No abstract

Tissue stroma is responsible for extracellular matrix (ECM) formation and secretion of factors that coordinate the behaviour of the surrounding cells through the microenvironment created. It's inability to spontaneously regenerate makes it a good candidate for research studies such as testing various tissue engineered products capable of replacing the stroma in order to assure normal tissue regeneration and function. In this study, a bioactive stroma was obtained considering two main components: 1) the artificial ECM formed using atelocollagen-oxidized polysaccharides hydrogels in which the polysaccharide compound (oxidised gellan or pullulan) has the role of crosslinker and 2) encapsulated stromal cells (dermal fibroblasts, ovarian theca-interstitial and granulosa cells). The cell-hosting ability of the hydrogels is demonstrated by a good diffusion of globular proteins (albumin) while the fibrillar morphology proves to be optimal for cell adhesion. These structural properties and cytocompatibility of the components maintain good cell viability and cell encapsulation for more than 12 days. Nevertheless, the results indicate some differences favouring the gellan crosslinked hydrogels. Ovarian stromal cells functionality was maintained as indicated by hormone secretion, confirming cell-cell signalling in encapsulated and co-culture conditions. In vivo implantation shows the regenerative potential of the cellpopulated hydrogels as they are integrated into the natural tissue. The possibility of cryopreserving the hydrogel-cell system, while maintaining both cell viability and hydrogel structural integrity underlines the potential of these ready-to-use hydrogels as bioactive stroma for multipurpose tissue regeneration.

Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.

No abstract