Parathyroid differentiation during thyroid and parathyroid surgery by spectroscopy problem, we identified the most distinctive features, for classification of parathyroid in relation to surrounding adipose tissue or adjacent thyroid tissue, by using binary logistic regression (SPSS Inc., Chicago, IL, USA) for both wavelength regions separately. This is a statistical technique that allows the prediction of categorical dependent variables (here the tissue type: parathyroid or adipose/thyroid) using a set of independent variables (here the 36 spectral features)30. In accordance with our previous report on classifying nerve tissue within adipose surroundings23, we trained a support vector machine (SVM) classifier31 which attempts to find an optimum line to separate the training data groups with a minimum risk29. To estimate classification performance and to prevent overly optimistic results20,32,33, we implemented a cross–validation (CV) approach. With a goal to obtain the classification accuracy as a performance measure, the data set is divided into a training set (to train the classifier) and a test set (to validate the classifier). The CV approach uses leave‐one‐out (LOO) validation of the collected parathyroid and adipose/thyroid hyperspectral data. This approach utilizes the same data set for both training and testing purposes and is very useful in cases of a relatively small data sample. In‐house developed classifiers (using MATLAB environment Version 7.7.0, MathWorks Inc., Natick, Massachussetts, USA) were used to estimate the classification performance by calculating sensitivity, specificity, positive predictive value, negative predictive value and accuracy for both wavelength regions (i.e., Si‐sensor and InGaAs‐sensor detection range). 151
proefschrift_Schols_SLV
To see the actual publication please follow the link above