The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared.Aims
Methods
Recent studies suggested that both the soluble protein of the mesenchymal stromal cell (MSC) secretome, as well as the secreted extracellular vesicles (EVs) promote bone regeneration. However, there is limited knowledge of the changes in MSC secretome vesicular fraction during aging. We therefore aimed to characterize the release profiles and cargo of EVs from MSCs of different chronological ages. Conditioned medium (CM) was collected from 13 bone marrow MSC strains (20-89 years) and from one MSC strain derived from human induced pluripotent stem cells (iPSCs). The EV-containing fraction was enriched with ultracentrifugation. The number of particles in the CM was evaluated by nanoparticle tracking analysis (NTA), and the number of EVs was evaluated by flow cytometry (FC) after staining with cell-mask-green and anti-CD81 antibody. EV cargo analysis was conducted using next-generation sequencing (NGS). Our data confirmed the release of EVs from all MSC strains used in the study. There were no correlations between the number of particles and the number of EVs released in the CM, and between the number of EVs released and the strain age. Nevertheless, some of the lowest concentrations of EVs were found in the CM of strains over 70 years of age, which exhibited a low/absent chondrogenic and osteogenic differentiation potential. In contrast, iPSC-MSCs, which exhibited a high growth and three-lineage differentiation potential, released a similar amount of EVs as the best performing bone marrow MSC strain. NGS analysis identified several microRNAs that were significantly enriched in EVs of young MSC strains exhibiting low senescence, and those that were enriched in EVs of strains exhibiting high differentiation potentials. Gender had no influence on microRNA profiles in EVs or releasing MSCs. Taken together, our data provides new insights into the properties of MSC vesicular secretome and its therapeutic potential during aging.
