed method is tested on three publicly available datasets with 3, 20, and 128 channels, respectively, and compared to five state-of-the-art methods. The results show that the proposed method detects depression effectively with a peak accuracy of 0.933 in decision-level fusion, which is the highest among the state-of-the-art methods.
- MeSH
- algoritmy MeSH
- deprese diagnóza MeSH
- depresivní porucha unipolární * diagnóza MeSH
- elektroencefalografie MeSH
- lidé MeSH
- rozhraní mozek-počítač * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
The corneal endothelium plays a key role in maintaining corneal transparency. Its dysfunction is currently treated with penetrating or lamellar keratoplasty. Advanced cell therapy methods seek to address the persistent global deficiency of donor corneas by enabling the renewal of the endothelial monolayer with tissue-engineered grafts. This review provides an overview of recently published literature on the preparation of endothelial grafts for transplantation derived from cadaveric corneas that have developed over the last decade (2010-2021). Factors such as the most suitable donor parameters, culture substrates and media, endothelial graft storage conditions, and transplantation methods are discussed. Despite efforts to utilize alternative cellular sources, such as induced pluripotent cells, cadaveric corneas appear to be the best source of cells for graft preparation to date. However, native endothelial cells have a limited natural proliferative capacity, and they often undergo rapid phenotype changes in ex vivo culture. This is the main reason why no culture protocol for a clinical-grade endothelial graft prepared from cadaveric corneas has been standardized so far. Currently, the most established ex vivo culture protocol involves the peel-and-digest method of cell isolation and cell culture by the dual media method, including the repeated alternation of high and low mitogenic conditions. Culture media are enriched by additional substances, such as signaling pathway (Rho-associated protein kinase, TGF-β, etc.) inhibitors, to stimulate proliferation and inhibit unwanted morphological changes, particularly the endothelial-to-mesenchymal transition. To date, this promising approach has led to the development of endothelial grafts for the first in-human clinical trial in Japan. In addition to the lack of a standard culture protocol, endothelial-specific markers are still missing to confirm the endothelial phenotype in a graft ready for clinical use. Because the corneal endothelium appears to comprise phenotypically heterogeneous populations of cells, the genomic and proteomic expression of recently proposed endothelial-specific markers, such as Cadherin-2, CD166, or SLC4A11, must be confirmed by additional studies. The preparation of endothelial grafts is still challenging today, but advances in tissue engineering and surgery over the past decade hold promise for the successful treatment of endothelial dysfunctions in more patients worldwide.
- MeSH
- antiportéry metabolismus MeSH
- endoteliální buňky transplantace MeSH
- lidé MeSH
- proteiny přenášející anionty metabolismus MeSH
- proteomika MeSH
- rohovka MeSH
- rohovkový endotel * metabolismus transplantace MeSH
- transplantace rohovky * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- přehledy MeSH
Wireless capsule endoscopy (WCE) is one of the most efficient methods for the examination of gastrointestinal tracts. Computer-aided intelligent diagnostic tools alleviate the challenges faced during manual inspection of long WCE videos. Several approaches have been proposed in the literature for the automatic detection and localization of anomalies in WCE images. Some of them focus on specific anomalies such as bleeding, polyp, lesion, etc. However, relatively fewer generic methods have been proposed to detect all those common anomalies simultaneously. In this paper, a deep convolutional neural network (CNN) based model 'WCENet' is proposed for anomaly detection and localization in WCE images. The model works in two phases. In the first phase, a simple and efficient attention-based CNN classifies an image into one of the four categories: polyp, vascular, inflammatory, or normal. If the image is classified in one of the abnormal categories, it is processed in the second phase for the anomaly localization. Fusion of Grad-CAM++ and a custom SegNet is used for anomalous region segmentation in the abnormal image. WCENet classifier attains accuracy and area under receiver operating characteristic of 98% and 99%. The WCENet segmentation model obtains a frequency weighted intersection over union of 81%, and an average dice score of 56% on the KID dataset. WCENet outperforms nine different state-of-the-art conventional machine learning and deep learning models on the KID dataset. The proposed model demonstrates potential for clinical applications.
Destruction or dysfunction of limbal epithelial stem cells (LESCs) leads to unilateral or bilateral limbal stem cell deficiency (LSCD). Fifteen years have passed since the first transplantation of ex vivo cultivated oral mucosal epithelial cells (COMET) in humans in 2004, which represents the first use of a cultured non-limbal autologous cell type to treat bilateral LSCD. This review summarizes clinical outcomes from COMET studies published from 2004 to 2019 and reviews results with emphasis on the culture methods by which grafted cell sheets were prepared.
- MeSH
- autologní transplantace MeSH
- epitelové buňky MeSH
- kultivované buňky MeSH
- lidé MeSH
- limbus corneae * MeSH
- nemoci rohovky * terapie MeSH
- rohovkový epitel * MeSH
- transplantace buněk MeSH
- transplantace kmenových buněk MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- přehledy MeSH