Identification of after-culture microbial species using a low-cost fully automated system would strongly benefit Low Income Countries, as traditional culture plate reading for the purpose of species identification currently requires trained professionals and remains mostly manual, while more recent automated identification methods are costly. Our application is the label-free identification of uropathogens from bacterial colonies images directly on a non-chromogenic culture medium. With a frugal innovation mindset, we are developing a simple diagnostic system based on a filter wheel and a smartphone-driven CMOS camera. We are reporting performance of identification for true clinical samples and compare it to samples issued from a strain collection. Also, the capability to classify the five most-prevalent uropathogens (MPU) in presence of low-prevalent uropathogens (LPU) is evaluated. Two machine learning classification approaches are compared: classical or probabilistic support vector machine SVM (Platt method) using solely a 1-D vector of intensities without any morphological predictors at this stage. Some apparent shortcomings of the logistic regression approach are highlighted for the probabilistic SVM approach.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.