In our study, we developed an automated approach for generating quantitative image analysis metrics (imaging biomarkers) that are then analyzed with a set of 13 machine learning algorithms to generate an overall risk score that is called a Q-score. This approach yielded 98% sensitivity and 36% specificity for melanoma detection, approaching sensitivity/specificity of expert lesion evaluation. Importantly, we found strong spectral dependence of many imaging biomarkers in blue or red color channels, suggesting the need to optimize spectral evaluation of pigmented lesions.
In this groundbreaking talk, biophotonic engineer Daniel Gareau shows us new technology that depicts cellular imaging, in a bid to make it more accessible to doctors. By shifting the visual language to something more familiar, this technology may have the potential of positively impacting doctors' daily practice.
A stage-scanning, line-scanning confocal microscope is under development for rapid, noninvasive imaging of whole biological tissue.
In this groundbreaking talk, biophotonic engineer Daniel Gareau shows us new technology that depicts cellular imaging, in a bid to make it more accessible to doctors. By shifting the visual language to something more familiar, this technology may have the potential of positively impacting doctors' daily practice.