What is it about?
Automated algorithms for automated detection of melanoma; A new strategy to reduce these costs is to reduce the time to find the right diagnosis by providing the experts (physicians, surgeons, but also nurses) with additional important information about the patient that helps them to avoid other expensive and time-consuming diagnostic methods. Spectral imaging sensors can acquire hyper-spectral images, images with an additional spectral dimension to the spatial information, providing not only the brightness (monochrome imaging = one channel) or color (RGB-imaging = 3 channels) but an entire spectrum for each pixel (10 up to 1000 bands). This allows acquiring images containing valuable information about the molecular or atomic composition and structure of the observed materials. Recent advances in sensor technology, calibration procedures, hyper-spectral classification and post-processing together with a large and increasing number of outstanding research projects indicate the high potential of spectral imaging as an emerging technology. Applications range from material inspection, analysis and classification tasks to medical diagnosis systems. Thus, spectral imaging opens a wide field of applications for scientists and engineers in medicine, agriculture, pharmaceutical, manufacturing, recycling, chemistry, forensic medicine and military.
Featured Image
Why is it important?
The costs for the health systems-world wide-explode and it seems that this problem will not be solved easily in the next time.
Perspectives
Read the Original
This page is a summary of: Comparative study of maximum likelihood and spectral angle mapper algorithms used for automated detection of melanoma, Skin Research and Technology, July 2014, Wiley,
DOI: 10.1111/srt.12160.
You can read the full text:
Contributors
The following have contributed to this page