Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB.

BACKGROUND: Endothelial healing after deployment of cardiovascular devices is particularly important in the context of clinical outcome. It is therefore of great interest to develop tools for a precise prediction of endothelial growth after injury in the process of implant deployment. For experimental investigation of re-endothelialization in vitro cell migration assays are routinely used. However, semi-automatic analyses of live cell images are often based on gray value distributions and are as such limited by image quality and user dependence. The rise of deep learning algorithms offers promising opportunities for application in medical image analysis. Here, we present an intelligent cell detection (iCD) approach for comprehensive assay analysis to obtain essential characteristics on cell and population scale. RESULTS: In an in vitro wound healing assay, we compared conventional analysis methods with our iCD approach. Therefore we determined cell density and cell velocity on cell scale and the movement of the cell layer as well as the gap closure between two cell monolayers on population scale. Our data demonstrate that cell density analysis based on deep learning algorithms is superior to an adaptive threshold method regarding robustness against image distortion. In addition, results on cell scale obtained with iCD are in agreement with manually velocity detection, while conventional methods, such as Cell Image Velocimetry (CIV), underestimate cell velocity by a factor of 0.5. Further, we found that iCD analysis of the monolayer movement gave results just as well as manual freehand detection, while conventional methods again shows more frayed leading edge detection compared to manual detection. Analysis of monolayer edge protrusion by ICD also produced results, which are close to manual estimation with an relative error of 11.7%. In comparison, the conventional Canny method gave a relative error of 76.4%. CONCLUSION: The results of our experiments indicate that deep learning algorithms such as our iCD have the ability to outperform conventional methods in the field of wound healing analysis. The combined analysis on cell and population scale using iCD is very well suited for timesaving and high quality wound healing analysis enabling the research community to gain detailed understanding of endothelial movement.

Intradermal influenza vaccination of healthy adults using a new microinjection system: a 3-year randomised controlled safety and immunogenicity trial.

BACKGROUND: Intradermal vaccination provides direct and potentially more efficient access to the immune system via specialised dendritic cells and draining lymphatic vessels. We investigated the immunogenicity and safety during 3 successive years of different dosages of a trivalent, inactivated, split-virion vaccine against seasonal influenza given intradermally using a microinjection system compared with an intramuscular control vaccine. METHODS: In a randomised, partially blinded, controlled study, healthy volunteers (1150 aged 18 to 57 years at enrollment) received three annual vaccinations of intradermal or intramuscular vaccine. In Year 1, subjects were randomised to one of three groups: 3 microg or 6 microg haemagglutinin/strain/dose of inactivated influenza vaccine intradermally, or a licensed inactivated influenza vaccine intramuscularly containing 15 microg/strain/dose. In Year 2 subjects were randomised again to one of two groups: 9 microg/strain/dose intradermally or 15 microg intramuscularly. In Year 3 subjects were randomised a third time to one of two groups: 9 microg intradermally or 15 microg intramuscularly. Randomisation lists in Year 1 were stratified for site. Randomisation lists in Years 2 and 3 were stratified for site and by vaccine received in previous years to ensure the inclusion of a comparable number of subjects in a vaccine group at each centre each year. Immunogenicity was assessed 21 days after each vaccination. Safety was assessed throughout the study. RESULTS: In Years 2 and 3, 9 microg intradermal was comparably immunogenic to 15 microg intramuscular for all strains, and both vaccines met European requirements for annual licensing of influenza vaccines. The 3 microg and 6 microg intradermal formulations were less immunogenic than intramuscular 15 microg. Safety of the intradermal and intramuscular vaccinations was comparable in each year of the study. Injection site erythema and swelling was more common with the intradermal route. CONCLUSION: An influenza vaccine with 9 microg of haemagglutinin/strain given using an intradermal microinjection system showed comparable immunogenic and safety profiles to a licensed intramuscular vaccine, and presents a promising alternative to intramuscular vaccination for influenza for adults younger than 60 years. TRIAL REGISTRATION: (Clinicaltrials.gov) NCT00703651.