Chapter 10 Figure 10.3 Mean spectra per tissue type 154 Average tissue spectra for thyroid (red), parathyroid (green) and adipose tissue (blue). Dashed lines in the corresponding colors indicate the respective standard deviations. Classification of spectral data in Si‐sensor range From the 36 extracted features (see Figure 10.2) 11 were located within the silicon detection range. Given the study sample of an average of 20 spots per tissue type, inclusion of maximum 2 features is allowed. Binary logistic regression identified gradients Ft3 (B2 – B6) and Ft36 (650 – 700 nm) as most promising combination for differentiation of parathyroid from surrounding adipose tissue. Gradient Ft36 (650 ‐ 700 nm) solely, also appeared to be the best distinctive feature for differentiation of parathyroid from thyroid tissue. Figure 10.4A shows a scatter plot (Ft36 and Ft3) for classification of parathyroid in adipose surrounding. Figure 10.4B shows a boxplot (Ft 36) for classification of parathyroid in thyroid surrounding. The quantitative results of classification performance are listed in Table 10.2. Leave‐one‐ out cross‐validation (LOO CV) is based on Si‐sensor range data from thyroid and parathyroid surgery for train and test purposes.
proefschrift_Schols_SLV
To see the actual publication please follow the link above