Burn debridement is a challenging technique that requires significant skill to identify regions requiring excision and appropriate excision depth. A machine learning tool is being developed in order to assist surgeons by providing a quantitative assessment of burn-injured tissue. Three noninvasive optical imaging techniques capable of distinguishing between four kinds of tissue-healthy skin, viable wound bed, deep burn, and shallow burn-during serial burn debridement in a porcine model are presented in this paper. The combination of all three techniques considerably improves the accuracy of tissue classification, from 0.42 to almost 0.77.
The process of burn debridement is a challenging technique requiring significant skills to identify the regions that need excision and their appropriate excision depths. In order to assist surgeons, a machine learning tool is being developed to provide a quantitative assessment of burn-injured tissue. This paper presents three non-invasive optical imaging techniques capable of distinguishing four kinds of tissue-healthy skin, viable wound bed, shallow burn, and deep burn-during serial burn debridement in a porcine model. All combinations of these three techniques have been studied through a k-fold cross-validation method. In terms of global performance, the combination of all three techniques significantly improves the classification accuracy with respect to just one technique, from 0.42 up to more than 0.76. Furthermore, a non-linear spatial filtering based on the mode of a small neighborhood has been applied as a post-processing technique, in order to improve the performance of the classification. Using this technique, the global accuracy reaches a value close to 0.78 and, for some particular tissues and combination of techniques, the accuracy improves by 13%.
Conventional multistatic radar systems using microwave and millimeter-wave (mm-wave) frequencies seek to reconstruct the target in the imaging domain, employing many transmitting and receiving antenna elements. These systems are suboptimal, in that they do not take into consideration the large mutual information existing between the measurements. This work reports a new mm-wave radar system for high sensing capacity applications. The system is composed of a Compressive Reflector Antenna (CRA), whose surface is specially tailored by digitized Metamaterial Absorbers (MMAs). The MMA elements are designed to have a highly frequency-dispersive response in the operating band of the radar. This enables the CRA to create highly uncorrelated spatial and spectral codes in the imaging region. A semi-analytic method based on Drude-Lorentz model is used to approximate the reflection response of the MMAs. The performance of the developed radar system is evaluated in active mm-wave sensing systems by imaging PEC scatterers and an extended human-size model in the near-field of the radar. A computational method based on physical optics is established for solving the numerical examples. For reconstructing the image using compressive sensing techniques, a norm-1 regularized iterative algorithm based on the Alternating Direction Method of Multipliers (ADMM) and a Nesterov-based algorithm (NESTA) were applied.Index Terms-Compressive reflector antenna, millimeter-wave imaging, metamaterial absorber, coded aperture.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.